Lung image registration, lesion positioning method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a lung image registration, lesion positioning method and device, electronic equipment and storage medium, and relates to the technical field of DR image processing. Wherein, the method comprises: acquiring multiple left lung images and / or multiple right lung images at multiple moments in the breathing process; registering the left lung images at adjacent moments in the multiple left lung images respectively to obtain a plurality of first registration images corresponding thereto; registering the right lung images at adjacent moments in the multiple right lung images respectively to obtain a plurality of second registration images corresponding thereto; determining a first fixed image and a second fixed image in the multiple left lung images and the multiple right lung images respectively; registering any other first registration image except the first registration image corresponding to the first fixed image to the first fixed image respectively, and registering any other second registration image except the second registration image corresponding to the second fixed image to the second fixed image respectively. Lung image registration and lesion positioning can be achieved.

Description

Technical Field

[0001] This disclosure relates to the field of DR image processing technology, and in particular to a method and apparatus for lung image registration and lesion localization, as well as electronic equipment and storage medium. Background Technology

[0002] Digital X-ray (DR) imaging can provide high-resolution and real-time X-ray images (two-dimensional DR images) and has been widely used in examinations of the skeletal system, chest, and dentistry, such as fracture diagnosis, lung disease screening, and dental X-rays.

[0003] Medical image registration is based on "aligning" human images taken at different times or images taken at the same time by different machines (DR, MRI, CT, etc.) to obtain complementary information and better diagnose patients.

[0004] Currently, DR imaging should be widely used in lung imaging or routine physical examinations in primary healthcare institutions. Compared with other static images, such as brain images or other skeletal images, lung images exhibit non-linear deformation during respiration. In particular, for multiple DR lung images taken at different times during respiration, the registration of multiple DR lung images taken at different times during respiration is especially difficult due to the unique nature of DR lung imaging, which involves multiple chest tissues superimposed onto a single two-dimensional image and the irregular movement of the lungs during respiration. This, in turn, affects further analysis or diagnosis of lung diseases. Summary of the Invention

[0005] This disclosure presents a method and device for lung image registration and lesion localization, as well as an electronic device and storage medium.

[0006] According to one aspect of this disclosure, a lung image registration method is provided, comprising:

[0007] Acquire multiple left lung images and / or multiple right lung images at multiple time points during the breathing process; wherein the multiple left lung images and / or the multiple right lung images are configured as two-dimensional DR images; register the left lung images at adjacent time points in the multiple left lung images to obtain multiple corresponding first registered images; and / or register the right lung images at adjacent time points in the multiple right lung images to obtain multiple corresponding second registered images; determine a first fixed image and / or a second fixed image in the multiple left lung images and / or the multiple right lung images; register any first registered image other than the first registered image corresponding to the first fixed image to the first fixed image, and / or register any second registered image other than the second registered image corresponding to the second fixed image to the second fixed image.

[0008] Preferably, before acquiring multiple left lung images and / or multiple right lung images at multiple moments during the breathing process, two-dimensional DR left lung images and their corresponding first set position information and / or two-dimensional DR right lung images and their corresponding second set position information at multiple moments during the breathing process are acquired.

[0009] The two-dimensional DR left lung image and / or two-dimensional DR right lung image at multiple time points are cropped based on the first set location information and / or the second set location information, respectively, to obtain multiple corresponding left lung images and / or multiple right lung images.

[0010] Preferably, the method for determining the first predetermined position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process includes: detecting, respectively, multiple first highest point position information, multiple first lowest point position information, multiple first leftmost position information, and multiple first rightmost position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process; determining the first predetermined position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process based on the multiple first highest point position information, the multiple first lowest point position information, the multiple first leftmost position information, and the multiple first rightmost position information; and / or,

[0011] The method for detecting multiple first highest point position information, multiple first lowest point position information, multiple first leftmost position information, and multiple first rightmost position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process includes: acquiring multiple first mask images corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process; determining multiple corresponding left lung edge images based on the multiple first mask images; detecting multiple first highest point position information, multiple first lowest point position information, multiple first leftmost position information, and multiple first rightmost position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process based on the multiple left lung edge images; and / or,

[0012] The method for determining the first predetermined position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process based on the plurality of first highest point position information, the plurality of first lowest point position information, the plurality of first leftmost point position information, and the plurality of first rightmost point position information includes: extracting the ordinates of the plurality of first highest points and the plurality of first lowest points from the plurality of first highest point position information and the plurality of first lowest point position information respectively; determining the maximum value of the first ordinate corresponding to the plurality of first highest point ordinates and the minimum value of the first ordinate corresponding to the plurality of first lowest point ordinates; extracting the abscissas of the plurality of first leftmost points and the plurality of first rightmost points from the plurality of first leftmost point position information and the plurality of first rightmost point position information respectively; determining the minimum value of the first abscissa corresponding to the plurality of first leftmost abscissas and the maximum value of the first abscissa corresponding to the plurality of first rightmost abscissas; determining the first predetermined position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process according to the maximum value of the first ordinate, the minimum value of the first ordinate, the minimum value of the first abscissa, and the maximum value of the first abscissa; and / or,

[0013] The method for determining the first predetermined position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process based on the first maximum value of the first ordinate, the first minimum value of the first ordinate, the first minimum value of the first abscissa, and the first maximum value of the first abscissa includes: drawing two corresponding first y-axis perpendicular lines from the first maximum value of the first ordinate and the first minimum value of the first ordinate to the y-axis, and drawing two corresponding first x-axis perpendicular lines from the first minimum value of the first abscissa and the first maximum value of the first abscissa to the x-axis; configuring the intersection of the first y-axis perpendicular lines and the first x-axis perpendicular lines as the first predetermined position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process; and / or,

[0014] A method for determining second predetermined position information corresponding to two-dimensional DR right lung images at multiple moments during the respiratory process includes: detecting, respectively, multiple second highest point position information, multiple second lowest point position information, multiple second rightmost point position information, and multiple second rightmost point position information corresponding to the two-dimensional DR right lung images at multiple moments during the respiratory process; determining, based on the multiple second highest point position information, the multiple second lowest point position information, the multiple second rightmost point position information, and the multiple second rightmost point position information, the second predetermined position information corresponding to the two-dimensional DR right lung images at multiple moments during the respiratory process; and / or,

[0015] The method for detecting multiple second highest point position information, multiple second lowest point position information, multiple second rightmost point position information, and multiple second rightmost point position information corresponding to two-dimensional DR right lung images at multiple moments during the breathing process includes: acquiring multiple second mask images corresponding to the two-dimensional DR right lung images at multiple moments during the breathing process; determining multiple right lung edge images based on the multiple second mask images; detecting multiple second highest point position information, multiple second lowest point position information, multiple second rightmost point position information, and multiple second rightmost point position information corresponding to the two-dimensional DR right lung images at multiple moments during the breathing process based on the multiple right lung edge images; and / or,

[0016] The method for determining the second predetermined position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process based on the plurality of second highest point position information, the plurality of second lowest point position information, the plurality of second rightmost point position information, and the plurality of second rightmost point position information includes: extracting the ordinates of the plurality of second highest points and the plurality of second lowest points from the plurality of second highest point position information; determining the maximum value of the second ordinate corresponding to the plurality of second highest point ordinates, and determining the minimum value of the second ordinate corresponding to the plurality of second lowest point ordinates; extracting the plurality of second rightmost point abscissas from the plurality of second rightmost point position information and the plurality of second rightmost point abscissas from the plurality of second rightmost point position information; determining the minimum value of the second abscissa corresponding to the plurality of second rightmost point abscissas, and determining the maximum value of the second abscissa corresponding to the plurality of second rightmost point abscissas; determining the second predetermined position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process based on the maximum value of the second ordinate, the minimum value of the second ordinate, the minimum value of the second abscissa, and the maximum value of the second abscissa; and / or,

[0017] The method for determining the second predetermined position information corresponding to the two-dimensional DR right lung images at multiple moments during the breathing process based on the second maximum value of the second ordinate, the second minimum value of the second ordinate, the second minimum value of the second abscissa, and the second maximum value of the second abscissa includes: drawing two corresponding second y-axis perpendicular lines from the second maximum value of the second ordinate and the second minimum value of the second ordinate to the y-axis, and drawing two corresponding second x-axis perpendicular lines from the second minimum value of the second abscissa and the second maximum value of the second abscissa to the x-axis; configuring the intersection of the second y-axis perpendicular lines and the second x-axis perpendicular lines as the second predetermined position information corresponding to the two-dimensional DR right lung images at multiple moments during the breathing process; and / or,

[0018] A method for determining two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple moments during the respiratory process includes: detecting the costal margin boundary, lung apex boundary, and mediastinal and diaphragmatic edges of the left chest images and / or right chest images of the two-dimensional DR lung images at multiple moments during the respiratory process, respectively, to obtain two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple moments; or,

[0019] Obtain a pre-defined convolutional neural network segmentation model and DR lung region label images used to train the segmentation model; train the segmentation model using the DR lung region label images used to train the segmentation model; based on the trained segmentation model, segment the left and right lungs of the two-dimensional DR lung images at multiple time points during the breathing process to obtain two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple time points; and / or, the method for determining the DR lung region label images used to train the segmentation model includes: performing costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edge detection on the left chest images and / or right chest images of multiple DR lung region images respectively to obtain DR lung region label images corresponding to the multiple DR lung region images.

[0020] Preferably, the method of registering left lung images at adjacent time points in the plurality of left lung images to obtain a plurality of corresponding first registered images includes: obtaining a first registration model and its corresponding first setting rule; using the first registration model to register left lung images at adjacent time points in the plurality of left lung images; using the first setting rule to terminate the registration of left lung images at adjacent time points in the plurality of left lung images; and / or,

[0021] Wherein, the first parameter map of the first registration model is configured as an affine transformation; and / or,

[0022] Based on the configuration of the first parameter map of the first registration model as an affine transformation, one or more of the following transformations are further configured in the first parameter map: translation, rigid transformation, and B-spline; or, based on the configuration of the first parameter map of the first registration model as one or more of the following transformations: translation, rigid transformation, and B-spline, an affine transformation is further configured in the first parameter map; and / or,

[0023] Wherein, the first setting rule is configured as a first preset registration number and / or a first preset similarity; when the first setting rule is configured as the first preset registration number, if the first number of registrations of the left lung images at adjacent times in the multiple left lung images is greater than or equal to the first preset registration number, then the registration of the left lung images at adjacent times in the multiple left lung images ends; when the first setting rule is configured as the first preset similarity, the similarity of the left lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the first preset similarity, then the registration of the left lung images at adjacent times in the multiple left lung images ends.

[0024] When the first setting rule is configured with a first preset registration count and a first preset similarity, if the first number of registrations of the left lung images at adjacent times in the multiple left lung images is greater than or equal to the first preset registration count, then the registration of the left lung images at adjacent times in the multiple left lung images ends; if the first number of registrations of the left lung images at adjacent times in the multiple left lung images is greater than or equal to the first preset registration count, then the registration of the left lung images at adjacent times in the multiple left lung images ends; if the first number of registrations of the left lung images at adjacent times in the multiple left lung images is less than the first preset registration count, then the similarity of the left lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the first preset similarity, then the registration of the left lung images at adjacent times in the multiple left lung images ends; and / or,

[0025] The method for registering left lung images at adjacent time points in the plurality of left lung images using the first registration model includes: configuring the left lung image at the previous time point in the left lung images at adjacent time points as a first fixed left lung image; configuring the left lung image corresponding to the previous time point and the next time point in the adjacent time points as a first floating left lung image; registering the first floating left lung image to the first fixed left lung image using the first registration model; and / or,

[0026] The method for calculating the similarity of left lung images at adjacent time points during the registration process includes: performing erosion operations on a first fixed left lung image and a first floating left lung image during the registration process according to a set erosion pixel value, respectively, to obtain corresponding first fixed left lung eroded images and first floating left lung eroded images; obtaining a corresponding first fixed left lung boundary image based on the first fixed left lung image and the first fixed eroded left lung image; obtaining a corresponding first floating left lung boundary image based on the first floating left lung image and the first floating eroded left lung image; calculating the similarity between the first fixed left lung boundary image and the first floating left lung boundary image to obtain the similarity of left lung images at adjacent time points during the registration process; and / or,

[0027] A method for registering right lung images at adjacent time points in a plurality of right lung images to obtain corresponding plurality of second registered images includes: obtaining a second registration model and its corresponding second setting rule; using the second registration model to register right lung images at adjacent time points in the plurality of right lung images; using the second setting rule to terminate the registration of right lung images at adjacent time points in the plurality of right lung images; and / or,

[0028] Wherein, the second parameter map of the second registration model is configured as an affine transformation; and / or,

[0029] Based on the second parameter map of the second registration model being configured as an affine transformation, one or more of the following transformations are further configured in the second parameter map: translation, rigid transformation, and B-spline; or, based on the second parameter map of the second registration model being configured as one or more of the following transformations: translation, rigid transformation, and B-spline, an affine transformation is further configured in the second parameter map; and / or,

[0030] Wherein, the second setting rule is configured as a second preset registration number and / or a second preset similarity; when the second setting rule is configured as the second preset registration number, if the second number of registrations of the right lung images at adjacent times in the multiple right lung images is greater than or equal to the second preset registration number, then the registration of the right lung images at adjacent times in the multiple right lung images ends; when the second setting rule is configured as the second preset similarity, the similarity of the right lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the second preset similarity, then the registration of the right lung images at adjacent times in the multiple right lung images ends; when the second setting rule is configured as the second preset registration number and the second preset similarity, when the second setting rule is configured as the second preset... During the registration process, if the second registration count of right lung images at adjacent times in the multiple right lung images is greater than or equal to the second preset registration count, then the registration of right lung images at adjacent times in the multiple right lung images ends; if the second registration count of right lung images at adjacent times in the multiple right lung images is greater than or equal to the second preset registration count, then the registration of right lung images at adjacent times in the multiple right lung images ends; if the second registration count of right lung images at adjacent times in the multiple right lung images is less than the second preset registration count, then the similarity of right lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the second preset similarity, then the registration of right lung images at adjacent times in the multiple right lung images ends; and / or,

[0031] The method of registering right lung images at adjacent time points in the plurality of right lung images using the second registration model includes: configuring the right lung image at the previous time point in the adjacent right lung images as a second fixed right lung image; configuring the right lung image corresponding to the previous time point and the next time point in the adjacent right lung images as a second floating right lung image; registering the second floating right lung image to the second fixed right lung image using the second registration model; and / or,

[0032] The method for calculating the similarity of right lung images at adjacent time points during the registration process includes: performing erosion operations on the second fixed right lung image and the second floating right lung image during the registration process according to a set erosion pixel value, respectively, to obtain corresponding second fixed right lung eroded images and second floating right lung eroded images; obtaining corresponding second fixed right lung boundary images based on the second fixed right lung image and the second fixed eroded right lung image; obtaining corresponding second floating right lung boundary images based on the second floating right lung image and the second floating eroded right lung image; and calculating the similarity between the second fixed right lung boundary images and the second floating right lung boundary images to obtain the similarity of right lung images at adjacent time points during the registration process.

[0033] According to one aspect of this disclosure, a lung image registration device is provided, comprising:

[0034] The acquisition unit is used to acquire multiple images of the left lung and / or multiple images of the right lung at multiple moments during the breathing process; wherein the multiple images of the left lung and / or the multiple images of the right lung are configured as two-dimensional DR images;

[0035] The first registration unit is used to register the left lung images at adjacent times in the plurality of left lung images respectively to obtain a plurality of corresponding first registration images; and / or to register the right lung images at adjacent times in the plurality of right lung images respectively to obtain a plurality of corresponding second registration images;

[0036] The first determining unit is used to determine a first fixed image and / or a second fixed image in the plurality of left lung images and / or the plurality of right lung images, respectively;

[0037] The second registration unit is configured to register any first registration image other than the first fixed image to the first fixed image, and / or register any second registration image other than the second fixed image to the second fixed image.

[0038] According to one aspect of this disclosure, a lesion localization method is provided, including the lung image registration method as described above or the lung image registration device as described above for registration, characterized in that a first fixed image and a second fixed image are determined respectively from a first registered image with the largest left lung area among the plurality of left lung images and a second registered image with the largest right lung area among the plurality of right lung images;

[0039] The first registered image with the smallest left lung area among the multiple left lung images and the second registered image with the smallest right lung area among the multiple right lung images are respectively determined as the first floating image and the second floating image;

[0040] The first floating image and the second floating image are registered with the first fixed image and the second fixed image, respectively, to obtain the left lung registration image and the right lung registration image;

[0041] The location of the air retention lesion in the left lung is located based on the first fixed image and the registered image of the left lung; and the location of the air retention lesion in the right lung is located based on the second fixed image and the registered image of the right lung.

[0042] Preferably, the method for locating the left lung air retention lesion based on the first fixed image and the left lung registration image includes:

[0043] Based on the obtained set air threshold range, the left lung air region corresponding to the first fixed image and the left lung registration image is determined respectively;

[0044] Calculate the first difference corresponding to the same position in the air region of the left lung in the first fixed image and the left lung registration image;

[0045] The location corresponding to the first difference being less than or equal to the obtained first preset difference threshold is configured as the location of the left lung air retention lesion; and / or,

[0046] The method for locating the right lung air retention lesion based on the second fixed image and the right lung registration image includes:

[0047] Based on the obtained set air threshold range, the right lung air region corresponding to the second fixed image and the right lung registration image is determined respectively;

[0048] Calculate the second difference corresponding to the same position in the air region of the right lung in the second fixed image and the right lung registration image;

[0049] The location corresponding to the second difference being less than or equal to the obtained second preset difference threshold is configured as the location of the right lung air retention lesion; and / or,

[0050] Before locating the left lung air retention lesion based on the first fixed image and the left lung registration image, the procedure includes:

[0051] Based on the obtained first set boundary distance, the boundaries of the first fixed image and the left lung registration image are removed to obtain the corresponding first fixed image and left lung registration image.

[0052] The location of the air retention lesion in the left lung is located based on the first fixed-process image and the registered-process image of the left lung; and / or,

[0053] The method for locating the left lung air retention lesion based on the first fixed-processed image and the left lung registration-processed image includes:

[0054] Based on the obtained set air threshold range, the left lung air region corresponding to the first fixed processing image and the left lung registration processing image is determined respectively.

[0055] Calculate the third difference between the air regions of the left lung corresponding to the first fixed-process image and the left lung registration-processed image;

[0056] The location corresponding to the third difference being less than or equal to the obtained third preset difference threshold is configured as the location of the left lung air retention lesion; and / or,

[0057] Before locating the right lung air retention lesion based on the second fixed image and the right lung registration image, the procedure includes:

[0058] Based on the obtained second set boundary distance, the boundaries of the second fixed image and the right lung registration image are removed to obtain the corresponding second fixed image and right lung registration image.

