Dynamic x-ray image processing method, system and dynamic x-ray camera

Abstract

The present disclosure relates to a dynamic X-ray image processing method, a system and a dynamic X-ray machine, and relates to the technical field of dynamic X-ray image processing. The dynamic X-ray image processing method comprises: acquiring a plurality of first heart margin distances of a lung airflow and blood flow mixed image sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images in a breathing process, and a plurality of second heart margin distances of a lung blood flow image sequence corresponding to a plurality of X-ray two-dimensional chest images at multiple moments in a breath holding state; and matching the plurality of first heart margin distances and the plurality of second heart margin distances to determine a corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence. The embodiment of the present disclosure can realize dynamic X-ray image processing.

Description

Technical Field

[0001] This disclosure relates to the field of dynamic X-ray image processing technology, and in particular to a dynamic X-ray image processing method, system and dynamic X-ray camera. Background Technology

[0002] Pulmonary ventilation is the exchange of gases between the lungs and the external environment, while pulmonary gas exchange is the exchange of gases between the alveoli and the blood. Pulmonary ventilation is achieved through respiratory movements, while pulmonary gas exchange ensures the renewal of gases in the blood; both work together to maintain normal physiological functions. Specifically, pulmonary ventilation refers to the process of gas exchange between the lungs and the external environment during respiration. It involves the entry of outside air into the alveoli through the respiratory tract and the expulsion of waste gases from the alveoli into the external environment. This process is achieved through rhythmic respiratory movements of the chest cavity, including inhalation and exhalation.

[0003] Lung ventilation status is directly related to chronic obstructive pulmonary disease (COPD). Currently, dynamic X-ray imaging can be used to obtain multiple dynamic two-dimensional chest X-ray images during breathing. Although multiple dynamic two-dimensional chest X-ray images during breathing can reflect lung ventilation status, due to the effect of heartbeat, lung ventilation during breathing is often combined with pulmonary blood flow. This makes it impossible to accurately extract lung ventilation from multiple dynamic two-dimensional chest X-ray images during breathing.

[0004] The core problem of accurately extracting lung ventilation from multiple dynamic 2D chest X-ray images during respiration due to the effect of heartbeat lies in the difficulty of matching the mixed image sequence of lung airflow and blood flow corresponding to multiple dynamic 2D chest X-ray images during respiration with the lung blood flow image sequence corresponding to multiple 2D chest X-ray images at multiple times during breath-holding. Therefore, it is necessary to propose a dynamic X-ray image processing technology to solve the current technical problem of matching the mixed image sequence of lung airflow and blood flow corresponding to multiple dynamic 2D chest X-ray images during respiration with the lung blood flow image sequence corresponding to multiple 2D chest X-ray images at multiple times during breath-holding, so as to accurately extract lung ventilation from multiple dynamic 2D chest X-ray images during respiration. Summary of the Invention

[0005] This disclosure proposes a dynamic X-ray image processing method, system, and corresponding technical solution for a dynamic X-ray camera.

[0006] According to one aspect of this disclosure, a dynamic X-ray image processing method is provided, comprising: acquiring multiple first cardiac edge distances of a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac edge distances of a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during breath-holding; matching the multiple first cardiac edge distances and the multiple second cardiac edge distances to determine the correspondence between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0007] Preferably, determining the plurality of first cardiac edge distances includes: determining the plurality of first cardiac edge distances corresponding to the lung airflow and blood flow mixed image sequence based on the right lung mask edge image and left lung mask edge image of the first fixed X-ray image to be registered of the plurality of first right lung X-ray images and the plurality of first left lung X-ray images to be registered corresponding to the lung airflow and blood flow mixed image sequence.

[0008] Preferably, before determining the multiple first cardiac border distances corresponding to the lung airflow and blood flow mixed image sequence based on the right lung mask edge image and left lung mask edge image of the first fixed X-ray image to be registered based on the multiple first right lung X-ray images and multiple first left lung X-ray images to be registered corresponding to the lung airflow and blood flow mixed image sequence, the method includes: acquiring multiple first right lung mask registration images corresponding to the multiple first right lung X-ray registration images and multiple first left lung mask registration images corresponding to the multiple first right lung X-ray registration images during the determination of the lung airflow and blood flow mixed image sequence; and respectively processing the multiple first right lung mask registration images... Edge detection is performed on multiple first left lung mask registration images to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence; or, it includes: acquiring multiple first right lung mask images corresponding to multiple first right lung X-ray images and multiple first left lung mask images corresponding to multiple first left lung X-ray images during the determination of the lung airflow and blood flow mixed image sequence; edge detection is performed on the multiple first right lung mask images and multiple first left lung mask images respectively to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence.

[0009] Preferably, determining the multiple first cardiac border distances corresponding to the lung airflow and blood flow mixed image sequence based on the right lung mask edge image and the left lung mask edge image of each lung airflow and blood flow mixed image sequence includes: determining the corresponding right cardiac border point and left cardiac border point based on the right lung mask edge image and the left lung mask edge image of each lung airflow and blood flow mixed image sequence; calculating the horizontal distance between the right cardiac border point and the left cardiac border point corresponding to each lung airflow and blood flow mixed image, and determining the multiple first cardiac border distances corresponding to the lung airflow and blood flow mixed image sequence.

[0010] Preferably, determining the plurality of second cardiac border distances includes: determining the plurality of second cardiac border distances corresponding to the lung blood flow image sequence based on the right lung mask edge image and the left lung mask edge image of the second right lung X-ray image and the second left lung X-ray image to be registered corresponding to the lung blood flow image sequence.