[0059] The location of the air retention lesion in the right lung is located based on the second fixed-process image and the right lung registration-processed image; and / or,

[0060] The method for locating the right lung air retention lesion based on the second fixed-processed image and the right lung registration-processed image includes:

[0061] Based on the obtained set air threshold range, the right lung air region corresponding to the second processed fixed image and the right lung registration processed image is determined respectively;

[0062] Calculate the fourth difference between the right lung air region corresponding to the second fixed-process image and the right lung registration-processed image;

[0063] The location corresponding to the fourth difference value being less than or equal to the obtained fourth preset difference value threshold is configured as the location of the right lung air retention lesion; and / or,

[0064] Before acquiring multiple left lung images and / or multiple right lung images at multiple moments during the breathing process, rib removal is performed on the two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple moments during the breathing process to obtain multiple left lung images and / or multiple right lung images at multiple moments during the breathing process.

[0065] According to one aspect of this disclosure, a lesion localization device is provided, comprising a registration model, a first lesion localization unit, and a second lesion localization unit registered using the lung image registration method described above; or, comprising: a lung image registration device, a second determination unit, a first lesion localization unit, and a second lesion localization unit as described above.

[0066] The registration model is used to determine a first fixed image and a second fixed image from the first registered image with the largest left lung area among the multiple left lung images and the second registered image with the largest right lung area among the multiple right lung images, respectively. The registration model is also used to determine a first floating image and a second floating image from the first registered image with the smallest left lung area among the multiple left lung images and the second registered image with the smallest right lung area among the multiple right lung images, respectively. The registration model is also used to register the first floating image and the second floating image with the first fixed image and the second fixed image, respectively, to obtain a left lung registration image and a right lung registration image. The first lesion localization unit is used to locate the location of an air retention lesion in the left lung based on the first fixed image and the left lung registration image. The second lesion localization unit is used to locate the location of an air retention lesion in the right lung based on the second fixed image and the right lung registration image; or...

[0067] The first determining unit of the lung image registration device is used to determine a first fixed image and a second fixed image from the first registration image with the largest left lung area among the multiple left lung images and the second registration image with the largest right lung area among the multiple right lung images, respectively.

[0068] The second determining unit is used to determine the first registered image with the smallest left lung area among the multiple left lung images and the second registered image with the smallest right lung area among the multiple right lung images as the first floating image and the second floating image, respectively.

[0069] The second registration unit of the lung image registration device registers the first floating image and the second floating image with the first fixed image and the second fixed image, respectively, to obtain a left lung registration image and a right lung registration image;

[0070] The first lesion localization unit is used to locate the location of the air retention lesion in the left lung based on the first fixed image and the registered image of the left lung;

[0071] The second lesion localization unit is used to locate the location of the air retention lesion in the right lung based on the second fixed image and the right lung registration image.

[0072] According to one aspect of this disclosure, an electronic device is provided, comprising:

[0073] processor;

[0074] Memory used to store processor-executable instructions;

[0075] The processor is configured to perform the above-described methods for lung image registration and / or lesion localization.

[0076] According to one aspect of this disclosure, a computer-readable storage medium is provided having computer program instructions stored thereon, which, when executed by a processor, implement the above-described lung image registration and / or ventilatory retention methods.

[0077] In this disclosure, a method and apparatus for lung image registration and lesion localization, as well as an electronic device and storage medium, are proposed to solve the problem of low accuracy in the current registration of multiple images at multiple times, which affects subsequent analysis of lung diseases.

[0078] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0079] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0080] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0081] Figure 1 A flowchart illustrating a lung image registration method according to an embodiment of the present disclosure is shown;

[0082] Figure 2 A flowchart illustrating a lesion localization method according to an embodiment of the present disclosure is shown;

[0083] Figure 3 This is a block diagram illustrating an electronic device 800 according to an exemplary embodiment;

[0084] Figure 4 This is a block diagram illustrating an electronic device 1900 according to an exemplary embodiment. Detailed Implementation

[0085] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0086] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0087] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0088] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0089] It is understood that the various method embodiments mentioned above in this disclosure can be combined with each other to form combined embodiments without violating the principle and logic. Due to space limitations, this disclosure will not elaborate further.

[0090] In addition, this disclosure also provides lung image registration and / or ventilation retention devices, electronic devices, computer-readable storage media, and programs, all of which can be used to implement any of the lung image registration and / or ventilation retention methods provided in this disclosure. The corresponding technical solutions and descriptions are described in the corresponding section of the method and will not be repeated here.

[0091] Figure 1 A flowchart illustrating a lung image registration method according to an embodiment of this disclosure is shown. Figure 1 As shown, the lung image registration method includes: Step S101: acquiring multiple left lung images and / or multiple right lung images at multiple time points during the respiratory process; wherein, the multiple left lung images and / or the multiple right lung images are configured as two-dimensional DR images; Step S102: registering the left lung images at adjacent time points in the multiple left lung images to obtain multiple corresponding first registration images; and / or, registering the right lung images at adjacent time points in the multiple right lung images to obtain multiple corresponding second registration images; Step S103: determining a first fixed image and / or a second fixed image in the multiple left lung images and / or the multiple right lung images; Step S104: registering any other first registration image (excluding the first registration image corresponding to the first fixed image) to the first fixed image, and / or registering any other second registration image (excluding the second registration image corresponding to the second fixed image) to the second fixed image. This method aims to solve the problem of low accuracy in the current registration of multiple images at multiple time points, which affects subsequent analysis of lung diseases.

[0092] In the embodiments of this disclosure and other possible embodiments, there may be three parallel corresponding technical solutions, which can respectively realize the registration of multiple left lung images, multiple right lung images, multiple left lung images and multiple right lung images at multiple moments during the breathing process.

[0093] For example, the lung image registration method includes: step S101: acquiring multiple left lung images at multiple times during the breathing process; wherein the multiple left lung images are configured as two-dimensional DR images; step S102: registering the left lung images at adjacent times in the multiple left lung images to obtain multiple corresponding first registration images; step S103: determining a first fixed image in the multiple left lung images; step S104: registering any other first registration image other than the first fixed image to the first fixed image.

[0094] For example, the lung image registration method includes: step S101: acquiring multiple right lung images at multiple times during the breathing process; wherein the multiple right lung images are configured as two-dimensional DR images; step S102: registering the right lung images at adjacent times in the multiple right lung images to obtain multiple corresponding second registration images; step S103: determining a second fixed image in the multiple right lung images; step S104: registering any other second registration image other than the second fixed image to the second fixed image.

[0095] For example, the lung image registration method includes: step S101: acquiring multiple left lung images and multiple right lung images at multiple times during the breathing process; wherein, the multiple left lung images and the multiple right lung images are configured as two-dimensional DR images; step S102: registering the left lung images at adjacent times in the multiple left lung images to obtain multiple corresponding first registration images; registering the right lung images at adjacent times in the multiple right lung images to obtain multiple corresponding second registration images; step S103: determining a first fixed image and a second fixed image among the multiple first registration images and the multiple second registration images; step S104: registering any other first registration image besides the first fixed image to the first fixed image, and registering any other second registration image besides the second fixed image to the second fixed image.

[0096] In embodiments of this disclosure and other possible embodiments, left lung images at adjacent time points in the plurality of left lung images are registered to obtain a plurality of corresponding first registered images; and / or, right lung images at adjacent time points in the plurality of right lung images are registered to obtain a plurality of corresponding second registered images. Since left lung images and / or right lung images at adjacent time points are most similar, this disclosure first uses left lung images and / or right lung images at adjacent time points for a first (initial) registration, obtaining a plurality of corresponding first registered images and / or a plurality of second registered images. Based on this, a first fixed image and / or a second fixed image are determined from the plurality of left lung images and / or the plurality of right lung images; any other first registered image besides the first fixed image is registered to the first fixed image, and / or any other second registered image besides the second fixed image is registered to the second fixed image.

[0097] Step S101: Acquire multiple left lung images and / or multiple right lung images at multiple times during the breathing process; wherein, the multiple left lung images and / or the multiple right lung images are configured as two-dimensional DR images. The multiple left lung images and the multiple right lung images are configured to be multiple left lung images and multiple right lung images acquired at multiple times during the breathing process of the same patient.

[0098] In the embodiments of this disclosure and other possible embodiments, a digital X-ray (DR) imaging device can be used to image the chest to obtain a corresponding two-dimensional DR left lung image and / or a two-dimensional DR right lung image. Furthermore, the DR imaging device can be used to image the chest during the breathing process to obtain two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple moments during the breathing process.

[0099] In the embodiments of this disclosure and other possible embodiments, the breathing process configuration may be one breathing cycle or multiple breathing cycles or 1 / N breathing processes (one breathing process corresponds to a time segment or time period); wherein, N is configured as a positive integer greater than or equal to 1.

[0100] In the embodiments of this disclosure and other possible embodiments, before acquiring the two-dimensional DR left lung image and / or two-dimensional DR right lung image at multiple moments during the breathing process, the two-dimensional DR lung image at multiple moments during the breathing process is acquired, and the two-dimensional DR lung image at multiple moments during the breathing process is segmented into left and right lungs to obtain the two-dimensional DR left lung image and two-dimensional DR right lung image at multiple moments.

[0101] In embodiments of this disclosure, a method for determining two-dimensional DR left lung images and / or two-dimensional DR left lung images at multiple moments during the respiratory process includes: performing costal margin boundary, lung apex boundary, and mediastinal and diaphragmatic edge detection on the left chest image and / or right chest image of the two-dimensional DR lung images at multiple moments during the respiratory process, respectively, to obtain two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple moments; or, acquiring a preset convolutional neural network segmentation model and DR lung region label images used to train the segmentation model; and using the D... The segmentation model is trained using R-zone labeled images; based on the trained segmentation model, the left and right lungs of the two-dimensional DR lung images at multiple time points during the breathing process are segmented to obtain two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple time points; and / or, the method for determining the DR lung zone labeled images used to train the segmentation model includes: performing costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edge detection on the left chest images and / or right chest images of multiple DR lung zone images respectively to obtain DR lung zone labeled images corresponding to the multiple DR lung zone images.

[0102] In embodiments of this disclosure and other possible embodiments, a DR image to be processed (a two-dimensional DR lung image at multiple moments during respiration) is acquired, and it is determined whether the DR image to be processed is a lung image; wherein the lung image is configured as a two-dimensional DR lung image at multiple moments during respiration; if it is the lung image, a thoracic cavity detection is performed on the DR image to be processed to remove information outside the thoracic cavity from the DR image to be processed.

[0103] In embodiments of this disclosure and other possible embodiments, the method for determining whether a DR image to be processed is a lung image includes: calculating the average grayscale value corresponding to the DR image to be processed, and determining whether it is a lung image based on the average grayscale value and a set grayscale value. Those skilled in the art can configure the set grayscale value according to actual needs. For example, the set grayscale value can be configured to any value or range between -1000HU and 0HU. Alternatively, in embodiments of this disclosure and other possible embodiments, the determination of whether a DR image to be processed is a lung image can also be made by manual judgment of the DR image to be processed.

[0104] In the embodiments of this disclosure and other possible embodiments, the method for determining whether an image is a lung image based on the average gray value and a set gray value includes: if the DR image to be processed has not undergone inversion processing, then if the average gray value is less than or equal to the set gray value, the DR image to be processed is determined to be a lung image; if the DR image to be processed has undergone inversion processing, then if the average gray value is greater than or equal to the set gray value, the DR image to be processed is determined to be a lung image. The principle is that if it is a lung image, the lungs in the lung image will generally be filled with or contain a certain amount of air, and air corresponds to a relatively small gray value (CT value), generally configured as -1000 HU; while the gray value (CT value) of water is generally configured as 0 HU, and the gray value (CT value) of bone is generally configured as 1000 HU or higher; therefore, the above technical solution is used to determine whether the DR image to be processed is a lung image.

[0105] In embodiments of this disclosure and other possible embodiments, if the image is a lung image, then a thoracic cavity detection is performed on the DR image to be processed to remove information outside the thoracic cavity from the DR image to be processed. In embodiments of this disclosure and other possible embodiments, the information outside the thoracic cavity includes: removing unnecessary information such as arms, heads, and blank backgrounds.

[0106] In the embodiments of this disclosure, before performing thoracic cavity detection on the DR image to be processed (the lung image to be segmented or the two-dimensional DR lung image at multiple moments during breathing or breath-holding), the DR image to be processed is filtered, and the filtered lung image to be segmented is downsampled to a set size.

[0107] In embodiments of this disclosure, image enhancement is performed on the logarithmic transformation of the DR image to be processed, which is of a set size, to obtain an enhanced DR image to be processed.

[0108] (1) Image preprocessing of DR images to be processed (lung images to be segmented or two-dimensional DR lung images at multiple moments during the breathing process).

[0109] In the embodiments of this disclosure and other possible embodiments, a. a DR image (lung image to be segmented) is processed, and a low-pass filter is applied to the DR image (lung image to be segmented). The filtered lung image to be segmented is then downsampled to a set size to speed up image processing. A logarithmic transformation is performed on the downsampled lung image to enhance the image, resulting in an enhanced lung image to be segmented. The low-pass template used is Gaussian filtering or mean filtering, and the set size value can be configured as 3×3 or 5×5. The downsampling range can be configured to 2-6 times. Those skilled in the art can configure the set size value and / or the downsampling range according to actual needs.

[0110] In the embodiments of this disclosure and other possible embodiments, b. the technical solution for detecting the thoracic cavity in the DR image to be processed adopts adaptive determination of the thoracic cavity contour based on the characteristics of the lung image to be segmented, and removes unnecessary information such as arms, head and blank background.

[0111] In the embodiments of this disclosure, step 1) of the method for performing DR image processing on the DR image to be processed includes: calculating a plurality of first gradient magnitudes corresponding to the horizontal direction of each pixel in the DR image to be processed and a plurality of second gradient magnitudes corresponding to the vertical direction of each pixel; determining a plurality of total gradient magnitudes based on the plurality of first gradient magnitudes and the plurality of second gradient magnitudes; integrating the plurality of first gradient magnitudes corresponding to the horizontal direction and the plurality of second gradient magnitudes corresponding to the vertical direction along a direction perpendicular to them to obtain a plurality of first integral values ​​and a plurality of second integral values; and integrating the plurality of total gradient magnitudes. The integral is divided into two directions corresponding to the longitudinal and transverse directions to obtain multiple third integral values ​​and multiple fourth integral values; multiple first local maxima corresponding to the multiple first ratios are calculated, and multiple first local minima and multiple second local minima corresponding to the multiple first ratios and multiple second ratios are calculated; the thoracic profile corresponding to the DR image to be processed is determined based on the multiple first local maxima, the multiple first local minima, the multiple second local minima, and the thoracic profile features; wherein, the thoracic profile features can be configured with a first segmentation position of the neck or shoulder corresponding to the thoracic profile and a second segmentation position on both sides of the thoracic profile.

[0112] In embodiments of this disclosure, the method for calculating multiple first gradient magnitudes in the horizontal direction and multiple second gradient magnitudes in the vertical direction of each pixel in the DR image to be processed includes: obtaining a gradient operator; and using the gradient operator to calculate multiple first gradient magnitudes in the horizontal direction and multiple second gradient magnitudes in the vertical direction of each pixel in the DR image to be processed.

[0113] In embodiments of this disclosure, the method for determining multiple total gradient magnitudes based on the plurality of first gradient magnitudes and the plurality of second gradient magnitudes includes: calculating a plurality of first sums of squares corresponding to the plurality of first gradient magnitudes and a plurality of second sums of squares corresponding to the plurality of second gradient magnitudes, and determining the plurality of total gradient magnitudes based on the plurality of first sums of squares and the plurality of second sums of squares; and / or, the method for determining the plurality of total gradient magnitudes based on the plurality of first sums of squares and the plurality of second sums of squares includes: summing the plurality of first sums of squares and the plurality of second sums of squares, and taking the square root of the sums to obtain the plurality of total gradient magnitudes.

[0114] In embodiments of this disclosure and other possible embodiments, a plurality of first gradient magnitudes corresponding to the horizontal direction of each pixel in the lung image to be segmented and a plurality of second gradient magnitudes corresponding to the vertical direction of each pixel are calculated respectively; and a plurality of total gradient magnitudes are determined based on the plurality of first gradient magnitudes and the plurality of second gradient magnitudes; wherein, the method of determining the plurality of total gradient magnitudes based on the plurality of first gradient magnitudes and the plurality of second gradient magnitudes includes: calculating a plurality of first sums of squares corresponding to the plurality of first gradient magnitudes and a plurality of second sums of squares corresponding to the plurality of second gradient magnitudes respectively, and determining the plurality of total gradient magnitudes based on the plurality of first sums of squares and the plurality of second sums of squares. The method of determining the plurality of total gradient magnitudes based on the plurality of first sums of squares and the plurality of second sums of squares includes: summing the plurality of first sums of squares and the plurality of second sums of squares respectively, and taking the square root of the sums to obtain the plurality of total gradient magnitudes.

[0115] For example, each pixel e in the lung image to be segmented and its eight-neighbor matrix are: Using the Sobel gradient operator Calculate the magnitudes of the first gradient (c + 2*f + ia - 2*dg) in the horizontal direction for each pixel e in the lung image to be segmented, and then use the transpose of the Sobel gradient operator. Calculate the magnitudes of the second gradient in the vertical direction (g + 2*h + ia - 2*bc) for each pixel e in the lung image to be segmented. Additionally, those skilled in the art may choose other gradient operators, such as the Roberts gradient operator or the Laplace gradient operator, depending on the specific needs.

[0116] For example, based on the plurality of first gradient magnitudes (h1, h2, ..., h... n and the plurality of second gradient magnitudes (k1,k2,...,k n Determine multiple total gradient magnitudes.

[0117] Step 2). Integrate the multiple first gradient magnitudes corresponding to the horizontal direction and the multiple second gradient magnitudes corresponding to the vertical direction along the direction perpendicular to them to obtain multiple first integral values ​​and multiple second integral values;

[0118] Specifically, multiple first gradient magnitudes corresponding to the horizontal direction are integrated in the vertical direction to obtain multiple first integral values; and multiple second integral values ​​are obtained by integrating multiple first gradient magnitudes corresponding to the vertical direction in the horizontal direction.

[0119] Step 3). Integrate the multiple total gradient magnitude integrals in the two corresponding directions, the vertical and horizontal directions, respectively, to obtain multiple third integral values ​​and multiple fourth integral values; wherein, integrating the multiple total gradient magnitude integrals in the vertical direction yields multiple third integral values; and integrating the multiple total gradient magnitude integrals in the horizontal direction yields multiple fourth integral values.

[0120] Step 4). (a) When determining multiple first local maxima, calculate the ratio based on the results of Step 2 and Step 3. When the ratio is less than a preset value, the image information at this location is considered noise and needs to be discarded. The noise can be configured to be image information corresponding to unnecessary information such as arms, heads, and blank backgrounds.

[0121] Specifically, based on the plurality of first integral values ​​and the plurality of third integral values, it is determined whether each of the plurality of first ratios corresponding to the plurality of first integral values ​​and the plurality of third integral values ​​in the horizontal direction should be retained.

[0122] The method for determining whether to retain each of the plurality of first ratios corresponding to the plurality of first integral values ​​and the plurality of third integral values ​​in the horizontal direction, based on the plurality of first integral values ​​and the plurality of third integral values, includes: obtaining a first preset value; calculating the plurality of first ratios between the plurality of first integral values ​​and the corresponding plurality of third integral values ​​in the horizontal direction; and discarding the first ratio if it is less than the first preset value. In embodiments of this disclosure and other possible embodiments, those skilled in the art may configure the first preset value as needed.

[0123] (b) When determining multiple first local minima, calculate the ratio based on the results of step 2 and step 3. When the ratio is greater than a preset value, the image information at this location is considered noise and needs to be discarded. The noise can be configured to include image information corresponding to unnecessary information such as arms, heads, and blank backgrounds.

[0124] Specifically, based on the plurality of first integral values ​​and the plurality of third integral values, it is determined whether each of the plurality of first ratios corresponding to the plurality of first integral values ​​and the plurality of third integral values ​​in the horizontal direction should be retained.

[0125] The method for determining whether to retain each of the plurality of first ratios corresponding to the plurality of first integral values ​​and the plurality of third integral values ​​in the horizontal direction, based on the plurality of first integral values ​​and the plurality of third integral values, includes: obtaining a first preset value; calculating the plurality of first ratios between the plurality of first integral values ​​and the corresponding plurality of third integral values ​​in the horizontal direction; and discarding the first ratio if one of the plurality of first ratios is greater than the first preset value.

[0126] Specifically, based on the plurality of second integral values ​​and the plurality of fourth integral values, it is determined whether each of the plurality of second ratios corresponding to the plurality of second integral values ​​and the plurality of fourth integral values ​​in the longitudinal direction should be retained.

[0127] The method for determining whether to retain each of the plurality of second ratios corresponding to the plurality of second integral values ​​and the plurality of fourth integral values ​​in the longitudinal direction, based on the plurality of second integral values ​​and the plurality of fourth integral values, includes: obtaining a second preset value; calculating the plurality of second ratios between the plurality of second integral values ​​and the corresponding plurality of fourth integral values ​​in the longitudinal direction; and discarding a certain second ratio if it is greater than the second preset value. In embodiments of this disclosure and other possible embodiments, those skilled in the art may configure the second preset value as needed.

[0128] In embodiments of this disclosure, before calculating the plurality of first local maxima corresponding to the plurality of first ratios, and calculating the plurality of first local minima and the plurality of second local minima corresponding to the plurality of first ratios and the plurality of second ratios, it is determined, based on the plurality of first integral values ​​and the plurality of third integral values, whether each of the plurality of first ratios corresponding to the plurality of first integral values ​​and the plurality of third integral values ​​in the horizontal direction should be retained; and, based on the plurality of second integral values ​​and the plurality of fourth integral values, it is determined whether each of the plurality of second ratios corresponding to the plurality of second integral values ​​and the plurality of fourth integral values ​​in the vertical direction should be retained; then, the plurality of first local maxima corresponding to the retained plurality of first ratios are calculated, and the plurality of first local minima and the plurality of second local minima corresponding to the retained plurality of first ratios and the retained plurality of second ratios are calculated.

[0129] In embodiments of this disclosure, the differential derivatives of the first curves corresponding to the plurality of first ratios are calculated to obtain the plurality of first local maxima and the plurality of first local minima; and the differential derivatives of the second curves corresponding to the plurality of second ratios are calculated to obtain the plurality of second local minima.

[0130] In embodiments of this disclosure, the method for determining the thoracic map corresponding to the lung image to be segmented based on a plurality of first local maxima, a plurality of first local minima, a plurality of second local minima, and thoracic features includes: determining second segmentation positions on both sides of the thoracic cavity based on the plurality of first local maxima and the thoracic features; determining first segmentation positions of the neck or shoulder based on the plurality of second local minima and the thoracic features; and determining the thoracic map corresponding to the lung image to be segmented based on the first segmentation positions and the first segmentation positions.

[0131] In the embodiments of this disclosure and other possible embodiments, 5) calculate the plurality of first local maxima corresponding to the plurality of first ratios discarded in step 4(a). Similarly, calculate the plurality of first local minima and the plurality of second local minima corresponding to the plurality of first ratios and the plurality of second ratios discarded in step 4(b). Wherein, the plurality of first ratios discarded are the plurality of first ratios retained after discarding; similarly, the plurality of second ratios discarded are the plurality of second ratios retained after discarding.

[0132] The thoracic profile corresponding to the lung image to be segmented is determined based on multiple first local maxima, multiple first local minima, multiple second local minima, and thoracic profile features, removing unnecessary information such as arms, head, and blank background. The thoracic profile features can be configured with a first segmentation position corresponding to the neck or shoulder and second segmentation positions on both sides of the thoracic profile.

[0133] The method for determining the thoracic map corresponding to the lung image to be segmented based on multiple first local maxima, multiple first local minima, multiple second local minima, and thoracic features includes: determining second segmentation positions on both sides of the thoracic cavity based on the multiple first local maxima and the thoracic features; determining first segmentation positions of the neck or shoulder based on the multiple second local minima and the thoracic features; and determining the thoracic map corresponding to the lung image to be segmented based on the first segmentation positions.

[0134] The plurality of first local maxima are obtained by calculating the differential derivatives of the first curves corresponding to the plurality of discarded first ratios; wherein the differential derivatives can be configured as first-order, second-order, or other multi-order differential derivatives. Similarly, the plurality of first local minima are obtained by calculating the differential derivatives of the first curves corresponding to the plurality of discarded first ratios; wherein the differential derivatives can be configured as first-order, second-order, or other multi-order differential derivatives. Similarly, the plurality of second local minima are obtained by calculating the differential derivatives of the second curves corresponding to the plurality of discarded second ratios; wherein the differential derivatives can be configured as first-order, second-order, or other multi-order differential derivatives.

[0135] In embodiments of this disclosure, the method for determining the second segmentation positions on both sides of the thorax based on the plurality of first local maxima and the thorax features includes: determining the maximum value among all the plurality of first local maxima on one side of the centerline of the DR image to be processed, and configuring the position information corresponding to the maximum value as the segmentation position point of the side to be determined corresponding to the side of the thorax; determining the minimum value among all the plurality of first local minima on the other side of the centerline of the DR image to be processed, and configuring the position information corresponding to the minimum value as the segmentation position point of the other side to be determined corresponding to the other side of the thorax.

[0136] In embodiments of this disclosure, a method for determining the first segmentation position of the neck or shoulder based on the plurality of second local minima and the thoracic features includes: configuring the position information corresponding to the minimum value of the plurality of second local minima as the first segmentation position of the neck or shoulder.

[0137] In embodiments of this disclosure and other possible embodiments, the method for determining the second segmentation positions on both sides of the thorax based on the plurality of first local maxima and the thorax features includes: determining the maximum value among all the plurality of first local maxima on one side (right side) of the center line of the image to be segmented, and configuring the position information corresponding to the maximum value as the segmentation position point of the side to be determined corresponding to the side of the thorax; determining the minimum value among all the plurality of first local minima on the other side (left side) of the center line of the image to be segmented, and configuring the position information corresponding to the minimum value as the segmentation position point of the other side to be determined corresponding to the other side of the thorax.

[0138] For example, determine all of the plurality of first local maxima (a1, a2, ..., a) on one side (right side) of the centerline. n The maximum value a in ) m Where m is less than or equal to n; m is the location information corresponding to the maximum value (e.g., a certain horizontal coordinate), that is, the segmentation point of the side to be determined corresponding to one side of the thorax. Similarly, determine all the plurality of first local minima (b1, b2, ..., b) on the other side (left side) of the centerline. n The minimum value b in ) r , where r is less than or equal to n; r is the location information (e.g., a certain horizontal coordinate) corresponding to the minimum value.

[0139] In embodiments of this disclosure and other possible embodiments, a method for determining a first segmentation position of the neck or shoulder based on the plurality of second local minima and the thoracic features includes: configuring the position information (e.g., a certain ordinate) corresponding to the minimum value of the plurality of second local minima as the first segmentation position of the neck or shoulder.

[0140] (2) Lung field segmentation.

[0141] In the embodiments of this disclosure, the thoracic image obtained by thoracic cavity detection of the DR image to be processed is configured as the lung image to be segmented; and the left and right lungs are segmented based on the lung image to be segmented.

[0142] In embodiments of this disclosure, the lung image to be segmented is segmented into a left chest image and a right chest image; the left lung and right lung are segmented based on the left chest image and the right chest image, respectively.

[0143] In embodiments of this disclosure, the lung image to be segmented is segmented into a left chest image and a right chest image; the left lung and right lung are segmented based on the left chest image and the right chest image, respectively; or, a segmentation model of a preset convolutional neural network, DR lung region label images used to train the segmentation model, and multiple DR lung images (lung images to be segmented) at multiple times during breathing or breath-holding; wherein, the method for determining the DR lung region label images used to train the segmentation model includes: performing costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edge detection on the left chest image and right chest image of the multiple DR lung region images, respectively, to obtain DR lung region label images corresponding to the multiple DR lung region images; training the segmentation model using the DR lung region label images used to train the segmentation model; and completing the left lung and / or right lung segmentation of the multiple DR lung images to be segmented based on the trained segmentation model.

[0144] In embodiments of this disclosure and other possible embodiments, the segmentation model of the preset convolutional neural network is configured as a Unet convolutional neural network, an nnUnet convolutional neural network, or a convolutional neural network improved based on the Unet convolutional neural network, or a convolutional neural network improved based on the nnUnet convolutional neural network. For example, the convolutional neural network improved based on the Unet convolutional neural network can be configured as a ResUnet convolutional neural network with a residual structure.

[0145] In embodiments of this disclosure and other possible embodiments, the Unet convolutional neural network or nnUnet convolutional neural network or a convolutional neural network improved based on Unet convolutional neural network or a convolutional neural network improved based on nnUnet convolutional neural network includes at least: a downsampling shrinking path, an upsampling expanding path, and a final classification layer.

[0146] In embodiments of this disclosure and other possible embodiments, the multiple DR lung area images are configured to be acquired during deep inspiration or breath-holding.

[0147] In embodiments of this disclosure and other possible embodiments, before training the segmentation model using the DR lung region label image used to train the segmentation model, the DR lung region label image is data augmented to obtain an augmented DR lung region label image; and the segmentation model is trained using the augmented DR lung region label image.

[0148] In embodiments of this disclosure and other possible embodiments, the method for data augmentation of the DR lung region label image to obtain an enhanced DR lung region label image includes: performing spatial geometric transformation and / or flipping and / or rotating and / or cropping and / or scaling and / or image shifting and / or edge filling and / or random erasing and / or random occlusion operations on the DR lung region label image to obtain the enhanced DR lung region label image.

[0149] In embodiments of this disclosure and other possible embodiments, the method for data augmentation of the DR lung region label image to obtain an enhanced DR lung region label image further includes: randomly selecting any two DR lung region label images from the DR lung region label images; performing a configuration operation on the arbitrary two DR lung region label images to obtain a corresponding DR lung region label registration image; and performing a fusion operation on the DR lung region label registration image to obtain the enhanced DR lung region label image.

[0150] In the embodiments of this disclosure and other possible embodiments, the method of performing a fusion operation on the DR lung region label registration image to obtain an enhanced DR lung region label image includes: performing a minimum, maximum, or average operation on the pixel values ​​corresponding to the DR lung region label registration image to obtain the enhanced DR lung region label image.

[0151] In the embodiments and other possible embodiments of this disclosure, the registration method used in this disclosure can employ existing registration algorithms or models, such as one or more of SIFT (Scale-invariant feature transform), SURF (Speeded Up Robust Features), and ORB (Oriented FAST and Rotated BRIEF) registration algorithms or models, or other registration algorithms or models based on convolutional neural networks. For example, a registration algorithm or model based on convolutional neural networks can be configured as a registration algorithm or model based on VGG networks.

[0152] c. Based on the chest image corresponding to the lung image to be segmented, the chest image is divided into two parts: a left chest image and a right chest image. Based on this, the left lung field of the left chest image is segmented and the right lung field of the right chest image is segmented.

[0153] In embodiments of this disclosure, a method for segmenting the left and right lungs based on the left chest image and the right chest image respectively includes: detecting the costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edges of the left chest image and the right chest image respectively; obtaining a segmented image of the left lung based on the costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edges corresponding to the left chest image; and obtaining a segmented image of the right lung based on the costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edges corresponding to the right chest image.

[0154] In an embodiment of this disclosure, the method for determining the rib edge boundary of the left chest image includes: constructing a directional derivative template for the left chest image using directional derivatives, and setting a predetermined weighting depth for the directional derivative template; performing template traversal of the directional derivatives on the left chest image using the directional derivative template corresponding to the predetermined weighting depth, and superimposing the result of the template traversal onto the left chest image to obtain a superimposed left chest image; performing binarization processing on the superimposed left chest image to obtain a binary map of the left rib edge; obtaining a rib edge angle map of the left side to be filtered based on the binary map of the left rib edge and the superimposed left chest image; obtaining a filtered left rib edge angle map based on the rib edge angle map of the left side to be filtered and a first predetermined rib edge angle; and performing connected component selection on the left rib edge angle map to obtain the rib edge boundary corresponding to the largest connected component.

[0155] In an embodiment of this disclosure, the method for obtaining the left rib angle map to be screened based on the left rib edge binary image and the overlay image of the left chest includes: performing morphological opening and closing operations and thinning processing on the left rib edge binary image to obtain a morphologically processed left rib edge binary image; performing a bitwise AND operation on the gradient direction angle of each pixel in the morphologically processed left rib edge binary image and the overlay image of the left chest to obtain the left rib angle map to be screened.

[0156] In the embodiments of this disclosure, before constructing the directional derivative template of the left chest image using the directional derivative, the left chest image is subjected to Gaussian blurring at a set scale to obtain a corresponding Gaussian blurred image of the left chest; then, the directional derivative template of the Gaussian blurred image of the left chest is constructed using the directional derivative; during the process of defining the rib edge boundary of the left chest image, the template of the directional derivative corresponding to the set weighted depth is used to perform template traversal of the directional derivative of the Gaussian blurred image of the left chest, and the result of the template traversal is superimposed on the left chest image to obtain a Gaussian blurred superimposed image of the left chest; the Gaussian blurred superimposed image of the left chest is binarized to obtain a binary map of the left rib edge; based on the binary map of the left rib edge and the Gaussian blurred superimposed image of the left chest, the rib edge angle map of the left side to be screened is obtained.

[0157] a. In embodiments of this disclosure and other possible embodiments, the lung field segmentation steps are as follows, taking a left chest image as an example. For example, rib margin boundary detection in a left chest image.

[0158] 1) Apply a Gaussian blur of a predetermined scale to the left chest region (image) to reduce the detail information of this left chest region (image), resulting in a processed Gaussian blurred image of the left chest. The predetermined scale can be configured as 7×7 or 9×9, and those skilled in the art can configure the predetermined scale according to actual needs. The root mean square error of the Gaussian blur algorithm can be configured as a value such as 2, 2.5, or 3, and those skilled in the art can configure the root mean square error σ of the Gaussian blur algorithm according to actual needs.

[0159] 2) Construct a directional derivative template for the processed Gaussian blurred image f(x0, y0) of the left chest using the directional derivative, and set a weighted depth for the directional derivative template. Here, (x0, y0) represent the x-coordinate x0 and y-coordinate y0 of the coordinate point corresponding to the left chest image f(x0, y0), respectively.

[0160] The formula for calculating the directional derivative is as follows:

[0161]

[0162] Where l is a unit vector in the direction, and cosα and cosβ are the cosines of the l direction. The direction can be configured as a horizontal direction, α is the angle formed by the l direction and the horizontal direction, and β is the angle formed by the l direction and the vertical direction.

[0163] The method for constructing a directional derivative template of the processed Gaussian blurred image f(x0, y0) of the left chest using the directional derivative includes: obtaining the first radius in the x0 direction corresponding to the set template radius r. and the second radius in the y0 direction Based on the first radius and the second radius The directional derivative template of the processed Gaussian blurred image f(x0, y0) of the left chest is constructed using the directional derivative.

[0164]

[0165] in,

[0166]

[0167] For example, the set template radius can be configured to 1, 2, 3, 4, 5, etc. Those skilled in the art can configure the set template radius according to actual needs.

[0168] For example, the first radius in the x0 direction When configured as -1, 0, or 1, the second radius in the y0 direction The value range is -1, 0, and 1.

[0169] Those skilled in the art can configure the set weighting depth according to actual needs; for example, the set weighting depth can be configured to 6. Furthermore, the method for setting the set weighting depth of the directional derivative template includes: obtaining the set weighting depth; multiplying the set weighting depth by the directional derivative template to obtain the directional derivative template corresponding to the set weighting depth; and, based on the structural characteristics of the rib region, reasonably setting the directional angle range and substituting it into the directional derivative calculation formula to obtain a template array.

[0170] 3) Using the directional derivative template corresponding to the weighted depth, perform directional derivative template traversal on the Gaussian blurred image of the left chest after step a.1, and superimpose the result of the template traversal (add the corresponding pixels) onto the Gaussian blurred image of the left chest in step 1 to obtain the Gaussian blurred superimposed image of the left chest.

[0171] For example, in the Gaussian blurred image of the left chest, each pixel e and its eight-neighbor matrix are: Using the directional derivative template corresponding to the weighted depth Calculate the superposition value of e for each pixel (e+w*(c+2*f+ia-2*dg)).

[0172] 4) Perform maximum inter-class variance binarization on the result of step a.3 (the Gaussian blurred image of the left chest) to obtain the rib edge binary image.

[0173] 5) Perform morphological opening and closing operations and thinning on the result of step a.4 (rib edge binary image) to obtain the morphologically processed rib edge binary image.

[0174] 6) Calculate the horizontal and vertical gradients of the results from step a.3 (the Gaussian blurred overlay image of the left chest) to obtain the horizontal gradient map and the vertical gradient map; based on the horizontal gradient map and the vertical gradient map, calculate the gradient direction angle of each pixel in the Gaussian blurred overlay image of the left chest.

[0175] 7) Perform a bitwise AND operation between the result of step a.5 (the morphologically processed binary image of the rib margin) and the result of step a.6 (the gradient direction angle of each pixel in the Gaussian blurred superimposed image of the left chest) to obtain the rib margin angle image to be screened.

[0176] 8) Based on the characteristics of the rib edge tissue, set a reasonable angle range (first set rib edge angle range), and perform angle filtering on the results obtained in step a.7 (rib edge angle diagram to be filtered) to obtain the filtered rib edge angle diagram.