[0011] Preferably, before determining the multiple second cardiac border distances corresponding to the lung blood flow image sequence based on the right lung mask edge image and left lung mask edge image of the second X-ray image to be fixed and registered, respectively based on the lung blood flow image sequence or the multiple second right lung X-ray images and multiple second left lung X-ray images to be registered corresponding to the lung blood flow image sequence, the method includes: acquiring multiple second right lung mask registration or Gaussian blur images and multiple second left lung mask registration or Gaussian blur images corresponding to the multiple second right lung X-ray registration or Gaussian blur images during the determination of the lung blood flow image sequence; and respectively processing the multiple second right lung mask registration or Gaussian blur images and multiple second left lung X-ray images. Edge detection is performed on the masked registration or Gaussian blurred image to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence; or, it includes: acquiring multiple second right lung mask images and multiple second left lung mask images corresponding to the multiple second right lung X-ray images and multiple second left lung X-ray images to be registered during the determination of the lung blood flow image sequence; edge detection is performed on the multiple second right lung mask images and multiple second left lung mask images respectively to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence.

[0012] Preferably, determining the multiple second cardiac border distances corresponding to the lung blood flow image sequence based on the right lung mask edge image and the left lung mask edge image of each lung blood flow image in the lung blood flow image sequence includes: determining the corresponding right cardiac border point and left cardiac border point based on the right lung mask edge image and the left lung mask edge image of each lung blood flow image in the lung blood flow image sequence; calculating the horizontal distance between the right cardiac border point and the left cardiac border point corresponding to each lung blood flow image to determine the multiple second cardiac border distances corresponding to the lung blood flow image sequence.

[0013] Preferably, before acquiring the multiple first cardiac border distances of the lung airflow and blood flow mixed image sequence corresponding to the multiple dynamic two-dimensional chest X-ray images during respiration, determining the lung airflow and blood flow mixed image sequence includes: segmenting the lung fields of the multiple dynamic two-dimensional chest X-ray images during respiration to obtain multiple first right lung mask images, multiple first left lung mask images, and one or more first mask images of multiple first lung masks; and extracting multiple first right lung X-ray images, multiple first left lung X-ray images, and one or more first lung X-ray images corresponding to the multiple first right lung mask images, the multiple first left lung mask images, and one or more first mask images of multiple lung masks. Or several first X-ray images; register multiple first right lung X-ray images, multiple first left lung X-ray images, and one or more first lung X-ray images that are adjacent or at a set time interval to obtain multiple first right lung X-ray registered images, multiple first left lung X-ray registered images, and one or more first lung X-ray registered images; perform pixel-level subtraction processing on multiple first right lung X-ray registered images, multiple first left lung X-ray registered images, and one or more first lung X-ray registered images that are adjacent or at a set time interval to determine the lung airflow and blood flow mixed image sequence corresponding to the acquired dynamic multiple X-ray two-dimensional chest images during the respiratory process.

[0014] Preferably, before determining the multiple second cardiac border distances of the pulmonary blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple time points during the breath-holding state, the determination of the pulmonary blood flow image sequence includes: performing lung field segmentation on the multiple two-dimensional chest X-ray images at multiple time points during the breath-holding state to obtain multiple second right lung mask images, multiple second left lung mask images, and one or more second mask images of multiple second lung masks; extracting multiple second right lung X-ray images, multiple second left lung X-ray images, and one or more second lung X-ray images corresponding to the multiple second right lung mask images, the multiple second left lung mask images, and one or more second lung mask images of multiple lung masks; and extracting multiple second right lung X-ray images, multiple second left lung X-ray images, and one or more second lung X-ray images of multiple lung masks corresponding to adjacent or predetermined time intervals. A second right lung X-ray image, multiple second left lung X-ray images, and one or more types of second lung X-ray images are registered or Gaussian blurred to obtain multiple registered or Gaussian blurred second right lung X-ray images, multiple registered or Gaussian blurred second left lung X-ray images, and one or more types of registered or Gaussian blurred second lung X-ray images. Pixel-level subtraction processing is performed on multiple registered or Gaussian blurred second right lung X-ray images, multiple registered or Gaussian blurred second left lung X-ray images, and one or more types of registered or Gaussian blurred second lung X-ray images at adjacent times or at a set time interval to determine the lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times under the breath-holding state.

[0015] Preferably, the step of matching the plurality of first cardiac border distances and the plurality of second cardiac border distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: calculating the plurality of cardiac border distance differences between each of the plurality of first cardiac border distances and the plurality of second cardiac border distances; matching the lung airflow and blood flow mixed image corresponding to the first cardiac border distance with the smallest difference among the plurality of cardiac border distances with the lung blood flow image corresponding to the second cardiac border distance to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0016] Preferably, the dynamic X-ray image processing method further includes: determining one or more of the following lung ventilation volumes based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence with the corresponding matching relationship: dynamic left lung ventilation, dynamic right lung ventilation, and dynamic lung ventilation.

[0017] Preferably, determining one or more of the following lung ventilation volumes—dynamic left lung ventilation, dynamic right lung ventilation, and dynamic lung ventilation—based on the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: registering the left lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence with its matching left lung blood flow image to obtain a left lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the left lung airflow and blood flow mixed registration image sequence and its matching left lung blood flow image to determine the dynamic left lung ventilation; and / or, respectively registering the lung airflow and blood flow mixed registration image sequence with its matching left lung blood flow image to determine the dynamic left lung ventilation; and / or, respectively registering the left lung airflow and blood flow mixed registration image sequence with its matching left lung blood flow image to determine the dynamic left lung ventilation. The right lung airflow and blood flow mixed image sequence in the airflow and blood flow mixed image sequence is registered with its matching right lung blood flow image to obtain a right lung airflow and blood flow mixed registered image sequence; pixel-level subtraction processing is performed on the right lung airflow and blood flow mixed registered image sequence and its matching right lung blood flow image to determine the dynamic right lung ventilation; and / or, the lung airflow and blood flow mixed image sequence is registered with its matching lung blood flow image to obtain a lung airflow and blood flow mixed registered image sequence; pixel-level subtraction processing is performed on the lung airflow and blood flow mixed registered image sequence and its matching lung blood flow image to determine the dynamic lung ventilation.