[0177] 9) Based on the results in step a.8 (the filtered rib angle diagram), select the connected components to obtain the largest connected component, which is the rib portion (rib boundary).

[0178] Similarly, in the embodiments of this disclosure, the method for determining the rib edge boundary of the right chest image includes: constructing a directional derivative template of the right chest image using directional derivatives, and setting a predetermined weighting depth for the directional derivative template; performing template traversal of the directional derivatives of the right chest image using the directional derivative template corresponding to the predetermined weighting depth, and superimposing the result of the template traversal onto the right chest image to obtain a right chest overlay image; performing binarization processing on the right chest overlay image to obtain a right rib edge binary image; obtaining a rib edge angle image of the right side to be filtered based on the right rib edge binary image and the right chest overlay image; obtaining a filtered right rib edge angle image based on the rib edge angle image of the right side to be filtered and a second predetermined rib edge angle; and performing connected component selection on the right rib edge angle image to obtain the rib edge boundary corresponding to the largest connected component.

[0179] Similarly, in the embodiments of this disclosure, the method for obtaining the right rib angle map to be screened based on the right rib edge binary image and the right chest superimposed image includes: performing morphological opening and closing operations and thinning processing on the right rib edge binary image to obtain a morphologically processed right rib edge binary image; performing a bitwise AND operation on the gradient direction angle of each pixel in the morphologically processed right rib edge binary image and the right chest superimposed image to obtain the right rib angle map to be screened.

[0180] Similarly, in the embodiments of this disclosure, before constructing the directional derivative template of the right chest image using the directional derivative, the right chest image is subjected to Gaussian blurring at a set scale to obtain a corresponding right chest Gaussian blurred image; then, the directional derivative template of the right chest Gaussian blurred image is constructed using the directional derivative; during the process of defining the rib edge boundary of the right chest image, the directional derivative template corresponding to the set weighted depth is used to perform template traversal of the directional derivative of the right chest Gaussian blurred image, and the result of the template traversal is superimposed on the right chest image to obtain a right chest Gaussian blurred superimposed image; the right chest Gaussian blurred superimposed image is binarized to obtain a right rib edge binary image; based on the right rib edge binary image and the right chest Gaussian blurred superimposed image, the rib edge angle map of the right side to be screened is obtained.

[0181] b. Lung apex boundary detection. In an embodiment of this disclosure, the method for detecting the left lung apex boundary of the left chest image includes: determining a left lung apex detection region based on the left chest image; determining a left lung apex edge binary map based on the left lung apex detection region; and obtaining the fitted left lung apex boundary by fitting a quadratic function based on the left lung apex edge binary map.

[0182] In an embodiment of this disclosure, the method for determining the detection region of the left lung apex based on the left chest image includes: detecting a first coordinate corresponding to the uppermost coordinate point of the costal margin in the left chest image; the region formed by the first coordinate and the coordinate point of the uppermost right corner of the left chest image as the left lung apex detection region.

[0183] In the embodiments of this disclosure and other possible embodiments, 1) the coordinates of the uppermost coordinate point of the costal margin portion of the detected left chest image are used. 2) The rectangular area formed by the hypotenuse of this coordinate point and the coordinate point of the upper right corner of the left chest image is the lung apex detection area. For the lung apex detection area corresponding to the right lung, the rectangular area formed by the hypotenuse of the coordinate point of the uppermost coordinate point of the costal margin portion and the coordinate point of the upper left corner of the right chest image is the lung apex detection area corresponding to the right lung. 3) The lung apex area obtained in step b.2 is subjected to a set-scale Gaussian filter and contrast enhancement to obtain a filtered and enhanced lung apex area image. 4) Based on the angular characteristics of the lung apex edge, the binary image of the left lung apex edge is determined using the same method as steps a.2 to a.5 based on the filtered and enhanced lung apex area image. The angular characteristics of the lung apex edge are configured as a set angle range. 5) Based on the features of the lung apex edge and the binary image of the left lung apex edge, the Hough space parameters of a quadratic function are used for fitting to obtain the fitted lung apex edge (line). The edge of the lung apex is characterized as a quadratic function that opens downwards.

[0184] Similarly, in the embodiments of this disclosure, the method for detecting the right lung apex boundary of the right chest image includes: determining the right lung apex detection region based on the right chest image; determining the right lung apex edge binary map based on the right lung apex detection region; and obtaining the fitted right lung apex boundary by fitting a quadratic function based on the right lung apex edge binary map.

[0185] Similarly, in the embodiments of this disclosure, the method for determining the right lung apex detection region based on the right chest image includes: detecting the second coordinate corresponding to the uppermost coordinate point of the costal margin in the right chest image; the region formed by the second coordinate and the coordinate point of the upper left corner of the left chest image as the right lung apex detection region.

[0186] c. Mediastinal and diaphragmatic edge detection. In embodiments of this disclosure, a method for detecting the left lung mediastinal and diaphragmatic edges on the left chest image includes: binarizing the left chest image to obtain a left chest binary image; performing edge detection on the left chest binary image to obtain a left chest edge binary map; obtaining a left chest edge angle map based on the gradient direction angle of each pixel in the left chest binary image and the left chest edge binary map; obtaining selected left diaphragmatic and mediastinal edge angle maps based on the obtained left chest edge angle maps and setting the edge angle ranges of the diaphragm and mediastinum; and performing connected component selection processing based on the selected left diaphragmatic and mediastinal edge angle maps to obtain the left lung mediastinal and diaphragmatic edges corresponding to the largest connected component.

[0187] In an embodiment of this disclosure, the method for binarizing the left chest image to obtain a left chest binary image includes: performing contrast enhancement processing and maximum inter-class variance processing on the left chest Gaussian blurred image corresponding to the left chest image to obtain a left chest binary image.

[0188] In an embodiment of this disclosure, the method for determining the gradient direction angle of each pixel in the binary image of the left chest edge includes: calculating the horizontal and vertical gradients of the Gaussian blurred image of the left chest corresponding to the left chest image to obtain the horizontal gradient map and the vertical gradient map of the left chest; and obtaining the gradient direction angle of each pixel in the Gaussian blurred image of the left chest based on the horizontal gradient map and the vertical gradient map of the left chest.

[0189] In embodiments of this disclosure and other possible embodiments, a method for detecting the left lung mediastinum and diaphragm edges in the left chest image includes: 1) performing contrast enhancement processing and maximum inter-class variance processing on the processed left chest Gaussian blurred image obtained in step a.1 to obtain a left chest binary image; 2) performing morphological opening and closing operations and Canny edge detection sequentially on the result of step c.1 (left chest binary image) to obtain a left chest edge binary map; 3) calculating the horizontal and vertical gradients of the processed left chest Gaussian blurred image obtained in step a.1 to obtain a horizontal gradient map and a vertical gradient map; and calculating based on the horizontal and vertical gradient maps... 4) Perform an AND operation on the left chest binary image obtained in step c.1 and the left chest edge binary image obtained in step c.2, retaining the angles at the edge pixels to obtain the left chest edge angle map; 5) Select an appropriate angle range based on the edge characteristics of the diaphragm and diaphragm (set the edge angle range of the diaphragm and diaphragm), remove stray tissue edge information in the left chest edge angle map, and obtain the selected left diaphragm and diaphragm edge angle map; 6) Perform connected component selection processing based on the result of c.5 (the selected left diaphragm and diaphragm edge angle map) to obtain the largest connected component, which is the edge region of the diaphragm and diaphragm.

[0190] Similarly, in the embodiments of this disclosure, the method for detecting the right lung mediastinal and diaphragmatic edges of the right chest image includes: binarizing the right chest image to obtain a right chest binary image; performing edge detection on the right chest binary image to obtain a right chest edge binary map; obtaining a right chest edge angle map based on the gradient direction angle of each pixel in the right chest binary image and the right chest edge binary map; obtaining selected right diaphragmatic and mediastinal edge angle maps based on the obtained right chest edge angle maps and setting the edge angle range of the diaphragm and mediastinum; and performing connected component selection processing based on the selected right diaphragmatic and mediastinal edge angle maps to obtain the right lung mediastinal and diaphragmatic edges corresponding to the largest connected component.

[0191] Similarly, in the embodiments of this disclosure, the method of binarizing the right chest image to obtain a right chest binary image includes: performing contrast enhancement processing and maximum inter-class variance processing on the right chest Gaussian blurred image corresponding to the right chest image to obtain a right chest binary image.

[0192] Similarly, in the embodiments of this disclosure, the method for determining the gradient direction angle of each pixel in the binary image of the right chest edge includes: calculating the horizontal and vertical gradients of the right chest Gaussian blurred image corresponding to the right chest image to obtain the horizontal gradient map and the vertical gradient map of the right chest; and obtaining the gradient direction angle of each pixel in the right chest Gaussian blurred image based on the horizontal gradient map and the vertical gradient map of the right chest.

[0193] (3) Connection of the transverse and mediastinal edges, the lung apex and the costal margin. In the embodiments of this disclosure, the method for obtaining a segmented image of the left lung based on the costal margin boundary, lung apex boundary and mediastinal and transverse edges corresponding to the left chest image includes: calculating the first left lung apex edge point and the left lung mediastinal edge point corresponding to the shortest distance between the lung apex boundary and the mediastinal edge in the left chest image; calculating the second left lung apex edge point and the first left lung costal edge point corresponding to the shortest distance between the lung apex boundary and the costal margin edge in the left chest image; calculating the second costal edge point and the diaphragmatic edge point corresponding to the shortest distance between the costal margin boundary and the transverse edge in the left chest image; and obtaining a segmented image of the left lung based on the first left lung apex edge point, the left lung mediastinal edge point, the second left lung apex edge point, the first left lung costal edge point, the second costal edge point and the diaphragmatic edge point.

[0194] Similarly, in the embodiments of this disclosure, the method for obtaining a segmented image of the right lung based on the costal margin boundary, lung apex boundary, and mediastinal and transverse margins corresponding to the right chest image includes: calculating the first right lung apex edge point and the right lung mediastinal edge point corresponding to the shortest distance between the lung apex boundary and the mediastinal margin in the right chest image; calculating the second right lung apex edge point and the first right lung costal margin edge point corresponding to the shortest distance between the lung apex boundary and the costal margin boundary in the right chest image; calculating the second costal margin edge point and the diaphragmatic edge point corresponding to the shortest distance between the costal margin boundary and the transverse margin in the right chest image; and obtaining a segmented image of the right lung based on the first right lung apex edge point, the right lung mediastinal edge point, the second right lung apex edge point, the first right lung costal margin edge point, the second costal margin edge point, and the diaphragmatic edge point.

[0195] In embodiments of this disclosure and other possible embodiments, the method for connecting the transverse and mediastinal edges, the lung apex, and the costal margin includes: a. calculating the two points (the first lung apex edge point and the mediastinal edge point) with the shortest Euclidean distance between the lung apex edge (line) and the mediastinal edge (line), these two points being one of the endpoints of the lung apex and the transverse and mediastinal boundaries, respectively; b. calculating and obtaining the two points (the second lung apex edge point and the first costal edge edge point) with the shortest Euclidean distance between the lung apex edge (line) and the costal margin edge (line), these two points being one of the endpoints of the lung apex and the costal margin, respectively, and the lung apex region boundary can be obtained based on the other lung apex point obtained in step a; c. calculating and obtaining the costal margin (line) and the transverse and mediastinal edges... The two points with the shortest Euclidean distance between the edges (lines) of the diaphragm (the edge of the second costal margin and the edge of the transverse diaphragm) are respectively one of the endpoints of the costal margin and the transverse and mediastinal margins. The transverse and mediastinal margin boundary region can be obtained based on the other endpoint of the transverse and mediastinal margin boundary obtained in step a. The costal margin boundary region can be obtained based on the other endpoint of the costal margin obtained in step b. d. Connect the edge regions of the three parts obtained in steps a, b, and c above to obtain the closed lung field contour. The lung field region can be segmented based on the difference between the tissues inside and outside the contour boundary. e. The right lung field region is processed in the same way as above. Finally, the lung field region is mapped onto the original image to obtain the lung field segmentation of the original image.

[0196] In the embodiments and other possible embodiments of this disclosure, in order for those skilled in the art to better understand this disclosure or its embodiments, the corresponding time can be understood as the same time among multiple times.

[0197] In embodiments of this disclosure, before acquiring multiple left lung images and / or multiple right lung images at multiple moments during the breathing process, two-dimensional DR left lung images and their corresponding first predetermined position information and / or two-dimensional DR right lung images and their corresponding second predetermined position information are acquired at multiple moments during the breathing process; the multiple moments of the two-dimensional DR left lung images and / or two-dimensional DR right lung images are cropped based on the first predetermined position information and / or the second predetermined position information to obtain the corresponding multiple left lung images and / or multiple right lung images. The corresponding multiple left lung images and / or multiple right lung images all have the same first size and / or second size; the first size and / or the second size are respectively configured as the first shape and / or the second shape corresponding to the first predetermined position information and / or the second predetermined position information.

[0198] In embodiments of this disclosure and other possible embodiments, the method of cropping the multi-time-lapse 2D DR left lung image and / or 2D DR right lung image based on the first set position information and / or the second set position information to obtain corresponding multiple left lung images and / or multiple right lung images further includes: obtaining a set compensation margin; adjusting the first set position information and / or the second set position information according to the set compensation margin to obtain first adjusted position information and / or second adjusted position information; cropping the multi-time-lapse 2D DR left lung image and / or 2D DR right lung image based on the first adjusted position information and / or the second adjusted position information to obtain corresponding multiple left lung images and / or multiple right lung images. The first set position information and / or the second set position information are enlarged using the set compensation margin to obtain the first adjusted position information and / or the second adjusted position information.

[0199] For example, in embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the set compensation margin z according to actual needs. For example, the set compensation margin z can be configured to 20 pixel values ​​or other values. Similarly, the set compensation margin may include a first set compensation margin and a second set compensation margin; wherein the first set compensation margin and the second set compensation margin can be configured to the same value or different values. For example, the first set compensation margin and the second set compensation margin can be configured to 20 pixel values ​​or other values.

[0200] In the embodiments of this disclosure and other possible embodiments, the first set position information is configured as position information corresponding to a matrix; wherein, the four coordinate points of the matrix are configured as (x1, y1), (x1, y2), (x2, y1), and (x2, y2), respectively. Furthermore, according to the set compensation margin (the first set compensation margin), the first set position information is adjusted respectively, resulting in the four coordinate points corresponding to the first adjusted position information being configured as (x1-z, y1-z), (x1-z, y2+z), (x2+z, y1-z), and (x2+z, y2+z). Similarly, the second set position information is configured as position information corresponding to a matrix; wherein, the four coordinate points of the matrix are configured as (x3, y3), (x3, y4), (x4, y3), and (x4, y4), respectively. According to the set compensation margin (the second set compensation margin), the second set position information is adjusted respectively, and the four coordinate points corresponding to the second adjusted position information are configured as (x3-z, y3-z), (x3-z, y4+z), (x4+z, y3-z), and (x4+z, y4+z).

[0201] In embodiments of this disclosure, a method for determining the first predetermined position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process includes: detecting multiple first highest point position information, multiple first lowest point position information, multiple first leftmost position information, and multiple first rightmost position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process; and determining the first predetermined position information corresponding to the two-dimensional DR left lung images at multiple moments during the breathing process based on the multiple first highest point position information, the multiple first lowest point position information, the multiple first leftmost position information, and the multiple first rightmost position information.

[0202] In embodiments of this disclosure, the method for detecting multiple first highest point position information, multiple first lowest point position information, multiple first leftmost position information, and multiple first rightmost position information corresponding to two-dimensional DR left lung images at multiple moments during the breathing process includes: acquiring multiple first mask images corresponding to two-dimensional DR left lung images at multiple moments during the breathing process; determining multiple corresponding left lung edge images based on the multiple first mask images; and detecting multiple first highest point position information, multiple first lowest point position information, multiple first leftmost position information, and multiple first rightmost position information corresponding to two-dimensional DR left lung images at multiple moments during the breathing process based on the multiple left lung edge images.

[0203] In embodiments of this disclosure and other possible embodiments, the plurality of first mask images are configured to perform costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edge detection on the left chest image of the two-dimensional DR lung image at multiple time points during the breathing process, to obtain a plurality of mask images corresponding to the two-dimensional DR left lung image at multiple time points; or, the plurality of mask images corresponding to the two-dimensional DR left lung image at multiple time points output by the segmentation model. The values ​​of the plurality of mask images can be configured as a first value. For example, the first value can be configured as 1 or other values.

[0204] In embodiments of this disclosure and other possible embodiments, the method for determining multiple corresponding left lung edge images based on the multiple first mask images includes: obtaining a set edge detection algorithm, and using the set edge detection algorithm to determine the multiple corresponding left lung edge images on the multiple first mask images. The set edge detection algorithm can be configured as an edge detection algorithm based on one or more algorithms such as the Roberts operator, Prewitt operator, Sobel operator, Canny operator, and Laplacian operator.

[0205] Meanwhile, in the embodiments and other possible embodiments of this disclosure, a method for determining a plurality of corresponding left lung edge images is proposed. The method for determining the plurality of corresponding left lung edge images based on the plurality of first mask images includes: obtaining a first predetermined erosion pixel value; performing erosion operations on the plurality of first mask images according to the first predetermined erosion pixel value to obtain a plurality of corresponding first mask eroded images; and determining the plurality of corresponding left lung edge images based on the plurality of first mask eroded images and the corresponding plurality of first mask images. Wherein, the first predetermined erosion pixel value can be configured to 1.

[0206] In embodiments of this disclosure and other possible embodiments, the method for determining a plurality of corresponding left lung edge images based on the plurality of first mask erosion images and the corresponding plurality of first mask images includes: subtracting the corresponding plurality of first mask erosion images from the plurality of first mask images respectively to determine the corresponding plurality of left lung edge images.

[0207] In embodiments of this disclosure, the method for determining the first predetermined position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process based on the plurality of first highest point position information, the plurality of first lowest point position information, the plurality of first leftmost point position information, and the plurality of first rightmost point position information includes: extracting the ordinates of the plurality of first highest points and the plurality of first lowest points from the plurality of first highest point position information and the plurality of first lowest point position information respectively; determining the maximum value of the first ordinate corresponding to the plurality of first highest point ordinates and the minimum value of the first ordinate corresponding to the plurality of first lowest point ordinates; extracting the abscissas of the plurality of first leftmost points and the plurality of first rightmost points from the plurality of first leftmost point position information and the plurality of first rightmost point position information respectively; determining the minimum value of the first abscissa corresponding to the plurality of first leftmost abscissas and the maximum value of the first abscissa corresponding to the plurality of first rightmost abscissas; and determining the first predetermined position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process based on the maximum value of the first ordinate, the minimum value of the first ordinate, the minimum value of the first abscissa, and the maximum value of the first abscissa.