[0018] Preferably, the method further includes: acquiring the volume of the maximum exhaled volume in the first second during the breathing process and the dynamic lung ventilation determined by the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence based on the corresponding matching relationship; training the preset neural network using the lung ventilation and the corresponding volume of the maximum exhaled volume in the first second to construct a relationship model between the lung ventilation and the volume of the maximum exhaled volume in the first second.

[0019] Preferably, the step of training the preset neural network using the dynamic lung ventilation and the corresponding volume of the maximum exhaled volume in the first second to construct a relationship model between the lung ventilation and the volume of the maximum exhaled volume in the first second includes: configuring the dynamic lung ventilation and the corresponding volume of the maximum exhaled volume in the first second as feature vectors and their corresponding labels; and training the preset neural network based on the feature vectors and their corresponding labels to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhaled volume in the first second.

[0020] According to one aspect of this disclosure, a dynamic X-ray image processing system is provided, comprising: an acquisition unit, configured to acquire multiple first cardiac edge distances of a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac edge distances of a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during breath-holding; and a matching unit, configured to match the multiple first cardiac edge distances and the multiple second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0021] According to one aspect of this disclosure, a dynamic X-ray image processing system is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the dynamic X-ray image processing method described above.

[0022] According to one aspect of this disclosure, a dynamic X-ray image processing system is provided, comprising: a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the above-described dynamic X-ray image processing method.

[0023] According to one aspect of this disclosure, a dynamic X-ray image processing system is provided, comprising: a computer program product, the computer program product being configured with computer program instructions that, when executed by a processor, implement the aforementioned dynamic X-ray image processing method.

[0024] According to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: an acquisition unit, configured to acquire multiple first cardiac distances of a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac distances of a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during breath-holding; and a matching unit, configured to match the multiple first cardiac distances and the multiple second cardiac distances to determine a corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0025] According to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the aforementioned dynamic X-ray image processing method.

[0026] According to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the above-described dynamic X-ray image processing method.

[0027] According to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: a computer program product, wherein the computer program product is configured with computer program instructions that, when executed by a processor, implement the aforementioned dynamic X-ray image processing method.

[0028] According to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: the dynamic X-ray image processing system as described above.

[0029] In this embodiment of the disclosure, the core problem of the inability to accurately extract lung ventilation from multiple dynamic two-dimensional chest X-ray images during respiration due to the effect of heartbeat lies in the difficulty of matching the lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration with the lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times under breath-holding conditions. It is necessary to propose a dynamic X-ray image processing method, system, and corresponding technical solution for a dynamic X-ray camera to solve the current technical problem of the difficulty in matching the lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration with the lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times under breath-holding conditions, so as to accurately extract lung ventilation from multiple dynamic two-dimensional chest X-ray images during respiration.

[0030] 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.

[0031] 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

[0032] 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.

[0033] Figure 1 A flowchart illustrating a dynamic X-ray image processing method according to an embodiment of the present disclosure is shown. Detailed Implementation

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] It is understood that the various embodiments of dynamic X-ray image processing methods 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.

[0039] In addition, this disclosure also provides a diagram of a dynamic X-ray image processing apparatus or system, electronic equipment, computer-readable storage medium, and program, all of which can be used to implement any of the dynamic X-ray image processing 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.

[0040] Figure 1 A flowchart illustrating a dynamic X-ray image processing method according to an embodiment of the present disclosure is shown, such as... Figure 1 As shown, the dynamic X-ray image processing method includes: Step S101: acquiring multiple first cardiac border distances of a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac border distances of a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during breath-holding; Step S102: matching the multiple first cardiac border distances and the multiple second cardiac border distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0041] In this embodiment of the disclosure, the mixed image sequence of lung airflow and blood flow includes: a mixed image sequence of left lung airflow and blood flow and a mixed image sequence of right lung airflow and blood flow; the lung blood flow image sequence includes: a blood flow image sequence of left lung and a blood flow image sequence of right lung; the dynamic multiple X-ray two-dimensional chest images during the breathing process and the multiple X-ray two-dimensional chest images at multiple moments during the breath-holding state are taken from the same subject.

[0042] Step S101: Obtain multiple first cardiac border distances of the lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during the breathing process, and multiple second cardiac border distances of the lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during the breath-holding state.

[0043] In this embodiment of the disclosure, the step of matching the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: calculating the plurality of cardiac edge distance differences between each of the plurality of first cardiac edge distances and the plurality of second cardiac edge distances; matching the lung airflow and blood flow mixed image corresponding to the first cardiac edge distance with the smallest difference among the plurality of cardiac edge distances with the lung blood flow image corresponding to the second cardiac edge distance to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0044] Step S102: Match the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0045] In this embodiment of the disclosure, determining the plurality of first cardiac edge distances includes: determining the plurality of first cardiac edge distances corresponding to the lung airflow and blood flow mixed image sequence based on the right lung mask edge image and left lung mask edge image of the first fixed X-ray image to be registered of the plurality of first right lung X-ray images and the plurality of first left lung X-ray images to be registered corresponding to the lung airflow and blood flow mixed image sequence.

[0046] In this embodiment of the disclosure, before determining the multiple first cardiac border distances corresponding to the lung airflow and blood flow mixed image sequence based on the right lung mask edge image and left lung mask edge image of the first fixed X-ray image to be registered based on the multiple first right lung X-ray images and multiple first left lung X-ray images to be registered corresponding to the lung airflow and blood flow mixed image sequence, the method includes: acquiring multiple first right lung mask registration images corresponding to the multiple first right lung X-ray registration images and multiple first left lung mask registration images corresponding to the multiple first left lung X-ray registration images during the determination of the lung airflow and blood flow mixed image sequence; and respectively processing the multiple first right lung masks... Edge detection is performed on the registered image and multiple first left lung mask registered images to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence; or, it includes: acquiring multiple first right lung mask images corresponding to multiple first right lung X-ray images and multiple first left lung mask images corresponding to multiple first left lung X-ray images during the determination of the lung airflow and blood flow mixed image sequence; edge detection is performed on the multiple first right lung mask images and multiple first left lung mask images respectively to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence.

[0047] In this embodiment of the disclosure, the plurality of first right lung X-ray registration images are identical to the plurality of first deformation fields corresponding to the plurality of first right lung mask registration images, and the plurality of first left lung X-ray registration images are identical to the plurality of second deformation fields corresponding to the plurality of first left lung mask registration images.

[0048] Specifically, in determining the lung airflow and blood flow mixed image sequence, multiple first right lung X-ray images that are adjacent or at a set time interval are registered to obtain multiple first right lung X-ray registered images and generate multiple corresponding first deformation fields; the multiple first deformation fields are used to perform lung field mask deformation processing on multiple first right lung mask images corresponding to the multiple first right lung X-ray images to obtain multiple first right lung mask registered images.

[0049] Similarly, in determining the lung airflow and blood flow mixed image sequence, multiple first left lung X-ray images that are adjacent or at a set time interval are registered to obtain multiple first left lung X-ray registered images and generate multiple corresponding second deformation fields; the multiple second deformation fields are used to perform lung field mask deformation processing on the multiple first left lung mask images corresponding to the multiple first left lung X-ray images to obtain multiple first left lung mask registered images.

[0050] In this embodiment of the disclosure, determining multiple first cardiac border distances corresponding to the lung airflow and blood flow mixed image sequence based on the right lung mask edge image and the left lung mask edge image of each lung airflow and blood flow mixed image sequence includes: determining the corresponding right cardiac border point and left cardiac border point based on the right lung mask edge image and the left lung mask edge image of each lung airflow and blood flow mixed image sequence; calculating the horizontal distance between the right cardiac border point and the left cardiac border point corresponding to each lung airflow and blood flow mixed image, and determining multiple first cardiac border distances corresponding to the lung airflow and blood flow mixed image sequence.

[0051] In this embodiment of the disclosure, determining the plurality of second cardiac edge distances includes: determining the plurality of second cardiac edge distances corresponding to the lung blood flow image sequence based on the right lung mask edge image and the left lung mask edge image of the second right lung X-ray image and the second left lung X-ray image to be registered corresponding to the lung blood flow image sequence.

[0052] In this embodiment of the disclosure, before determining the multiple second cardiac border distances corresponding to the lung blood flow image sequence based on the right lung mask edge image and left lung mask edge image of the second X-ray image to be fixed and registered, respectively based on the lung blood flow image sequence or the multiple second right lung X-ray images and multiple second left lung X-ray images to be registered corresponding to the lung blood flow image sequence, the method includes: acquiring multiple second right lung mask registration or Gaussian blur images and multiple second left lung mask registration or Gaussian blur images corresponding to the multiple second right lung X-ray registration or Gaussian blur images during the determination of the lung blood flow image sequence; and respectively processing the multiple second right lung mask registration or Gaussian blur images and multiple second... Edge detection is performed on the left lung mask registration or Gaussian blurred image to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence; or, it includes: acquiring multiple second right lung mask images and multiple second left lung mask images corresponding to the multiple second right lung X-ray images and multiple second left lung X-ray images to be registered during the determination of the lung blood flow image sequence; edge detection is performed on the multiple second right lung mask images and multiple second left lung mask images respectively to obtain the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence.

[0053] In this embodiment of the disclosure, the plurality of second right lung X-ray registration images are identical to the plurality of third deformation fields corresponding to the plurality of second right lung mask registration images, and the plurality of second left lung X-ray registration images are identical to the plurality of fourth deformation fields corresponding to the plurality of second left lung mask registration images.

[0054] Specifically, in determining the lung blood flow image sequence, multiple second right lung X-ray images that are adjacent or at a set time interval are registered to obtain multiple corresponding second right lung X-ray registered images and generate multiple corresponding third deformation fields; the multiple third deformation fields are used to perform lung field mask deformation processing on multiple second right lung mask images corresponding to the multiple second right lung X-ray images to obtain multiple second right lung mask registered images.

[0055] Similarly, in determining the lung blood flow image sequence, multiple second left lung X-ray images that are adjacent or at a set time interval are registered to obtain multiple corresponding second left lung X-ray registered images and generate multiple corresponding fourth deformation fields; the multiple fourth deformation fields are used to perform lung field mask deformation processing on multiple second left lung mask images corresponding to the multiple second left lung X-ray images to obtain multiple second left lung mask registered images.

[0056] In this embodiment of the disclosure, determining the multiple second cardiac border distances corresponding to the lung blood flow image sequence based on the right lung mask edge image and the left lung mask edge image of each lung blood flow image in the lung blood flow image sequence includes: determining the corresponding right cardiac border point and left cardiac border point based on the right lung mask edge image and the left lung mask edge image of each lung blood flow image in the lung blood flow image sequence; calculating the horizontal distance between the right cardiac border point and the left cardiac border point corresponding to each lung blood flow image to determine the multiple second cardiac border distances corresponding to the lung blood flow image sequence.

[0057] In this embodiment of the disclosure, before obtaining the multiple first cardiac border distances of the lung airflow and blood flow mixed image sequence corresponding to the multiple dynamic two-dimensional chest X-ray images during respiration, determining the lung airflow and blood flow mixed image sequence includes: segmenting the lung fields (left lung field and / or right lung field and / or both lung fields) of the multiple dynamic two-dimensional chest X-ray images during respiration to obtain one or more first mask images of multiple first right lung mask images, multiple first left lung mask images, and multiple first lung mask images (first double lung mask images) corresponding to the multiple dynamic two-dimensional chest X-ray images during respiration; and extracting multiple first right lung X-ray images, multiple first left lung X-ray images, and first lung X-ray images corresponding to the multiple first right lung mask images, the multiple first left lung mask images, and one or more of the multiple lung mask images, respectively. One or more first X-ray images (first bilateral lung X-ray images); registration of one or more first X-ray images of the right lung, the left lung, and the lungs (bilateral lung X-ray images) at adjacent or set time intervals to obtain one or more first X-ray registered images of the right lung, the left lung, and the lungs (bilateral lung X-ray images); pixel-level subtraction processing is performed on one or more first X-ray registered images of the right lung, the left lung, and the lungs (bilateral lung X-ray images) at adjacent or set time intervals to determine the lung airflow and blood flow mixed image sequence corresponding to the acquired dynamic multi-X-ray two-dimensional chest images during the respiratory process.