[0208] In an embodiment of this disclosure, the method for determining the first set position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process based on the first maximum value of the first ordinate, the first minimum value of the first ordinate, the first minimum value of the first abscissa, and the first maximum value of the first abscissa includes: drawing two corresponding first y-axis perpendicular lines to the y-axis using the first maximum value of the first ordinate and the first minimum value of the first ordinate respectively; drawing two corresponding first x-axis perpendicular lines to the x-axis using the first minimum value of the first abscissa and the first maximum value of the first abscissa respectively; and configuring the intersection of the first y-axis perpendicular line and the first x-axis perpendicular line as the first set position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process.

[0209] In other words, the method for determining the first set position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process based on the first maximum value of the first vertical coordinate y1, the first minimum value of the first vertical coordinate y2, the first minimum value of the first horizontal coordinate x1, and the first maximum value of the first horizontal coordinate x2 includes: configuring the first set position information corresponding to the two-dimensional DR left lung image at multiple moments during the breathing process as position information corresponding to a matrix; wherein, the four coordinate points of the matrix are configured as (x1, y1), (x1, y2), (x2, y1), and (x2, y2), respectively.

[0210] In embodiments of this disclosure, a method for determining second predetermined position information corresponding to two-dimensional DR right lung images at multiple moments during the breathing process includes: detecting multiple second highest point position information, multiple second lowest point position information, multiple second rightmost point position information, and multiple second rightmost point position information corresponding to two-dimensional DR right lung images at multiple moments during the breathing process; and determining the second predetermined position information corresponding to two-dimensional DR right lung images at multiple moments during the breathing process based on the multiple second highest point position information, the multiple second lowest point position information, the multiple second rightmost point position information, and the multiple second rightmost point position information.

[0211] In embodiments of this disclosure, the method for detecting multiple second highest point position information, multiple second lowest point position information, multiple second rightmost point position information, and multiple second rightmost point position information corresponding to two-dimensional DR right lung images at multiple moments during the breathing process includes: acquiring multiple second mask images corresponding to two-dimensional DR right lung images at multiple moments during the breathing process; determining multiple right lung edge images based on the multiple second mask images; and detecting multiple second highest point position information, multiple second lowest point position information, multiple second rightmost point position information, and multiple second rightmost point position information corresponding to two-dimensional DR right lung images at multiple moments during the breathing process based on the multiple right lung edge images.

[0212] In embodiments of this disclosure and other possible embodiments, the plurality of second mask images are configured to detect the costal margin boundary, lung apex boundary, and mediastinal and transverse diaphragmatic edges of the right chest image of the two-dimensional DR lung image at multiple time points during the breathing process, thereby obtaining a plurality of mask images corresponding to the two-dimensional DR right lung image at multiple time points; or, the plurality of mask images corresponding to the two-dimensional DR right lung image at multiple time points output by the segmentation model. The values ​​of the plurality of mask images can be configured to be second values ​​that are different from the first value. For example, the second value can be configured to 2 or other values ​​that are different from the first value.

[0213] In embodiments of this disclosure and other possible embodiments, the method for determining corresponding right lung edge images based on the plurality of second mask images includes: obtaining a set edge detection algorithm, and using the set edge detection algorithm to determine corresponding right lung edge images on the plurality of second mask images respectively. The set edge detection algorithm can be configured as an edge detection algorithm based on one or more algorithms such as the Roberts operator, Prewitt operator, Sobel operator, Canny operator, and Laplacian operator.

[0214] Meanwhile, in the embodiments and other possible embodiments of this disclosure, a method for determining a plurality of corresponding right lung edge images is proposed. The method for determining the plurality of corresponding right lung edge images based on the plurality of second mask images includes: obtaining a second predetermined erosion pixel value; performing erosion operations on the plurality of second mask images according to the second predetermined erosion pixel value to obtain a plurality of corresponding second mask eroded images; and determining the plurality of corresponding right lung edge images based on the plurality of second mask eroded images and the corresponding plurality of second mask images. The second predetermined erosion pixel value can be configured to 1.

[0215] In embodiments of this disclosure and other possible embodiments, the method for determining a plurality of corresponding right lung edge images based on the plurality of second mask erosion images and the corresponding plurality of second mask images includes: subtracting the corresponding plurality of second mask erosion images from the plurality of second mask images respectively to determine the corresponding plurality of right lung edge images.

[0216] In embodiments of this disclosure, the method for determining the second predetermined position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process based on the plurality of second highest point position information, the plurality of second lowest point position information, the plurality of second rightmost point position information, and the plurality of second rightmost point position information includes: extracting the ordinates of the plurality of second highest points and the plurality of second lowest points from the plurality of second highest point position information and the plurality of second lowest point position information respectively; determining the maximum value of the second ordinate corresponding to the plurality of second highest point ordinates and the minimum value of the second ordinate corresponding to the plurality of second lowest point ordinates respectively; extracting the plurality of second rightmost point abscissas and the plurality of second rightmost point abscissas from the plurality of second rightmost point position information and the plurality of second rightmost point abscissas respectively; determining the minimum value of the second abscissa corresponding to the plurality of second rightmost point abscissas and the maximum value of the second abscissa corresponding to the plurality of second rightmost point abscissas respectively; and determining the second predetermined position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process based on the maximum value of the second ordinate, the minimum value of the second ordinate, the minimum value of the second abscissa, and the maximum value of the second abscissa.

[0217] In an embodiment of this disclosure, the method for determining the second set position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process based on the second maximum value of the second ordinate, the second minimum value of the second ordinate, the second minimum value of the second abscissa, and the second maximum value of the second abscissa includes: drawing two corresponding second y-axis perpendicular lines to the y-axis using the second maximum value of the second ordinate and the second minimum value of the second ordinate respectively; drawing two corresponding second x-axis perpendicular lines to the x-axis using the second minimum value of the second abscissa and the second maximum value of the second abscissa respectively; and configuring the intersection of the second y-axis perpendicular line and the second x-axis perpendicular line as the second set position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process.

[0218] In other words, the method for determining the second set position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process based on the second maximum value of the second ordinate y3, the second minimum value of the second ordinate y4, the second minimum value of the second abscissa x3, and the second maximum value of the second abscissa x4 includes: configuring the second set position information corresponding to the two-dimensional DR right lung image at multiple moments during the breathing process as position information corresponding to a matrix; wherein, the four coordinate points of the matrix are configured as (x3, y3), (x3, y4), (x4, y3), and (x4, y4), respectively.

[0219] Step S102: Register the left lung images at adjacent times in the multiple left lung images to obtain multiple corresponding first registered images; and / or, register the right lung images at adjacent times in the multiple right lung images to obtain multiple corresponding second registered images.

[0220] In embodiments of this disclosure, the method of registering left lung images at adjacent time points in the plurality of left lung images to obtain a plurality of corresponding first registered images includes: obtaining a first registration model and its corresponding first setting rule; using the first registration model to register left lung images at adjacent time points in the plurality of left lung images; and using the first setting rule to terminate the registration of left lung images at adjacent time points in the plurality of left lung images.

[0221] In the embodiments of this disclosure and other possible embodiments, the registration method for registering left lung images at adjacent time points in the multiple left lung images can employ existing registration algorithms or models (first registration model), such as one or more of the SIFT (Scale-invariant feature transform) registration algorithm or model, SURF (Speeded Up Robust Features) registration algorithm or model, ORB (Oriented FAST and Rotated BRIEF) registration algorithm or model, or other registration algorithms or models based on convolutional neural networks. For example, the registration algorithm or model based on convolutional neural networks can be configured as a registration algorithm or model based on VGG networks or based on the SimpleElastix registration algorithm or model specifically for medical images.

[0222] In the embodiments of this disclosure, the first parameter map of the first registration model is configured as an affine transformation; and / or, based on the configuration of the first parameter map of the first registration model as an affine transformation, one or more of a translation transformation, a rigid transformation, and a B-spline are further configured in the first parameter map; or, based on the configuration of the first parameter map of the first registration model as one or more of a translation transformation, a rigid transformation, and a B-spline, an affine transformation is further configured in the first parameter map.

[0223] In the embodiments of this disclosure, the first setting rule is configured as a first preset registration number and / or a first preset similarity; when the first setting rule is configured as the first preset registration number, if the first number of registrations of the left lung images at adjacent times in the plurality of left lung images is greater than or equal to the first preset registration number, then the registration of the left lung images at adjacent times in the plurality of left lung images ends; when the first setting rule is configured as the first preset similarity, the similarity of the left lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the first preset similarity, then the registration of the left lung images at adjacent times in the plurality of left lung images ends; when the first setting rule is configured as the first preset registration number and the first preset similarity, when the first setting rule When configured with a first preset registration count, if the first registration count of left lung images at adjacent times in the multiple left lung images is greater than or equal to the first preset registration count, then the registration of left lung images at adjacent times in the multiple left lung images ends; if the first registration count of left lung images at adjacent times in the multiple left lung images is greater than or equal to the first preset registration count, then the registration of left lung images at adjacent times in the multiple left lung images ends; if the first registration count of left lung images at adjacent times in the multiple left lung images is less than the first preset registration count, then the similarity of left lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the first preset similarity, then the registration of left lung images at adjacent times in the multiple left lung images ends.

[0224] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the first preset registration number and / or the first preset similarity according to actual needs. For example, the first preset registration number can be configured to 20 or other values, and the first preset similarity can be set to 0.8 or other values.

[0225] In one embodiment of this disclosure, the method of registering left lung images at adjacent time points in the plurality of left lung images using the first registration model includes: configuring the left lung image at the previous time point in the adjacent time point left lung images as a first fixed left lung image; configuring the left lung image corresponding to the previous time point and the next time point in the adjacent time points as a first floating left lung image; and registering the first floating left lung image to the first fixed left lung image using the first registration model. The first registration model can be configured as the registration algorithm or model used in the above-described registration method for registering left lung images at adjacent time points in the plurality of left lung images.

[0226] In an embodiment of this disclosure, the method for calculating the similarity of left lung images at adjacent moments during the registration process includes: performing erosion operations on a first fixed left lung image and a first floating left lung image during the registration process according to a set erosion pixel value, respectively, to obtain corresponding first fixed left lung eroded images and first floating left lung eroded images; obtaining a corresponding first fixed left lung boundary image based on the first fixed left lung image and the first fixed eroded left lung image; obtaining a corresponding first floating left lung boundary image based on the first floating left lung image and the first floating eroded left lung image; and calculating the similarity between the first fixed left lung boundary image and the first floating left lung boundary image to obtain the similarity of left lung images at adjacent moments during the registration process.

[0227] In embodiments of this disclosure and other possible embodiments, the method for obtaining a corresponding first floating left lung boundary image based on the first floating left lung image and the first floating eroded left lung image includes: subtracting the first floating eroded left lung image from the first floating left lung image to obtain the corresponding first floating left lung boundary image.

[0228] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the set erosion pixel value according to actual needs. For example, the set erosion pixel value can be configured to 1 or other values.

[0229] In embodiments of this disclosure, a method for registering right lung images at adjacent time points in a plurality of right lung images to obtain a plurality of corresponding second registered images includes: obtaining a second registration model and its corresponding second setting rule; using the second registration model to register right lung images at adjacent time points in the plurality of right lung images; and using the second setting rule to terminate the registration of right lung images at adjacent time points in the plurality of right lung images.

[0230] In the embodiments of this disclosure, the second parameter map of the second registration model is configured as an affine transformation; and / or, based on the configuration of the second parameter map of the second registration model as an affine transformation, one or more of a translation transformation, a rigid transformation, and a B-spline are further configured in the second parameter map; or, based on the configuration of the second parameter map of the second registration model as one or more of a translation transformation, a rigid transformation, and a B-spline, an affine transformation is further configured in the second parameter map.

[0231] In the embodiments of this disclosure and other possible embodiments, the method of registering right lung images at adjacent time points in the plurality of right lung images to obtain corresponding plurality of second registered images can employ existing registration algorithms or models (second registration models), such as one or more of SIFT (Scale-invariant feature transform) registration algorithms or models, SURF (Speeded Up Robust Features) registration algorithms or models, ORB (Oriented FAST and Rotated BRIEF) registration algorithms or models, or other registration algorithms or models based on convolutional neural networks. For example, the registration algorithm or model based on convolutional neural networks can be configured as a registration algorithm or model based on VGG networks or based on the SimpleElastix registration algorithm or model specifically for medical images.

[0232] In the embodiments of this disclosure, the second setting rule is configured as a second preset registration number and / or a second preset similarity; when the second setting rule is configured as a second preset registration number, if the second number of registrations of right lung images at adjacent times in the plurality of right lung images is greater than or equal to the second preset registration number, then the registration of right lung images at adjacent times in the plurality of right lung images ends; when the second setting rule is configured as a second preset similarity, the similarity of right lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the second preset similarity, then the registration of right lung images at adjacent times in the plurality of right lung images ends; when the second setting rule is configured as a second preset registration number and a second preset similarity, when the second setting rule When configured with a second preset number of registrations, if the second number of registrations of the right lung images at adjacent times in the multiple right lung images is greater than or equal to the second preset number of registrations, then the registration of the right lung images at adjacent times in the multiple right lung images ends; if the second number of registrations of the right lung images at adjacent times in the multiple right lung images is greater than or equal to the second preset number of registrations, then the registration of the right lung images at adjacent times in the multiple right lung images ends; if the second number of registrations of the right lung images at adjacent times in the multiple right lung images is less than the second preset number of registrations, the similarity of the right lung images at adjacent times in the registration process is calculated; if the similarity is greater than or equal to the second preset similarity, then the registration of the right lung images at adjacent times in the multiple right lung images ends.

[0233] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the second preset registration number and / or the second preset similarity according to actual needs. For example, the second preset registration number can be configured to 20 or other values, and the second preset similarity can be set to 0.8 or other values.

[0234] In one embodiment of this disclosure, the method of registering right lung images at adjacent times in the plurality of right lung images using the second registration model includes: configuring the right lung image at the previous time in the right lung images at adjacent times as a second fixed right lung image; configuring the right lung image corresponding to the previous time and the next time in the adjacent times as a second floating right lung image; and registering the second floating right lung image to the second fixed right lung image using the second registration model.

[0235] In an embodiment of this disclosure, the method for calculating the similarity of right lung images at adjacent time points during the registration process includes: performing erosion operations on a second fixed right lung image and a second floating right lung image during the registration process according to a set erosion pixel value, respectively, to obtain corresponding second fixed right lung eroded images and second floating right lung eroded images; obtaining a corresponding second fixed right lung boundary image based on the second fixed right lung image and the second fixed eroded right lung image; obtaining a corresponding second floating right lung boundary image based on the second floating right lung image and the second floating eroded right lung image; and calculating the similarity between the second fixed right lung boundary image and the second floating right lung boundary image to obtain the similarity of right lung images at adjacent time points during the registration process.

[0236] In embodiments of this disclosure and other possible embodiments, the method for obtaining a corresponding second floating right lung boundary image based on the second floating right lung image and the second floating eroded right lung image includes: subtracting the second floating eroded right lung image from the second floating right lung image to obtain the corresponding second floating right lung boundary image.

[0237] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the set erosion pixel value according to actual needs. For example, the set erosion pixel value can be configured to 1 or other values.

[0238] Step S103: Determine the first fixed image and / or the second fixed image from the plurality of left lung images and / or the plurality of right lung images respectively.

[0239] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can determine a first fixed image and / or a second fixed image from the plurality of left lung images and / or the plurality of right lung images according to actual needs. For example, the first fixed image and the second fixed image can be determined from the first registration image with the largest left lung area from the plurality of left lung images and the second registration image with the largest right lung area from the plurality of right lung images.

[0240] Step S104: Register any first registration image other than the first registration image corresponding to the first fixed image to the first fixed image, and / or register any second registration image other than the second fixed image to the second fixed image.

[0241] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can determine any first registration image other than the first fixed image as a plurality of first floating images, and any second registration image other than the second registration image corresponding to the second fixed image as a plurality of second floating reference images, according to actual needs. Wherein, at least one of the plurality of first floating images and one of the second floating reference images is configured. For example, the first registration image with the smallest left lung area among the plurality of left lung images and the second registration image with the smallest right lung area among the plurality of right lung images can be determined as the first floating image and the second floating image, respectively.

[0242] For example, the multiple left lung images are configured as 10 left lung images acquired at multiple moments during the breathing process, with the 10 left lung images at adjacent moments designated as L1, L2, L3, L4, L5, L6, L7, L8, L9, and L10. The left lung images at adjacent moments in the multiple left lung images are registered to obtain multiple corresponding first registration images. For example, the left lung image at the next adjacent moment is registered to the left lung image at the previous moment, resulting in multiple first registration images AL1(L1), AL2, AL3, AL4, AL5, AL6, AL7, AL8, AL9, and AL10. The first fixed image in the multiple left lung images is determined to be L6. Then, any other first registration image (AL1(L1) or AL2 or AL3 or AL4 or AL5 or AL7 or AL8 or AL9 or AL10) other than the first registration image AL6 corresponding to the first fixed image L6 is registered to the first fixed image.

[0243] For example, the multiple right lung images are configured as 10 right lung images acquired at multiple moments during the breathing process, with 10 right lung images at adjacent moments designated as R1, R2, R3, R4, R5, R6, R7, R8, R9, and R10. The right lung images at adjacent moments in the multiple right lung images are registered to obtain multiple corresponding second registration images. For example, the right lung image at a later moment is registered to the right lung image at a previous moment, resulting in multiple second registration images AR1(R1), AR2, AR3, AR4, AR5, AR6, AR7, AR8, AR9, and AR10. The second fixed image in the multiple right lung images is determined to be R6. Then, any other second registration image (AR1(R1), AR2, AR3, AR4, AR5, AR7, AR8, AR9, or AR10) other than the second registration image AR6 corresponding to the second fixed image R6 is registered to the second fixed image.

[0244] In the embodiments of this disclosure and other possible embodiments, any other first registration image other than the first fixed image and not adjacent to the first fixed image at any time is registered to the first fixed image, and / or any other second registration image other than the second fixed image and not adjacent to the second fixed image at any time is registered to the second fixed image.

[0245] In embodiments of this disclosure, the method of registering any other first registered image besides the first fixed image to the first fixed image, or registering any other first registered image besides the first fixed image at a time not adjacent to the first fixed image, to the first fixed image, includes: obtaining a third registration model and its corresponding third setting rule; using the third registration model to register any other first registered image besides the first fixed image to the first fixed image, or registering any other first registered image besides the first fixed image at a time not adjacent to the first fixed image, to the first fixed image; and using the third setting rule to terminate the registration of any other first registered image besides the first fixed image to the first fixed image, or terminate the registration of any other first registered image besides the first fixed image at a time not adjacent to the first fixed image, to the first fixed image.