[0058] In this embodiment of the disclosure, the step of extracting one or more first X-ray images corresponding to the plurality of first right lung mask images, the plurality of first left lung mask images, and one or more of the first mask images of the plurality of lung mask images includes: performing pixel-level multiplication processing on one or more of the first mask images of the plurality of first right lung mask images, the plurality of first left lung mask images, and the plurality of first lung mask images (first bilateral lung mask images) with the dynamic multiple two-dimensional chest X-ray images during the breathing process, and extracting one or more of the first X-ray images corresponding to the plurality of first right lung mask images, the plurality of first left lung mask images, and the plurality of first lung mask images (first bilateral lung mask images).

[0059] In this embodiment of the disclosure, before determining the multiple second cardiac border distances of the pulmonary blood flow image sequence corresponding to multiple X-ray two-dimensional chest images at multiple times during the breath-holding state, the determination of the pulmonary blood flow image sequence includes: segmenting the lung fields (left lung field and / or right lung field and / or both lung fields) of the multiple X-ray two-dimensional chest images at multiple times during the breath-holding state to obtain one or more second mask images of multiple second right lung mask images, multiple second left lung mask images, and multiple second lung mask images (second bilateral lung mask images) corresponding to the multiple X-ray two-dimensional chest images at multiple times during the breath-holding state; extracting one or more second lung X-ray images of multiple second right lungs, multiple second left lungs, and multiple lung mask images (second bilateral lung X-ray images) corresponding to the multiple second right lung mask images, the multiple second left lung mask images, and one or more second lung mask images; respectively Multiple second X-ray images of the right lung, left lung, and lungs (bilateral lung X-ray images) taken at adjacent or predetermined time intervals are registered or Gaussian blurred to obtain multiple second right lung X-ray registered or Gaussian blurred images, multiple second left lung X-ray registered or Gaussian blurred images, and multiple second lung X-ray registered or Gaussian blurred images (bilateral lung X-ray registered or Gaussian blurred images). Pixel-level subtraction is then performed on these multiple second right lung X-ray registered or Gaussian blurred images, multiple second left lung X-ray registered or Gaussian blurred images, and multiple second lung X-ray registered or Gaussian blurred images (bilateral lung X-ray registered or Gaussian blurred images) taken at adjacent or predetermined time intervals to determine the lung blood flow image sequence corresponding to the multiple two-dimensional chest X-ray images taken at multiple time intervals under the breath-holding state.

[0060] In this embodiment of the disclosure, the step of extracting one or more second lung X-ray images corresponding to the plurality of second right lung mask images, the plurality of second left lung mask images, and one or more of the second mask images of the plurality of lung mask images includes: performing pixel-level multiplication processing on the plurality of second right lung mask images, the plurality of second left lung mask images, and one or more of the second mask images of the plurality of lung mask images and the multiple two-dimensional chest X-ray images taken at multiple times during the breath-holding state, to extract one or more of the second lung X-ray images corresponding to the plurality of second right lung mask images, the plurality of second left lung mask images, and one or more of the second mask images of the plurality of lung mask images.

[0061] In this disclosure, the prior art (2024115505799, 2024-10-31, Dynamic Cardiac Angle Positioning Optimization Method and Apparatus, Program Product and Medical Device) is cited in this invention, and the technical solutions described in the above-mentioned prior art constitute a part of the specification of this disclosure.

[0062] In this embodiment of the disclosure, before calculating the horizontal distance between the right and left cardiac border points corresponding to each lung airflow and blood flow mixed image and / or before calculating the horizontal distance between the right and left cardiac border points corresponding to each lung blood flow image, the right cardiophrenic angle corresponding to the right cardiac border point and the left cardiophrenic angle corresponding to the left cardiac border point are optimized, including: acquiring at least one diaphragm sequence corresponding to dynamic right lung diaphragm sequence and dynamic left lung diaphragm sequence from multiple dynamic X-ray two-dimensional chest images during respiration and / or multiple X-ray two-dimensional chest images at multiple times during breath-holding; and determining whether there exists a diaphragm sequence in the dynamic right lung diaphragm sequence based on a first length sequence corresponding to the dynamic right lung diaphragm sequence. An abnormal right diaphragm sequence is identified; if present, the abnormal left cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence within the dynamic right lung diaphragm sequence is used to optimize the localization of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence within the same first X-ray two-dimensional chest image; and / or, based on the second length sequence corresponding to the dynamic left lung diaphragm sequence, it is determined whether an abnormal left diaphragm sequence exists within the dynamic left lung diaphragm sequence; if present, the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence within the abnormal right diaphragm in the same second X-ray two-dimensional chest image is optimized using the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence within the dynamic left lung diaphragm sequence.

[0063] In this embodiment of the disclosure, determining whether an abnormal right diaphragm sequence exists in the dynamic right lung diaphragm sequence based on the first length sequence corresponding to the dynamic right lung diaphragm sequence includes: determining the shortest length of the first length sequence corresponding to the dynamic right lung diaphragm sequence as the right lung baseline diaphragm length; and determining whether an abnormal right diaphragm exists in the dynamic right lung diaphragm sequence based on the difference between the right lung baseline diaphragm length and a first length in the first length sequence other than the right lung baseline diaphragm length being greater than or equal to a first preset length difference.