[0246] In the embodiments of this disclosure and other possible embodiments, the registration methods of registering any other first registered image besides the first fixed image to the first fixed image, or registering any other first registered image besides the first fixed image and not adjacent to the first fixed image to the first fixed image, can employ existing registration algorithms or models (third configuration models), such as one or more of SIFT (Scale-invariant feature transform) registration algorithms or models, SURF (Speeded Up Robust Features) registration algorithms or models, ORB (Oriented FAST and Rotated BRIEF) registration algorithms or models, or other registration algorithms or models based on convolutional neural networks. For example, the registration algorithm or model based on convolutional neural networks can be configured as a registration algorithm or model based on VGG networks or based on the SimpleElastix registration algorithm or model specifically for medical images.

[0247] In the embodiments of this disclosure, the third parameter graph of the third configuration model is configured as an affine transformation; and / or, based on the configuration of the third parameter graph of the third configuration model as an affine transformation, one or more of a translation transformation, a rigid transformation, and a B-spline are further configured in the third parameter graph; or, based on the configuration of the third parameter graph of the third configuration model as one or more of a translation transformation, a rigid transformation, and a B-spline, an affine transformation is further configured in the third parameter graph.

[0248] In the embodiments of this disclosure, the third setting rule is configured as a third preset registration number and / or a third preset similarity; when the third setting rule is configured as a third preset registration number, if the third registration of the left lung images at adjacent times in the plurality of left lung images is greater than or equal to the third preset registration number, then the registration of any other first registration image besides the first fixed image to the first fixed image is terminated, or the registration of any other first registration image at a time other than the first fixed image and not adjacent to the first fixed image is terminated; when the third setting rule is configured as a third preset similarity, the similarity between the first fixed image and any other first registration image during the registration process is calculated respectively; if the similarity is greater than or equal to the third preset similarity, then the registration of any other first registration image besides the first fixed image to the first fixed image is terminated, or the registration of any other first registration image at a time other than the first fixed image and not adjacent to the first fixed image is terminated; when the third setting rule is configured as a third preset registration number and a third preset similarity, when the third setting rule When configured with a third preset registration count, if the third registration count of the left lung images at adjacent times in the plurality of left lung images is greater than or equal to the third preset registration count, then the registration of any other first registered image (excluding the first fixed image) to the first fixed image is terminated, or the registration of any other first registered image at a time other than the first fixed image and not adjacent to the first fixed image is terminated. If the third registration count of the left lung images at adjacent times in the plurality of left lung images is greater than or equal to the third preset registration count, then the registration of the left lung images at adjacent times in the plurality of left lung images is terminated. If the third registration count of the left lung images at adjacent times in the plurality of left lung images is less than the third preset registration count, the similarity between the first fixed image and any other first registered image during the registration process is calculated respectively. If the similarity is greater than or equal to the third preset similarity, then the registration of any other first registered image (excluding the first fixed image) to the first fixed image is terminated, or the registration of any other first registered image at a time other than the first fixed image and not adjacent to the first fixed image is terminated.

[0249] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the third preset registration number and / or the third preset similarity according to actual needs. For example, the third preset registration number can be configured to 20 or other values, and the third preset similarity can be set to 0.8 or other values.

[0250] In embodiments of this disclosure, the method for calculating the similarity between the first fixed image and any other first registered image during the registration process includes: performing erosion operations on the first fixed image and any other first registered image during the registration process according to a set erosion pixel value to obtain a corresponding third fixed left lung erosion image and a third floating left lung erosion image; obtaining a corresponding third fixed left lung boundary image based on the third fixed left lung image and the third fixed eroded left lung image; obtaining a corresponding third floating left lung boundary image based on the third floating left lung image and the third floating eroded left lung image; and calculating the similarity between the third fixed left lung boundary image and the third floating left lung boundary image to obtain the similarity of the left lung images at adjacent time points during the registration process.

[0251] In embodiments of this disclosure and other possible embodiments, the method for obtaining a corresponding third floating left lung boundary image based on the third floating left lung image and the third floating eroded left lung image includes: subtracting the third floating eroded left lung image from the third floating left lung image to obtain the corresponding third floating left lung boundary image.

[0252] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the set erosion pixel value according to actual needs. For example, the set erosion pixel value can be configured to 1 or other values.

[0253] In the embodiments of this disclosure and other possible embodiments, the registration methods of registering any other second registered image besides the second fixed image to the second fixed image, or registering any other second registered image besides the second fixed image and not adjacent to the second fixed image to the second fixed image, can employ existing registration algorithms or models (fourth configuration model), such as one or more of SIFT (Scale-invariant feature transform) registration algorithms or models, SURF (Speeded Up Robust Features) registration algorithms or models, ORB (Oriented FAST and Rotated BRIEF) registration algorithms or models, or other registration algorithms or models based on convolutional neural networks. For example, the registration algorithm or model based on convolutional neural networks can be configured as a registration algorithm or model based on VGG networks or based on the SimpleElastix registration algorithm or model specifically for medical images.

[0254] In the embodiments of this disclosure, the fourth parameter graph of the fourth configuration model is configured as an affine transformation; and / or, based on the fourth parameter graph of the fourth configuration model being configured as an affine transformation, one or more of a translation transformation, a rigid transformation, and a B-spline are further configured in the fourth parameter graph; or, based on the fourth parameter graph of the fourth configuration model being configured as one or more of a translation transformation, a rigid transformation, and a B-spline, an affine transformation is further configured in the fourth parameter graph.

[0255] In the embodiments of this disclosure, the fourth setting rule is configured as a fourth preset registration number and / or a fourth preset similarity; when the fourth setting rule is configured as a fourth preset registration number, if the fourth registration number of the left lung images at adjacent times in the plurality of left lung images is greater than or equal to the fourth preset registration number, then the registration of any other second registration image besides the second fixed image to the second fixed image is terminated, or the registration of any other second registration image at a time other than the second fixed image and not adjacent to the second fixed image is terminated; when the fourth setting rule is configured as a fourth preset similarity, the similarity between the second fixed image and any other second registration image during the registration process is calculated respectively; if the similarity is greater than or equal to the fourth preset similarity, then the registration of any other second registration image besides the second fixed image to the second fixed image is terminated, or the registration of any other second registration image at a time other than the second fixed image and not adjacent to the second fixed image is terminated; when the fourth setting rule is configured as a fourth preset registration number and a fourth preset similarity, when the fourth setting rule When configured with a fourth preset registration count, if the fourth registration count of left lung images at adjacent times in the plurality of left lung images is greater than or equal to the fourth preset registration count, then the registration of any other second registered image (excluding the second fixed image) to the second fixed image is terminated, or the registration of any other second registered image at a time other than the second fixed image and not adjacent to the second fixed image is terminated. If the fourth registration count of left lung images at adjacent times in the plurality of left lung images is greater than or equal to the fourth preset registration count, then the registration of left lung images at adjacent times in the plurality of left lung images is terminated. If the fourth registration count of left lung images at adjacent times in the plurality of left lung images is less than the fourth preset registration count, the similarity between the second fixed image and any other second registered image during the registration process is calculated respectively. If the similarity is greater than or equal to the fourth preset similarity, then the registration of any other second registered image (excluding the second fixed image) to the second fixed image is terminated, or the registration of any other second registered image at a time other than the second fixed image and not adjacent to the second fixed image is terminated.

[0256] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the fourth preset registration number and / or the fourth preset similarity according to actual needs. For example, the fourth preset registration number can be configured to 20 or other values, and the fourth preset similarity can be set to 0.8 or other values.

[0257] In embodiments of this disclosure, the method for calculating the similarity between the second fixed image and any other second registered image during the registration process includes: performing erosion operations on the second fixed image and any other second registered image during the registration process according to a set erosion pixel value to obtain a corresponding fourth fixed left lung erosion image and a fourth floating left lung erosion image; obtaining a corresponding fourth fixed left lung boundary image based on the fourth fixed left lung image and the fourth fixed eroded left lung image; obtaining a corresponding fourth floating left lung boundary image based on the fourth floating left lung image and the fourth floating eroded left lung image; and calculating the similarity between the fourth fixed left lung boundary image and the fourth floating left lung boundary image to obtain the similarity of the left lung images at adjacent time points during the registration process.

[0258] In embodiments of this disclosure and other possible embodiments, the method for obtaining a corresponding fourth floating left lung boundary image based on the fourth floating left lung image and the fourth floating eroded left lung image includes: subtracting the fourth floating eroded left lung image from the fourth floating left lung image to obtain the corresponding fourth floating left lung boundary image.

[0259] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the set erosion pixel value according to actual needs. For example, the set erosion pixel value can be configured to 1 or other values.

[0260] Figure 2 A flowchart illustrating a lesion localization method according to an embodiment of this disclosure is shown. Figure 2 As shown, a lesion localization method includes the lung image registration method described above or the lung image registration device described above for registration, and steps S201: determining a first fixed image and a second fixed image from the first registered image with the largest left lung area among the multiple left lung images and the second registered image with the largest right lung area among the multiple right lung images; step S202: determining a first floating image and a second floating image from the first registered image with the smallest left lung area among the multiple left lung images and the second registered image with the smallest right lung area among the multiple right lung images; step S203: registering the first floating image and the second floating image with the first fixed image and the second fixed image respectively to obtain a left lung registered image and a right lung registered image; step S204: locating the location of an air retention lesion in the left lung based on the first fixed image and the left lung registered image; and locating the location of an air retention lesion in the right lung based on the second fixed image and the right lung registered image.

[0261] In the embodiments of this disclosure, based on the obtained set air threshold range, the left lung air regions corresponding to the first fixed image and the left lung registration image are determined respectively; the first difference corresponding to the same position in the left lung air regions of the first fixed image and the left lung registration image is calculated; and the position corresponding to the first difference being less than or equal to the obtained first preset difference threshold is configured as the left lung air retention lesion position.

[0262] In an embodiment of this disclosure, the method for locating the right lung air retention lesion based on the second fixed image and the right lung registration image includes: determining the right lung air region corresponding to the second fixed image and the right lung registration image based on an acquired preset air threshold range; calculating a second difference corresponding to the same position in the right lung air region of the second fixed image and the right lung registration image; and configuring the position corresponding to the second difference being less than or equal to the acquired second preset difference threshold as the right lung air retention lesion location.

[0263] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the set air threshold range, the first preset difference threshold, and the second preset difference threshold according to actual needs.

[0264] In embodiments of this disclosure, before locating the location of the left lung air retention lesion based on the first fixed image and the left lung registration image, the method includes: removing the boundaries of the first fixed image and the left lung registration image based on an acquired first preset boundary distance to obtain a corresponding first fixed processed image and a left lung registration processed image; locating the location of the left lung air retention lesion based on the first fixed processed image and the left lung registration processed image. The method for locating the location of the left lung air retention lesion based on the first fixed processed image and the left lung registration processed image includes: determining the left lung air region corresponding to the first fixed processed image and the left lung registration processed image based on an acquired preset air threshold range; calculating a third difference corresponding to the left lung air region corresponding to the first fixed processed image and the left lung registration processed image; and configuring the location corresponding to the third difference being less than or equal to an acquired third preset difference threshold as the location of the left lung air retention lesion.

[0265] Before locating the right lung air retention lesion location based on the second fixed image and the right lung registration image, the method includes: removing the boundaries of the second fixed image and the right lung registration image based on the acquired second preset boundary distance to obtain corresponding second fixed processed image and right lung registration processed image; locating the right lung air retention lesion location based on the second fixed processed image and the right lung registration processed image. Specifically, the method for locating the right lung air retention lesion location based on the second fixed processed image and the right lung registration processed image includes: determining the right lung air region corresponding to the second processed fixed image and the right lung registration processed image based on the acquired preset air threshold range; calculating a fourth difference value corresponding to the right lung air region corresponding to the second fixed processed image and the right lung registration processed image; and configuring the location corresponding to the fourth difference value being less than or equal to the acquired fourth preset difference value threshold as the right lung air retention lesion location.

[0266] In the embodiments of this disclosure and other possible embodiments, those skilled in the art can configure the first set boundary distance, the second set boundary distance, the set air threshold interval, the third preset difference threshold, and the fourth preset difference threshold according to actual needs.

[0267] In the embodiments of this disclosure and other possible embodiments, since the location of air retention lesions cannot be located in the lung edge region of the right and left lungs, the boundaries of the first fixed image, the left lung registration image, the second fixed image and the right lung registration image are removed by using the first set boundary distance and the second set boundary distance respectively, thereby improving the accuracy and practicality of determining the location of air retention lesions.

[0268] In embodiments of this disclosure, before acquiring multiple left lung images and / or multiple right lung images at multiple moments during the breathing process, rib removal is performed on the two-dimensional DR left lung images and / or two-dimensional DR right lung images at multiple moments during the breathing process, respectively, to obtain multiple left lung images and / or multiple right lung images at multiple moments during the breathing process.

[0269] In the embodiments of this disclosure and other possible embodiments, rib ablation is performed on the two-dimensional DR left lung image and / or two-dimensional DR right lung image at multiple moments during the breathing process, respectively, to avoid the influence of ribs on the location of air retention lesions, thereby improving the accuracy and practicality of determining the location of air retention lesions.

[0270] The entity executing the lung image registration method and / or ventilation retention can be a lung image registration device and / or a ventilation retention device. For example, the lung image registration and / or ventilation retention method can be executed by a terminal device, a server, or other processing device. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, the lung image registration and / or ventilation retention method can be implemented by a processor calling computer-readable instructions stored in memory.

[0271] Those skilled in the art will understand that in the above-described lung image registration and / or ventilation retention method in specific embodiments, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0272] This disclosure also provides a block diagram of a lung image registration device, comprising: an acquisition unit for acquiring multiple left lung images and / or multiple right lung images at multiple time points during respiration; wherein the multiple left lung images and / or the multiple right lung images are configured as two-dimensional DR images; a first registration unit for registering left lung images at adjacent time points in the multiple left lung images to obtain multiple corresponding first registration images; and / or for registering right lung images at adjacent time points in the multiple right lung images to obtain multiple corresponding second registration images; a first determination unit for determining a first fixed image and / or a second fixed image in the multiple left lung images and / or the multiple right lung images; and a second registration unit for registering any other first registration image (excluding the first fixed image) to the first fixed image, and / or registering any other second registration image (excluding the second fixed image) to the second fixed image. This addresses the problem of low accuracy in current multi-time point image registration, which affects subsequent lung disease analysis.

[0273] This disclosure also proposes a lesion localization device, which includes a registration model, a first lesion localization unit, and a second lesion localization unit registered using the lung image registration method described above; or, it includes a lung image registration device, a second determination unit, a first lesion localization unit, and a second lesion localization unit as described above.

[0274] Wherein, the registration model is used to determine a first fixed image and a second fixed image from the first registration image with the largest left lung area among the multiple left lung images and the second registration image with the largest right lung area among the multiple right lung images; the registration model is also used to determine a first floating image and a second floating image from the first registration image with the smallest left lung area among the multiple left lung images and the second registration image with the smallest right lung area among the multiple right lung images; the registration model is also used to register the first floating image and the second floating image with the first fixed image and the second fixed image respectively to obtain a left lung registration image and a right lung registration image; wherein, the first lesion localization unit is used to locate the location of the left lung air retention lesion based on the first fixed image and the left lung registration image; wherein, the second lesion localization unit is used to locate the location of the right lung air retention lesion based on the second fixed image and the right lung registration image; or, wherein, the The lung image registration device includes a first determining unit, configured to determine a first fixed image and a second fixed image from the first registered image with the largest left lung area among the multiple left lung images and the second registered image with the largest right lung area among the multiple right lung images; a second determining unit, configured to determine a first floating image and a second floating image from the first registered image with the smallest left lung area among the multiple left lung images and the second registered image with the smallest right lung area among the multiple right lung images; a second registration unit, configured to register the first floating image and the second floating image with the first fixed image and the second fixed image to obtain a left lung registration image and a right lung registration image; a first lesion localization unit, configured to locate the location of an air retention lesion in the left lung based on the first fixed image and the left lung registration image; and a second lesion localization unit, configured to locate the location of an air retention lesion in the right lung based on the second fixed image and the right lung registration image.

[0275] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above embodiments of lung image registration and / or ventilation retention methods. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0276] This disclosure also proposes a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the aforementioned lung image registration and / or ventilatory retention method. The computer-readable storage medium can be a non-volatile computer-readable storage medium. This addresses the problem of low accuracy in multi-image registration at multiple time points, which affects subsequent lung disease analysis.

[0277] This disclosure also proposes an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured for the aforementioned lung image registration and / or ventilatory retention method. The electronic device can be provided as a terminal, server, or other type of device. This addresses the problem of low accuracy in multi-image registration at multiple time points, which affects subsequent lung disease analysis.

[0278] Figure 3 This is a block diagram illustrating an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, or other terminal.

[0279] Reference Figure 3 The electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0280] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0281] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of this data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0282] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0283] Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0284] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0285] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0286] Sensor assembly 814 includes one or more sensors for providing state assessment of various aspects of electronic device 800. For example, sensor assembly 814 can detect the on / off state of electronic device 800, the relative malfunctioning location of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or a component of electronic device 800, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0287] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0288] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0289] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions that can be executed by a processor 820 of an electronic device 800 to perform the above-described method.

[0290] Figure 4 This is a block diagram illustrating an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. (Refer to...) Figure 4 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0291] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output (I / O) interface 1958. Electronic device 1900 can operate on an operating system stored in memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0292] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of an electronic device 1900 to perform the above-described method.

[0293] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0294] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0295] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0296] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0297] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0298] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0299] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0300] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0301] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A lung image registration method characterized by, The method comprises the following steps: acquiring a plurality of left lung images at multiple time points in a breathing process; wherein the plurality of left lung images are configured as two-dimensional DR images; before acquiring the plurality of left lung images at multiple time points in the breathing process, determining first set position information corresponding to the two-dimensional DR left lung images at multiple time points in the breathing process, comprising: detecting a plurality of first highest point position information, a plurality of first lowest point position information, a plurality of first leftmost position information and a plurality of first rightmost position information corresponding to the two-dimensional DR left lung images at multiple time points in the breathing process respectively; determining the first set position information corresponding to the two-dimensional DR left lung images at multiple time points in the breathing process based on the plurality of first highest point position information, the plurality of first lowest point position information, the plurality of first leftmost position information and the plurality of first rightmost position information; based on the two-dimensional DR left lung images at multiple time points in the breathing process and the corresponding first set position information, the two-dimensional DR left lung images at multiple time points are cropped to obtain corresponding multiple left lung images; aligning the left lung images at adjacent time points in the multiple left lung images respectively to obtain a plurality of first aligned images; determining a first fixed image in the multiple left lung images; aligning any one of the first aligned images other than the first aligned image corresponding to the first fixed image to the first fixed image.

2. The lung image registration method of claim 1, wherein, Further comprising: acquiring a plurality of right lung images at multiple time points in a breathing process; wherein the plurality of right lung images are configured as two-dimensional DR images; aligning the right lung images at adjacent time points in the multiple right lung images respectively to obtain a plurality of second aligned images; determining a second fixed image in the multiple right lung images; aligning any one of the second aligned images other than the second aligned image corresponding to the second fixed image to the second fixed image.

3. The lung image registration method of claim 2, wherein, Before acquiring the plurality of right lung images at multiple time points in the breathing process, comprising: acquiring two-dimensional DR right lung images at multiple time points in the breathing process and corresponding second set position information; based on the second set position information, the two-dimensional DR right lung images at multiple time points are cropped to obtain corresponding multiple right lung images.

4. The lung image registration method of claim 1, wherein, The method comprises the following steps: acquiring a plurality of first mask images corresponding to the two-dimensional DR left lung images at multiple time points in the breathing process; determining a plurality of left lung edge images corresponding to the two-dimensional DR left lung images at multiple time points in the breathing process based on the plurality of first mask images respectively; detecting a plurality of first highest point position information, a plurality of first lowest point position information, a plurality of first leftmost position information and a plurality of first rightmost position information corresponding to the two-dimensional DR left lung images at multiple time points in the breathing process based on the plurality of left lung edge images respectively.

5. The lung image registration method of any one of claims 1 or 4, wherein, The first set position information corresponding to the two-dimensional DR left lung image at multiple moments in the breathing process is determined based on the plurality of first highest point position information, the plurality of first lowest point position information, the plurality of first leftmost position information and the plurality of first rightmost position information, including: Respectively extracting a plurality of first highest point vertical coordinates and a plurality of first lowest point vertical coordinates in the plurality of first highest point position information and the plurality of first lowest point position information; Determining a first vertical coordinate maximum value corresponding to the plurality of first highest point vertical coordinates, and determining a first vertical coordinate minimum value corresponding to the plurality of first lowest point vertical coordinates; Respectively extracting a plurality of first leftmost horizontal coordinates and a plurality of first rightmost horizontal coordinates in the plurality of first leftmost position information and the plurality of first rightmost position information; Determining a first horizontal coordinate minimum value corresponding to the plurality of first leftmost horizontal coordinates, and determining a first horizontal coordinate maximum value corresponding to the plurality of first rightmost horizontal coordinates; Determining the first set position information corresponding to the two-dimensional DR left lung image at multiple moments in the breathing process according to the first vertical coordinate maximum value, the first vertical coordinate minimum value, the first horizontal coordinate minimum value and the first horizontal coordinate maximum value.

6. The lung image registration method of claim 5, wherein, The first set position information corresponding to the two-dimensional DR left lung image at multiple moments in the breathing process is determined according to the first vertical coordinate maximum value, the first vertical coordinate minimum value, the first horizontal coordinate minimum value and the first horizontal coordinate maximum value, including: Respectively making two corresponding first y-axis perpendicular lines to the y-axis with the first vertical coordinate maximum value and the first vertical coordinate minimum value, and respectively making two corresponding first x-axis perpendicular lines to the x-axis with the first horizontal coordinate minimum value and the first horizontal coordinate maximum value; The intersection of the first y-axis perpendicular line and the first x-axis perpendicular line is configured as the first set position information corresponding to the two-dimensional DR left lung image at multiple moments in the breathing process.

7. The lung image registration method of claim 3, wherein, Determining the second set position information corresponding to the two-dimensional DR right lung image at multiple moments in the breathing process, including: Respectively detecting a plurality of second highest point position information, a plurality of second lowest point position information, a plurality of second rightmost position information and a plurality of second rightmost position information corresponding to the two-dimensional DR right lung image at multiple moments in the breathing process; Determining the second set position information corresponding to the two-dimensional DR right lung image at multiple moments in the breathing process based on the plurality of second highest point position information, the plurality of second lowest point position information, the plurality of second rightmost position information and the plurality of second rightmost position information.

8. The lung image registration method of claim 7, wherein, The plurality of second highest point position information, the plurality of second lowest point position information, the plurality of second rightmost position information and the plurality of second rightmost position information corresponding to the two-dimensional DR right lung image at multiple moments in the breathing process are respectively detected, including: Obtaining a plurality of second mask images corresponding to the two-dimensional DR right lung image at multiple moments in the breathing process; Respectively determining a plurality of right lung edge images based on the plurality of second mask images; Respectively determining a plurality of second highest point position information, a plurality of second lowest point position information, a plurality of second rightmost position information and a plurality of second rightmost position information corresponding to the two-dimensional DR right lung image at multiple moments in the breathing process; Detecting, based on the multiple right lung edge images respectively, multiple second highest point position information, multiple second lowest point position information, multiple second rightmost position information and multiple second rightmost position information corresponding to the two-dimensional DR right lung images at multiple moments in the breathing process.

9. The lung image registration method of any one of claims 7 or 8, wherein, The determining of the second set position information corresponding to the two-dimensional DR right lung images at multiple moments in the breathing process based on the multiple second highest point position information, the multiple second lowest point position information, the multiple second rightmost position information and the multiple second rightmost position information comprises: Respectively extracting multiple second highest point longitudinal coordinates and multiple second lowest point longitudinal coordinates in the multiple second highest point position information and the multiple second lowest point position information; Determining a second longitudinal coordinate maximum value corresponding to the multiple second highest point longitudinal coordinates and a second longitudinal coordinate minimum value corresponding to the multiple second lowest point longitudinal coordinates; Respectively extracting multiple second rightmost lateral coordinates and multiple second rightmost lateral coordinates in the multiple second rightmost position information and the multiple second rightmost position information; Determining a second lateral coordinate minimum value corresponding to the multiple second rightmost lateral coordinates and a second lateral coordinate maximum value corresponding to the multiple second rightmost lateral coordinates; Determining the second set position information corresponding to the two-dimensional DR right lung images at multiple moments in the breathing process according to the second longitudinal coordinate maximum value, the second longitudinal coordinate minimum value, the second lateral coordinate minimum value and the second lateral coordinate maximum value.

10. The lung image registration method of claim 9, wherein, The determining of the second set position information corresponding to the two-dimensional DR right lung images at multiple moments in the breathing process according to the second longitudinal coordinate maximum value, the second longitudinal coordinate minimum value, the second lateral coordinate minimum value and the second lateral coordinate maximum value comprises: Respectively drawing two corresponding second y-axis perpendicular lines to the y-axis with the second longitudinal coordinate maximum value and the second longitudinal coordinate minimum value, and respectively drawing two corresponding second x-axis perpendicular lines to the x-axis with the second lateral coordinate minimum value and the second lateral coordinate maximum value; Arranging the intersection of the second y-axis perpendicular line and the second x-axis perpendicular line as the second set position information corresponding to the two-dimensional DR right lung images at multiple moments in the breathing process.

11. The lung image registration method of any of claims 1-4, 6-8, 10, wherein, Before the acquiring of the multiple left lung images at multiple moments in the breathing process, determining one or both of the two-dimensional DR left lung images at multiple moments in the breathing process and the two-dimensional DR right lung images at multiple moments in the breathing process comprises: Respectively performing rib edge boundary, lung apex boundary and mediastinum and transverse septum edge detection on one or both of the left chest images and the right chest images of the two-dimensional DR lung images at multiple moments in the breathing process to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments in the breathing process; or, Respectively performing rib edge boundary, lung apex boundary and mediastinum and transverse septum edge detection on one or both of the left chest images and the right chest images of the two-dimensional DR lung images at multiple moments in the breathing process to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments in the breathing process; or, acquire a segmentation model of a preset convolutional neural network and a DR lung region label image used for training the segmentation model; train the segmentation model by using the DR lung region label image used for training the segmentation model; and complete left lung and right lung segmentation of the two-dimensional DR lung images at multiple moments in the breathing process based on the trained segmentation model, to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments.

12. The lung image registration method of claim 5, wherein, Before the acquiring of the multiple left lung images at multiple moments in the breathing process, determining one or both of the two-dimensional DR left lung images at multiple moments in the breathing process and the two-dimensional DR right lung images at multiple moments in the breathing process comprises: respectively performing rib edge boundary, lung apex boundary, and mediastinum and diaphragm edge detection on one or both of the left chest images and the right chest images of the two-dimensional DR lung images at multiple moments in the breathing process, to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments; or acquire a segmentation model of a preset convolutional neural network and a DR lung region label image used for training the segmentation model; train the segmentation model by using the DR lung region label image used for training the segmentation model; and complete left lung and right lung segmentation of the two-dimensional DR lung images at multiple moments in the breathing process based on the trained segmentation model, to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments.

13. The lung image registration method of claim 9, wherein, Before the acquiring of the multiple left lung images at multiple moments in the breathing process, determining one or both of the two-dimensional DR left lung images at multiple moments in the breathing process and the two-dimensional DR right lung images at multiple moments in the breathing process comprises: respectively performing rib edge boundary, lung apex boundary, and mediastinum and diaphragm edge detection on one or both of the left chest images and the right chest images of the two-dimensional DR lung images at multiple moments in the breathing process, to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments; or acquire a segmentation model of a preset convolutional neural network and a DR lung region label image used for training the segmentation model; train the segmentation model by using the DR lung region label image used for training the segmentation model; and complete left lung and right lung segmentation of the two-dimensional DR lung images at multiple moments in the breathing process based on the trained segmentation model, to obtain one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple moments.

14. The lung image registration method of any of claims 1-4, 6-8, 10, 12, 13, wherein, The respectively registering the left lung images at adjacent moments in the multiple left lung images comprises: acquiring a first registration model and a corresponding first setting rule; respectively registering the left lung images at adjacent moments in the multiple left lung images by using the first registration model; respectively ending the registration of the left lung images at adjacent moments in the multiple left lung images by using the first setting rule.

15. The lung image registration method of claim 5, wherein, The respectively registering the left lung images at adjacent moments in the multiple left lung images comprises: acquiring a first registration model and a corresponding first setting rule; Respectively, using the first registration model, the left lung images of adjacent time in the plurality of left lung images are registered; Respectively, using the first registration model, the left lung images of adjacent time in the plurality of left lung images are registered; 16. The lung image registration method of claim 9, wherein, Respectively, using the first registration model, the left lung images of adjacent time in the plurality of left lung images are registered; Respectively, using the first registration model, the left lung images of adjacent time in the plurality of left lung images are registered; Respectively, using the first registration model, the left lung images of adjacent time in the plurality of left lung images are registered; Respectively, using the first registration model, the left lung images of adjacent time in the plurality of left lung images are registered; 17. The lung image registration method of claim 11, wherein, The first parameter map of the first registration model is configured as affine. The first parameter map of the first registration model is configured as affine. On the basis of the first parameter map of the first registration model being configured as affine, one or more of translation, rigid, and B-spline is additionally configured in the first parameter map; or, On the basis of the first parameter map of the first registration model being configured as one or more of translation, rigid, and B-spline, affine is additionally configured in the first parameter map.

18. The lung image registration method of claim 14, wherein, On the basis of the first parameter map of the first registration model being configured as affine, one or more of translation, rigid, and B-spline is additionally configured in the first parameter map; or, 19. The lung image registration method of any of claims 15-17, wherein, On the basis of the first parameter map of the first registration model being configured as one or more of translation, rigid, and B-spline, affine is additionally configured in the first parameter map.

20. The lung image registration method of claim 14, wherein, On the basis of the first parameter map of the first registration model being configured as affine, one or more of translation, rigid, and B-spline is additionally configured in the first parameter map; or, On the basis of the first parameter map of the first registration model being configured as one or more of translation, rigid, and B-spline, affine is additionally configured in the first parameter map.

21. The lung image registration method of any of claims 15-18, wherein, The first setting rule is configured as one or both of a first preset registration number and a first preset similarity; The first setting rule is configured as one or both of a first preset registration number and a first preset similarity; 22. The lung image registration method of claim 19, wherein, ​ ​ 23. The lung image registration method of claim 14, wherein, ​ When the first setting rule is configured as the first preset registration times, if the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are greater than or equal to the first preset registration times, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; When the first setting rule is configured as the first preset similarity, the similarity of the left lung images of adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the first preset similarity, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; When the first setting rule is configured as the first preset registration times and the first preset similarity, when the first setting rule is configured as the first preset registration times, if the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are greater than or equal to the first preset registration times, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; If the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are greater than or equal to the first preset registration times, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; If the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are less than the first preset registration times, the similarity of the left lung images of adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the first preset similarity, registration of the left lung images of adjacent time points in the plurality of left lung images is ended.

24. The lung image registration method of any of claims 15-18, 20, wherein, The first setting rule is configured as one or both of the first preset registration times and the first preset similarity; When the first setting rule is configured as the first preset registration times, if the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are greater than or equal to the first preset registration times, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; When the first setting rule is configured as the first preset similarity, the similarity of the left lung images of adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the first preset similarity, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; When the first setting rule is configured as the first preset registration times and the first preset similarity, when the first setting rule is configured as the first preset registration times, if the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are greater than or equal to the first preset registration times, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; If the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are greater than or equal to the first preset registration times, registration of the left lung images of adjacent time points in the plurality of left lung images is ended; If the first times of registration of the left lung images of adjacent time points in the plurality of left lung images are less than the first preset registration times, the similarity of the left lung images of adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the first preset similarity, registration of the left lung images of adjacent time points in the plurality of left lung images is ended. If the similarity is greater than or equal to the first preset similarity, registration of the left lung images at adjacent time points in the plurality of left lung images is ended.

25. The lung image registration method of claim 19, wherein, The first setting rule is configured as one or both of a first preset registration number and a first preset similarity; When the first setting rule is configured as the first preset registration number, if the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is greater than or equal to the first preset registration number, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. When the first setting rule is configured as the first preset similarity, the similarity of the left lung images at adjacent time points in the registration process at this time is calculated. If the similarity is greater than or equal to the first preset similarity, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. When the first setting rule is configured as the first preset registration number, if the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is greater than or equal to the first preset registration number, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. If the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is greater than or equal to the first preset registration number, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. If the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is less than the first preset registration number, the similarity of the left lung images at adjacent time points in the registration process at this time is calculated. If the similarity is greater than or equal to the first preset similarity, registration of the left lung images at adjacent time points in the plurality of left lung images is ended.

26. The lung image registration method of claim 21, wherein, The first setting rule is configured as one or both of a first preset registration number and a first preset similarity; When the first setting rule is configured as the first preset registration number, if the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is greater than or equal to the first preset registration number, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. When the first setting rule is configured as the first preset similarity, the similarity of the left lung images at adjacent time points in the registration process at this time is calculated. If the similarity is greater than or equal to the first preset similarity, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. When the first setting rule is configured as the first preset registration number, if the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is greater than or equal to the first preset registration number, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. If the first number of registration of the left lung images at adjacent time points in the plurality of left lung images is greater than or equal to the first preset registration number, registration of the left lung images at adjacent time points in the plurality of left lung images is ended. If the first number of times of registration of the left lung images of adjacent time points in the plurality of left lung images is less than the first preset number of times of registration, a similarity of the left lung images of adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the first preset similarity, the registration of the left lung images of adjacent time points in the plurality of left lung images is ended.

27. The lung image registration method of claim 14, wherein, The registration of the left lung images of adjacent time points in the plurality of left lung images respectively by using the first registration model comprises: The left lung image of a previous time point in the left lung images of adjacent time points is configured as a first fixed left lung image; The left lung images corresponding to the previous time point and a next time point in the adjacent time points are configured as first floating left lung images; The first floating left lung images are respectively registered to the first fixed left lung image by using the first registration model.

28. The lung image registration method of any of claims 15-18, 20, 22, 23, 25, 26, wherein, The registration of the left lung images of adjacent time points in the plurality of left lung images respectively by using the first registration model comprises: The left lung image of a previous time point in the left lung images of adjacent time points is configured as a first fixed left lung image; The left lung images corresponding to the previous time point and a next time point in the adjacent time points are configured as first floating left lung images; The first floating left lung images are respectively registered to the first fixed left lung image by using the first registration model.

29. The lung image registration method of claim 19, wherein, The registration of the left lung images of adjacent time points in the plurality of left lung images respectively by using the first registration model comprises: The left lung image of a previous time point in the left lung images of adjacent time points is configured as a first fixed left lung image; The left lung images corresponding to the previous time point and a next time point in the adjacent time points are configured as first floating left lung images; The first floating left lung images are respectively registered to the first fixed left lung image by using the first registration model.

30. The lung image registration method of claim 21, wherein, The registration of the left lung images of adjacent time points in the plurality of left lung images respectively by using the first registration model comprises: The left lung image of a previous time point in the left lung images of adjacent time points is configured as a first fixed left lung image; The left lung images corresponding to the previous time point and a next time point in the adjacent time points are configured as first floating left lung images; The first floating left lung images are respectively registered to the first fixed left lung image by using the first registration model.

31. The lung image registration method of claim 24, wherein, The registration of the left lung images of adjacent time points in the plurality of left lung images respectively by using the first registration model comprises: The left lung image of a previous time point in the left lung images of adjacent time points is configured as a first fixed left lung image; The left lung images corresponding to the previous time point and a next time point in the adjacent time points are configured as first floating left lung images; The first floating left lung images are respectively registered to the first fixed left lung image by using the first registration model.

32. The lung image registration method of any one of claims 23, 25, 26, wherein, The calculation of the similarity of the left lung images of adjacent time points in the registration process comprises: The first fixed left lung image and the first floating left lung image in the registration process are respectively subjected to an erosion operation according to a set erosion pixel value, to obtain a corresponding first fixed left lung erosion image and a first floating left lung erosion image; Based on the first fixed left lung image and the first fixed eroded left lung image, a corresponding first fixed left lung boundary image is obtained; Based on the first floating left lung image and the first floating left lung eroded image, a corresponding first floating left lung boundary image is obtained; The similarity of the first fixed left lung boundary image and the first floating left lung boundary image is calculated to obtain the similarity of the left lung images at adjacent time points in the registration process.

33. The lung image registration method of claim 24, wherein, The calculation of the similarity of the left lung images at adjacent time points in the registration process includes: According to the set eroded pixel value, the first fixed left lung image and the first floating left lung image in the registration process are respectively eroded to obtain the corresponding first fixed left lung eroded image and the first floating left lung eroded image; Based on the first fixed left lung image and the first fixed eroded left lung image, a corresponding first fixed left lung boundary image is obtained; Based on the first floating left lung image and the first floating left lung eroded image, a corresponding first floating left lung boundary image is obtained; The similarity of the first fixed left lung boundary image and the first floating left lung boundary image is calculated to obtain the similarity of the left lung images at adjacent time points in the registration process.

34. The lung image registration method of any one of claims 2, 3, 7, 8, 10, wherein, The multiple second registration images corresponding to the multiple right lung images at adjacent time points are obtained by registering the multiple right lung images at adjacent time points, including: A second registration model and its corresponding second set rule are obtained; The multiple right lung images at adjacent time points are respectively registered by using the second registration model; The registration of the multiple right lung images at adjacent time points is ended by using the second set rule respectively.