[0064] In this embodiment of the disclosure, determining whether an abnormal left diaphragm sequence exists in the dynamic left diaphragm sequence based on the second length sequence corresponding to the dynamic left diaphragm sequence includes: determining the left lung baseline diaphragm length based on the shortest length in the second length sequence corresponding to the dynamic left diaphragm sequence; and determining whether an abnormal left diaphragm exists in the dynamic left diaphragm sequence based on the difference between the left lung baseline diaphragm length and the second length in the second length sequence other than the left lung baseline diaphragm length being greater than or equal to a second preset length difference.

[0065] In this embodiment of the disclosure, the step of optimizing the localization of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence within the same first X-ray two-dimensional chest image using the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence includes: determining the standard X-ray two-dimensional chest images corresponding to the normal right diaphragm and normal left diaphragm in the dynamic multiple X-ray two-dimensional chest images and / or the multiple X-ray two-dimensional chest images at multiple times under breath-holding conditions; and configuring the normal left cardiophrenic angle corresponding to the normal left diaphragm in the standard X-ray two-dimensional chest image to the same first X-ray two-dimensional chest image. The initial left cardiophrenic angle is determined by the abnormal left diaphragm sequence in the standard two-dimensional chest image. A first distance in the y-direction is calculated between the normal right cardiophrenic angle corresponding to the normal right diaphragm in the standard two-dimensional chest image and the normal right cardiophrenic angle corresponding to the normal right diaphragm in the first two-dimensional chest image. The initial left cardiophrenic angle is adjusted using the first distance in the y-direction to obtain an adjusted left cardiophrenic angle. Based on the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first two-dimensional chest image, the abnormal left cardiophrenic angle is located and optimized.

[0066] In this embodiment of the disclosure, the step of optimizing the localization of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence within the same second X-ray two-dimensional chest image using the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence within the dynamic left lung diaphragm sequence includes: determining the standard X-ray two-dimensional chest images corresponding to the normal left and right diaphragms in the dynamic multi-image X-ray two-dimensional chest images; configuring the normal right cardiophrenic angle corresponding to the normal right diaphragm in the standard X-ray two-dimensional chest image to the initial right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence within the same second X-ray two-dimensional chest image; calculating the second distance in the y-direction between the normal left cardiophrenic angle corresponding to the normal left diaphragm in the standard X-ray two-dimensional chest image and the normal left cardiophrenic angle corresponding to the normal left diaphragm in the second X-ray two-dimensional chest image; adjusting the initial right cardiophrenic angle using the second distance in the y-direction to obtain the adjusted right cardiophrenic angle; and optimizing the localization of the abnormal right cardiophrenic angle based on the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image.

[0067] In the embodiments of this disclosure, a two-dimensional chest X-ray image can be referred to as a two-dimensional chest X-ray image, a two-dimensional chest X-ray image, or a two-dimensional X-ray image, etc. Any combination of two or more of the terms X-ray / DR, two-dimensional, chest, and image expresses the same meaning.

[0068] In the embodiments of this disclosure, normal right diaphragm sequence (normal right lung diaphragm sequence), abnormal right diaphragm sequence (abnormal right lung diaphragm sequence), normal left diaphragm sequence (normal left lung diaphragm sequence) and abnormal left diaphragm sequence (abnormal left lung diaphragm sequence) corresponding to multiple dynamic two-dimensional chest X-ray images during the breathing process are acquired.

[0069] In the embodiments of this disclosure, a digital X-ray (DR) imaging device can provide high-resolution and real-time two-dimensional X-ray images. The DR imaging device can be used to image the chest, obtaining corresponding two-dimensional X-ray chest images. For example, in the embodiments of this disclosure, the digital X-ray imaging device can be used to image the chest containing the lungs during free breathing or forced breathing, obtaining multiple dynamic two-dimensional X-ray chest images (dynamic two-dimensional X-ray chest images to be located) corresponding to a continuous time series during breathing. Simultaneously, the digital X-ray imaging device can also be used to image the chest containing the lungs during breath-holding, obtaining multiple dynamic two-dimensional X-ray chest images (two-dimensional X-ray chest images to be located) corresponding to a continuous time series during breath-holding. Specifically, the dynamic multiple two-dimensional X-ray chest images during breathing or during breath-holding include at least one two-dimensional X-ray chest image.

[0070] In the embodiments of this disclosure, the lung image to be segmented (the dynamic multiple X-ray two-dimensional chest images during the breathing process / the dynamic X-ray two-dimensional chest image to be located) is segmented into a left chest image and a right chest image; the left lung and the right lung are segmented based on the left chest image and the right chest image, respectively.

[0071] In embodiments of this disclosure, the lung image to be segmented (the dynamic multiple X-ray two-dimensional chest images during breathing / dynamic X-ray two-dimensional chest images to be located) 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 preset convolutional neural network segmentation model, DR lung region label images used to train the segmentation model, and multiple DR lung images to be segmented at multiple times during breathing or breath-holding (lung image to be segmented / dynamic multiple X-ray two-dimensional chest images during breathing to be segmented / dynamic X-ray two-dimensional chest images to be segmented to be located). Based on the trained segmentation model, the left lung and / or right lung segmentation of the multiple DR lung images to be segmented (i.e., the X-ray two-dimensional chest images to be located / X-ray two-dimensional chest images) is completed, resulting in the right lung mask image and / or the left lung mask image. The lung field mask value corresponding to the right lung mask image can be configured to 1, and the lung field mask value corresponding to the left lung mask image can be configured to 2.

[0072] In the embodiments of this disclosure, the set of left lung mask edge images corresponding to each of the dynamic multi-dimensional X-ray chest images constitutes a left lung mask edge image sequence; similarly, the set of right lung mask edge images corresponding to each of the dynamic multi-dimensional X-ray chest images constitutes a right lung mask edge image sequence.

[0073] In the embodiments of this disclosure, the set of right lung mask erosion images corresponding to each of the dynamic multi-dimensional X-ray chest images constitutes a right lung mask erosion image sequence; similarly, the set of left lung mask erosion images corresponding to each of the dynamic multi-dimensional X-ray chest images constitutes a left lung mask erosion image sequence.