35. The lung image registration method of claim 9, wherein, The multiple second registration images corresponding to the multiple right lung images at adjacent time points are obtained by registering the multiple right lung images at adjacent time points, including: A second registration model and its corresponding second set rule are obtained; The multiple right lung images at adjacent time points are respectively registered by using the second registration model; The registration of the multiple right lung images at adjacent time points is ended by using the second set rule respectively.

36. The lung image registration method of claim 34, wherein, The second parameter map of the second registration model is configured as affine transformation.

37. The lung image registration method of claim 35, wherein, The second parameter map of the second registration model is configured as affine transformation.

38. The lung image registration method of claim 34, wherein, On the basis of the second parameter map of the second registration model being configured as affine transformation, one or more of translation transformation, rigid transformation, and B-spline is additionally configured in the second parameter map; or, On the basis of the second parameter map of the second registration model being configured as one or more of translation transformation, rigid transformation, and B-spline, affine transformation is additionally configured in the second parameter map.

39. The lung image registration method of any of claims 35-37, wherein, On the basis of the second parameter map of the second registration model being configured as affine transformation, one or more of translation transformation, rigid transformation, and B-spline is additionally configured in the second parameter map; or, On the basis that the second parameter map of the second registration model is configured as one or more of translation, rigid, bspline, the second parameter map is additionally configured with affine.

40. The lung image registration method of claim 34, wherein, The second setting rule is configured as one or both of a second preset registration number and a second preset similarity; When the second setting rule is configured as the second preset registration number, if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is greater than or equal to the second preset registration number, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; When the second setting rule is configured as the second preset similarity, the similarity of the right lung images at adjacent time points in the registration process at this time is calculated; If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; When the second setting rule is configured as the second preset registration number and the second preset similarity, when the second setting rule is configured as the second preset registration number, if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is greater than or equal to the second preset registration number, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is greater than or equal to the second preset registration number, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is less than the second preset registration number, the similarity of the right lung images at adjacent time points in the registration process at this time is calculated; If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended.

41. The lung image registration method of any of claims 35-38, wherein, The second setting rule is configured as one or both of a second preset registration number and a second preset similarity; When the second setting rule is configured as the second preset registration number, if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is greater than or equal to the second preset registration number, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; When the second setting rule is configured as the second preset similarity, the similarity of the right lung images at adjacent time points in the registration process at this time is calculated; If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; When the second setting rule is configured as the second preset registration number and the second preset similarity, when the second setting rule is configured as the second preset registration number, if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is greater than or equal to the second preset registration number, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is greater than or equal to the second preset registration number, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registration of the right lung images at adjacent time points in the plurality of right lung images is less than the second preset registration number, the similarity of the right lung images at adjacent time points in the registration process at this time is calculated; If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended. When the second preset registration frequency and the second preset similarity are configured, if the second number of registrations of the right lung images at adjacent time points is greater than or equal to the second preset registration frequency, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registrations of the right lung images at adjacent time points is greater than or equal to the second preset registration frequency, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registrations of the right lung images at adjacent time points is less than the second preset registration frequency, the similarity of the right lung images at adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended.

42. The lung image registration method of claim 39, wherein, The second preset registration frequency and the second preset similarity are configured. When the second preset registration frequency is configured, if the second number of registrations of the right lung images at adjacent time points is greater than or equal to the second preset registration frequency, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended. When the second preset similarity is configured, the similarity of the right lung images at adjacent time points in the registration process is calculated. If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended. When the second preset registration frequency and the second preset similarity are configured, if the second number of registrations of the right lung images at adjacent time points is greater than or equal to the second preset registration frequency, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registrations of the right lung images at adjacent time points is greater than or equal to the second preset registration frequency, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended; if the second number of registrations of the right lung images at adjacent time points is less than the second preset registration frequency, the similarity of the right lung images at adjacent time points in the registration process is calculated; If the similarity is greater than or equal to the second preset similarity, the registration of the right lung images at adjacent time points in the plurality of right lung images is ended.

43. The lung image registration method of claim 34, wherein, The registration of the right lung images at adjacent time points in the plurality of right lung images by using the second registration model comprises: The right lung image at the previous time point in the right lung images at adjacent time points is configured as a second fixed right lung image; The right lung images at the previous time point and the next time point in the right lung images at adjacent time points are configured as second floating right lung images; The second floating right lung images are registered to the second fixed right lung image by using the second registration model.

44. The lung image registration method of any of claims 35-38, 40, 42, wherein, The second registration model is used to register the right lung images of adjacent time points in the plurality of right lung images respectively, including: The right lung image of the previous time point in the right lung images of the adjacent time points is configured as a second fixed right lung image; The right lung images corresponding to the previous time point and the next time point in the adjacent time points are configured as second floating right lung images; The second floating right lung images are respectively registered to the second fixed right lung image by using the second registration model.

45. The lung image registration method of claim 39, wherein, The second registration model is used to register the right lung images of adjacent time points in the plurality of right lung images respectively, including: The right lung image of the previous time point in the right lung images of the adjacent time points is configured as a second fixed right lung image; The right lung images corresponding to the previous time point and the next time point in the adjacent time points are configured as second floating right lung images; The second floating right lung images are respectively registered to the second fixed right lung image by using the second registration model.

46. The lung image registration method of claim 41, wherein, The second registration model is used to register the right lung images of adjacent time points in the plurality of right lung images respectively, including: The right lung image of the previous time point in the right lung images of the adjacent time points is configured as a second fixed right lung image; The right lung images corresponding to the previous time point and the next time point in the adjacent time points are configured as second floating right lung images; The second floating right lung images are respectively registered to the second fixed right lung image by using the second registration model.

47. The lung image registration method of any of claims 40 or 42, wherein, The similarity of the right lung images of adjacent time points in the registration process at this time is calculated, including: According to a set of erosion pixel values, the second fixed right lung image and the second floating right lung image in the registration process are respectively subjected to erosion operation to obtain corresponding second fixed right lung erosion images and second floating right lung erosion images; Based on the second fixed right lung image and the second fixed right lung erosion image, a corresponding second fixed right lung boundary image is obtained; Based on the second floating right lung image and the second floating right lung erosion image, a corresponding second floating right lung boundary image is obtained; The similarity of the second fixed right lung boundary image and the second floating right lung boundary image is calculated to obtain the similarity of the right lung images of adjacent time points in the registration process.

48. The lung image registration method of claim 41, wherein, The similarity of the right lung images of adjacent time points in the registration process at this time is calculated, including: According to a set of erosion pixel values, the second fixed right lung image and the second floating right lung image in the registration process are respectively subjected to erosion operation to obtain corresponding second fixed right lung erosion images and second floating right lung erosion images; Based on the second fixed right lung image and the second fixed right lung erosion image, a corresponding second fixed right lung boundary image is obtained; Based on the second floating right lung image and the second floating right lung erosion image, a corresponding second floating right lung boundary image is obtained; The similarity of the second fixed right lung boundary image and the second floating right lung boundary image is calculated to obtain the similarity of the right lung images of adjacent time points in the registration process.

49. A lung image registration apparatus, characterized by, It includes: The acquisition unit is configured to acquire a plurality of left lung images at multiple moments in a breathing process; wherein the plurality of left lung images are configured as two-dimensional DR images; before the acquisition of the plurality of left lung images at multiple moments in the breathing process, the first set position information corresponding to the two-dimensional DR left lung images at multiple moments in the breathing process is determined, including: detecting a plurality of first highest point position information, a plurality of first lowest point position information, a plurality of first leftmost position information and a plurality of first rightmost position information corresponding to the two-dimensional DR left lung images at multiple moments in the breathing process respectively; determining the first set position information corresponding to the two-dimensional DR left lung images at multiple moments in the breathing process based on the plurality of first highest point position information, the plurality of first lowest point position information, the plurality of first leftmost position information and the plurality of first rightmost position information; based on the two-dimensional DR left lung images at multiple moments in the breathing process and the corresponding first set position information, the plurality of two-dimensional DR left lung images at multiple moments are cropped to obtain a plurality of corresponding left lung images; The first registration unit is configured to register the left lung images at adjacent moments in the plurality of left lung images respectively to obtain a plurality of first registration images corresponding thereto; The first determination unit is configured to determine a first fixed image in the plurality of left lung images; The second registration unit is configured to register any one of the first registration images other than the first fixed image to the first fixed image.

50. The lung image registration device of claim 49, wherein: The acquisition unit is further configured to acquire a plurality of right lung images at multiple moments in a breathing process; wherein the plurality of right lung images are configured as two-dimensional DR images; The first registration unit is further configured to register the right lung images at adjacent moments in the plurality of right lung images respectively to obtain a plurality of second registration images corresponding thereto; The first determination unit is further configured to determine a second fixed image in the plurality of right lung images; The second registration unit is further configured to register any one of the second registration images other than the second fixed image corresponding to the second fixed image to the second fixed image.

51. A method of lesion localization comprising registering using the lung image registration method of any one of claims 1-48 or applying the lung image registration apparatus of any one of claims 49 or 50, wherein, The first registration image with the largest left lung area in the plurality of left lung images and the second registration image with the largest right lung area in the plurality of right lung images are determined as the first fixed image and the second fixed image respectively; The first registration image with the smallest left lung area in the plurality of left lung images and the second registration image with the smallest right lung area in the plurality of right lung images are determined as the first floating image and the second floating image respectively; The first floating image and the second floating image are registered with the first fixed image and the second fixed image respectively to obtain a left lung registration image and a right lung registration image; The left lung air retention lesion position is located based on the first fixed image and the left lung registration image; and the right lung air retention lesion position is located based on the second fixed image and the right lung registration image.

52. The lesion positioning method of claim 51, wherein, The left lung air retention lesion position located based on the first fixed image and the left lung registration image includes: Based on the acquired set air threshold interval, the left lung air area corresponding to the first fixed image and the left lung registration image is determined respectively; calculating a first difference value corresponding to a same position in a left lung air region of the first fixed image and the left lung registration image; configuring a position corresponding to the first difference value being less than or equal to a first preset difference value threshold as a left lung air retention lesion position.

53. The lesion localization method according to any one of claims 51 or 52, wherein, The positioning of the right lung air retention lesion position based on the second fixed image and the right lung registration image comprises: determining a right lung air region corresponding to the second fixed image and the right lung registration image based on a set air threshold interval; calculating a second difference value corresponding to a same position in a right lung air region of the second fixed image and the right lung registration image; configuring a position corresponding to the second difference value being less than or equal to a second preset difference value threshold as a right lung air retention lesion position.

54. The lesion positioning method according to any one of claims 51 or 52, wherein, Before the positioning of the left lung air retention lesion position based on the first fixed image and the left lung registration image, comprising: respectively removing a boundary of the first fixed image and the left lung registration image based on a first set boundary distance to obtain a corresponding first fixed processing image and left lung registration processing image; positioning the left lung air retention lesion position based on the first fixed processing image and the left lung registration processing image.

55. The lesion positioning method of claim 53, wherein, Before the positioning of the left lung air retention lesion position based on the first fixed image and the left lung registration image, comprising: respectively removing a boundary of the first fixed image and the left lung registration image based on a first set boundary distance to obtain a corresponding first fixed processing image and left lung registration processing image; positioning the left lung air retention lesion position based on the first fixed processing image and the left lung registration processing image.

56. The lesion positioning method of claim 54, wherein, The positioning of the left lung air retention lesion position based on the first fixed processing image and the left lung registration processing image comprises: determining a left lung air region corresponding to the first fixed processing image and the left lung registration processing image based on a set air threshold interval; calculating a third difference value corresponding to the left lung air region of the first fixed processing image and the left lung registration processing image; configuring a position corresponding to the third difference value being less than or equal to a third preset difference value threshold as a left lung air retention lesion position.

57. The lesion positioning method of claim 55, wherein, The positioning of the left lung air retention lesion position based on the first fixed processing image and the left lung registration processing image comprises: determining a left lung air region corresponding to the first fixed processing image and the left lung registration processing image based on a set air threshold interval; calculating a third difference value corresponding to the left lung air region of the first fixed processing image and the left lung registration processing image; configuring a position corresponding to the third difference value being less than or equal to a third preset difference value threshold as a left lung air retention lesion position.

58. The lesion positioning method according to any one of claims 51, 52, 55-57, wherein, Before the positioning of the right lung air retention lesion position based on the second fixed image and the right lung registration image, comprising: respectively removing a boundary of the second fixed image and the right lung registration image based on a second set boundary distance to obtain a corresponding second fixed processing image and right lung registration processing image; Positioning a right lung air retention lesion based on the second fixed processing image and the right lung registration processing image.

59. The lesion positioning method of claim 53, wherein, Before the positioning of the right lung air retention lesion based on the second fixed image and the right lung registration image, comprising: Respectively removing the boundaries of the second fixed image and the right lung registration image based on the obtained second set boundary distance, to obtain the corresponding second fixed processing image and right lung registration processing image; Positioning a right lung air retention lesion based on the second fixed processing image and the right lung registration processing image.

60. The lesion positioning method of claim 54, wherein, Before the positioning of the right lung air retention lesion based on the second fixed image and the right lung registration image, comprising: Respectively removing the boundaries of the second fixed image and the right lung registration image based on the obtained second set boundary distance, to obtain the corresponding second fixed processing image and right lung registration processing image; Positioning a right lung air retention lesion based on the second fixed processing image and the right lung registration processing image.

61. The lesion positioning method of claim 58, wherein, The positioning of the right lung air retention lesion based on the second fixed processing image and the right lung registration processing image, comprising: Based on the obtained set air threshold interval, respectively determining the corresponding right lung air region of the second fixed processing image and the right lung registration processing image; Calculating the fourth difference value corresponding to the right lung air region corresponding to the second fixed processing image and the right lung registration processing image; The position corresponding to the fourth difference value less than or equal to the obtained fourth preset difference threshold value is configured as the right lung air retention lesion position.

62. The lesion localization method according to any one of claims 59 or 60, wherein, The positioning of the right lung air retention lesion based on the second fixed processing image and the right lung registration processing image, comprising: Based on the obtained set air threshold interval, respectively determining the corresponding right lung air region of the second fixed processing image and the right lung registration processing image; Calculating the fourth difference value corresponding to the right lung air region corresponding to the second fixed processing image and the right lung registration processing image; The position corresponding to the fourth difference value less than or equal to the obtained fourth preset difference threshold value is configured as the right lung air retention lesion position.

63. The lesion positioning method according to any one of claims 51, 52, 55-57, 59-61, wherein, Before the obtaining of one or both lung images of the plurality of left lung images and the plurality of right lung images in the plurality of time instants in the breathing process, comprising: Respectively rib bone eliminating one or both lung images of the two-dimensional DR left lung image and the two-dimensional DR right lung image in the plurality of time instants in the breathing process, to obtain one or both lung images of the plurality of left lung images and the plurality of right lung images in the plurality of time instants in the breathing process.

64. The lesion positioning method of claim 53, wherein, Before the obtaining of one or both lung images of the plurality of left lung images and the plurality of right lung images in the plurality of time instants in the breathing process, comprising: Respectively rib bone eliminating one or both lung images of the two-dimensional DR left lung image and the two-dimensional DR right lung image in the plurality of time instants in the breathing process, to obtain one or both lung images of the plurality of left lung images and the plurality of right lung images in the plurality of time instants in the breathing process.

65. The lesion positioning method of claim 54, wherein, Before the obtaining of one or both lung images of the plurality of left lung images and the plurality of right lung images in the plurality of time instants in the breathing process, comprising: Rib bones in one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple time points in the breathing process are removed respectively to obtain one or both of the multiple left lung images and the multiple right lung images at multiple time points in the breathing process.

66. The lesion positioning method of claim 58, wherein, Before the acquiring of the one or both of the multiple left lung images and the multiple right lung images at multiple time points in the breathing process, the method comprises: Rib bones in one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple time points in the breathing process are removed respectively to obtain one or both of the multiple left lung images and the multiple right lung images at multiple time points in the breathing process.

67. The lesion positioning method of claim 62, wherein, Before the acquiring of the one or both of the multiple left lung images and the multiple right lung images at multiple time points in the breathing process, the method comprises: Rib bones in one or both of the two-dimensional DR left lung images and the two-dimensional DR right lung images at multiple time points in the breathing process are removed respectively to obtain one or both of the multiple left lung images and the multiple right lung images at multiple time points in the breathing process.

68. A lesion localization device, comprising: The method comprises: The registration model, the first lesion positioning unit and the second lesion positioning unit are applied to registration by using the lung image registration method according to any one of claims 1-48; wherein the registration model is configured to determine a first registration image with the largest left lung area in the multiple left lung images and a second registration image with the largest right lung area in the multiple right lung images as a first fixed image and a second fixed image respectively; The registration model is further configured to determine a first registration image with the smallest left lung area in the multiple left lung images and a second registration image with the smallest right lung area in the multiple right lung images as a first floating image and a second floating image respectively; The registration model is further configured to register the first floating image with the first fixed image and the second floating image with the second fixed image respectively to obtain a left lung registration image and a right lung registration image; The first lesion positioning unit is configured to position a left lung air retention lesion based on the first fixed image and the left lung registration image; The second lesion positioning unit is configured to position a right lung air retention lesion based on the second fixed image and the right lung registration image.

69. A lesion localization device, comprising: The method comprises: The lung image registration device, the second determination unit, the first lesion positioning unit and the second lesion positioning unit are according to any one of claims 49 or 50; The first determination unit of the lung image registration device is configured to determine a first registration image with the largest left lung area in the multiple left lung images and a second registration image with the largest right lung area in the multiple right lung images as a first fixed image and a second fixed image respectively; The second determination unit is configured to determine a first registration image with the smallest left lung area in the multiple left lung images and a second registration image with the smallest right lung area in the multiple right lung images as a first floating image and a second floating image respectively; The second registration unit of the lung image registration device is configured to register the first floating image with the first fixed image and the second floating image with the second fixed image respectively to obtain a left lung registration image and a right lung registration image; The first lesion positioning unit is configured to position a left lung air retention lesion based on the first fixed image and the left lung registered image. The second lesion positioning unit is configured to position a right lung air retention lesion based on the second fixed image and the right lung registered image.

70. An electronic device, comprising: The computer program product comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the lung image registration method according to any one of claims 1-48.

71. An electronic device, comprising: The computer program product comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the lesion positioning method according to any one of claims 51-67.

72. A computer-readable storage medium having stored thereon computer program instructions, wherein, The computer program instructions, when executed by the processor, implement the lung image registration method according to any one of claims 1-48.

73. A computer-readable storage medium having stored thereon computer program instructions, wherein, The computer program instructions, when executed by the processor, implement the lesion positioning method according to any one of claims 51-67.

Images