[0074] In an embodiment of this disclosure, the method for determining the right lung mask edge image sequence based on the right lung mask image sequence and its corresponding right lung mask erosion image sequence includes: subtracting the pixel value of the corresponding position in the right lung mask erosion image sequence from the pixel value of each position in the right lung mask image sequence to determine the right lung mask edge image sequence.

[0075] In an embodiment of this disclosure, the method for determining the left lung mask edge image sequence based on the left lung mask image sequence and its corresponding left lung mask erosion image sequence includes: subtracting the pixel value of the corresponding position in the left lung mask erosion image sequence from the pixel value of each position in the left lung mask image sequence to determine the left lung mask edge image sequence.

[0076] In the embodiments of this disclosure, before determining the right lung mask edge image sequence and / or left lung mask edge image sequence corresponding to the dynamic multiple X-ray two-dimensional chest images respectively, a preset lung field segmentation model is used to segment the lung fields of the dynamic multiple X-ray two-dimensional chest images respectively to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0077] In embodiments of this disclosure, the method of segmenting the lung fields of the dynamic multiple X-ray two-dimensional chest images using a preset lung field segmentation model to obtain the right lung mask image sequence and / or the left lung mask image sequence includes: segmenting the lung fields of the dynamic multiple X-ray two-dimensional chest images using a preset lung field segmentation model to obtain the right lung mask image sequence to be processed (the right lung mask image to be processed) and / or the left lung mask image sequence to be processed (the left lung mask image sequence to be processed); and processing the right lung mask image sequence to be processed and / or the left lung mask image sequence to be processed using a connected component algorithm to remove over-segmented regions outside the lung fields to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0078] In embodiments of this disclosure, the preset convolutional neural network corresponding to the segmentation model (preset lung field segmentation model) can be 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.

[0079] In embodiments of this disclosure, before acquiring the normal right diaphragm sequence, abnormal right diaphragm sequence, normal left diaphragm sequence, and abnormal left diaphragm sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, the method for determining the normal right diaphragm sequence, abnormal right diaphragm sequence, normal left diaphragm sequence, and abnormal left diaphragm sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration includes: acquiring at least one diaphragm sequence of dynamic right lung diaphragm sequence and dynamic left lung diaphragm sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration; determining the normal right diaphragm sequence and abnormal right diaphragm sequence corresponding to the dynamic right lung diaphragm sequence based on a first length sequence corresponding to the dynamic right lung diaphragm sequence; and / or, determining the normal left diaphragm sequence and abnormal left diaphragm sequence corresponding to the dynamic left lung diaphragm sequence based on a second length sequence corresponding to the dynamic left lung diaphragm sequence.

[0080] In embodiments of this disclosure, the method for determining the normal right diaphragm sequence and the abnormal right diaphragm sequence corresponding to the dynamic right lung diaphragm sequence based on the first length sequence corresponding to the dynamic right lung diaphragm sequence includes: determining the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence as the right lung baseline diaphragm length; and determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms based on the right lung baseline diaphragm length, the first length in the first length sequence excluding the right lung baseline diaphragm length, and the difference between the first preset length and the first length.

[0081] In embodiments of this disclosure, the method for determining the normal left diaphragm sequence and the abnormal left diaphragm sequence corresponding to the dynamic left diaphragm sequence based on the second length sequence corresponding to the dynamic left diaphragm sequence includes: determining the left lung baseline diaphragm length based on the shortest length in the second length sequence corresponding to the dynamic left diaphragm sequence; and determining the other left diaphragms as normal left diaphragms or abnormal left diaphragms based on the difference between the left lung baseline diaphragm length, the second length in the second length sequence excluding the left lung baseline diaphragm length, and the second preset length.

[0082] In embodiments of this disclosure, the method of determining the right lung baseline diaphragm length by the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence, and determining the other right lung diaphragms as normal or abnormal based on the right lung baseline diaphragm length, the first length in the first length sequence excluding the right lung baseline diaphragm length, and the difference between the first and first preset lengths, includes: determining the right lung baseline diaphragm by the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; and determining the other right lung diaphragms as normal or abnormal based on the first baseline length corresponding to the right lung baseline diaphragm, the first length in the dynamic right lung diaphragm sequence excluding the right lung baseline diaphragm, and the difference between the first and first preset lengths, respectively.

[0083] In embodiments of this disclosure, the method of determining the left lung baseline diaphragm length by the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence, and determining the other left lung diaphragms as normal or abnormal based on the difference between the left lung baseline diaphragm length, the second length in the second length sequence excluding the left lung baseline diaphragm length, and the second preset length, includes: determining the left lung baseline diaphragm by the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and determining the other left lung diaphragms as normal or abnormal based on the difference between the second baseline length corresponding to the left lung baseline diaphragm, the second length in the dynamic left lung diaphragm sequence excluding the left lung baseline diaphragm, and the second preset length, respectively.

[0084] In embodiments of this disclosure, a method for determining the first length sequence corresponding to the dynamic right lung diaphragm sequence includes: respectively counting the sum of the number of first pixel values ​​corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence; respectively obtaining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the number of first pixel values ​​corresponding to each right lung diaphragm and the area corresponding to each pixel; and / or, the method for determining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the number of first pixel values ​​corresponding to each right lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the number of first pixel values ​​corresponding to each right lung diaphragm by the area corresponding to each pixel to obtain the first length sequence corresponding to the dynamic right lung diaphragm sequence.

[0085] In embodiments of this disclosure, a method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence includes: summing the number of second pixel values ​​corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence; obtaining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the number of second pixel values ​​corresponding to each left lung diaphragm and the area corresponding to each pixel; and / or, the method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the number of second pixel values ​​corresponding to each left lung diaphragm and the area corresponding to each pixel includes: multiplying the sum of the number of second pixel values ​​corresponding to each left lung diaphragm by the area corresponding to each pixel to obtain the second length sequence corresponding to the dynamic left lung diaphragm sequence.

[0086] In embodiments of this disclosure, the unit of the first length sequence and / or the second length sequence is configured as pixel values. Specifically, the first length sequence is obtained by summing the number of first pixel values ​​corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence; and / or, the second length sequence is obtained by summing the number of second pixel values ​​corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence.

[0087] Furthermore, in the embodiments disclosed herein, the first preset length difference and the configured values ​​of the first preset length difference may be the same or different. For example, the first value corresponding to the first preset length difference may be configured as any value between 10 and 50 pixels; the second value corresponding to the second preset length difference may be configured as any value between 10 and 50 pixels. Additionally, those skilled in the art may configure other values ​​for the first value corresponding to the first preset length difference and the second value corresponding to the second preset length difference according to actual needs.

[0088] For example, in the embodiments of this disclosure, the first value corresponding to the first preset length difference and the second value corresponding to the second preset length difference can be configured as any one of 10, 20, 30, 40, and 50, respectively.

[0089] In embodiments of this disclosure, before acquiring at least one diaphragm sequence of the dynamic right lung diaphragm sequence and the dynamic left lung diaphragm sequence corresponding to multiple dynamic X-ray two-dimensional chest images during respiration, a method for determining the corresponding dynamic right lung diaphragm sequence and / or dynamic left lung diaphragm sequence based on the multiple dynamic X-ray two-dimensional chest images during respiration includes: acquiring at least one masked edge image sequence of the right lung masked edge image sequence (right lung masked edge image) and the left lung masked edge image sequence (left lung masked edge image) corresponding to multiple dynamic X-ray two-dimensional chest images (dynamic X-ray two-dimensional chest images to be located during respiration / dynamic lung images during respiration); and determining each right lung masked edge image in the right lung masked edge image sequence. The corresponding right lung apex; the right lung diaphragm is located based on the right lung apex, the right costophrenic angle, and the right lung mask edge image corresponding to each of the dynamic multi-X-ray two-dimensional chest images (each right lung mask edge image); and / or, the left lung apex corresponding to each left lung mask edge image in the left lung mask edge image sequence is determined, and the right costophrenic angle and / or the left costophrenic angle corresponding to each left lung mask edge image in the right lung mask edge image sequence are determined; the left lung diaphragm is located based on the right cardiophrenic angle, the left lung apex, the left costophrenic angle, and the left lung mask edge image corresponding to each of the dynamic multi-X-ray two-dimensional chest images (each left lung mask edge image). The set of right lung diaphragms corresponding to each of the dynamic multi-X-ray two-dimensional chest images constitutes a dynamic right lung diaphragm sequence; similarly, the set of left lung diaphragms corresponding to each of the dynamic multi-X-ray two-dimensional chest images constitutes a dynamic left lung diaphragm sequence.

[0090] In an embodiment of this disclosure, the method for determining the right lung apex corresponding to the right lung mask edge image sequence includes: detecting the right lung vertex corresponding to each right lung mask edge image in the right lung mask edge image sequence, and configuring the right lung vertex as the right lung apex corresponding to the right lung mask edge image sequence.

[0091] In an embodiment of this disclosure, the method for determining the left lung apex corresponding to the left lung mask edge image sequence includes: detecting the left lung vertex corresponding to each left lung mask edge image in the left lung mask edge image sequence, and configuring the left lung vertex as the left lung apex corresponding to the left lung mask edge image sequence.

[0092] In an embodiment of this disclosure, the method for determining the right costophrenic angle point corresponding to the right lung mask edge image sequence includes: detecting the lowest point of the right lung corresponding to each right lung mask edge image in the right lung mask edge image sequence, and configuring the lowest point of the right lung as the right costophrenic angle point corresponding to the right lung mask edge image sequence.

[0093] In embodiments of this disclosure, the method for determining the left costophrenic angle points corresponding to the left lung mask edge image sequence includes: detecting the lowest point of the left lung corresponding to each left lung mask edge image in the left lung mask edge image sequence, and configuring the lowest point of the left lung as the left costophrenic angle point corresponding to the left lung mask edge image sequence.

[0094] In embodiments of this disclosure, the method for locating the right lung diaphragm based on the right lung apex, right costophrenic angle, and right lung mask edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images includes: determining corresponding first straight lines based on the right lung apex and right costophrenic angle corresponding to each of the dynamic multiple X-ray two-dimensional chest images; calculating multiple first distances from multiple first pixel positions on the right edge line of the right lung mask edge image from the right lung apex to the right costophrenic angle to the first straight line; configuring the first pixel position corresponding to the largest distance among the multiple first distances as the right cardiodiaphragm angle; and configuring the mask edge line segment corresponding to the right lung mask edge image between the right cardiodiaphragm angle and the right costophrenic angle as the corresponding right lung diaphragm.

[0095] In embodiments of this disclosure, the method for locating the left diaphragm based on the right cardiophrenic angle, the left lung apex, the left costophrenic angle, and the left lung mask edge image corresponding to the right diaphragm in each of the dynamic multi-dimensional chest X-ray images includes: determining an auxiliary point corresponding to the lung mask edge image based on the coordinates of the right cardiophrenic angle and a set increment in the y-direction of each of the dynamic multi-dimensional chest X-ray images; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle; calculating multiple second distances from multiple second pixel positions on the left edge line of the left lung mask edge image from the right lung apex to the auxiliary point to the second straight line; configuring the second pixel position corresponding to the largest distance among the multiple second distances as the left cardiophrenic angle, and configuring the mask edge line segment corresponding to the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle as the corresponding left diaphragm.

[0096] In embodiments of this disclosure, the method for determining whether other right lung diaphragms are normal or abnormal right diaphragms based on the right lung baseline diaphragm length, a first length in the first length sequence excluding the right lung baseline diaphragm length, and a first preset length difference includes: calculating multiple first differences between the first length excluding the right lung baseline diaphragm length and the right lung baseline diaphragm length; if one of the multiple differences is greater than or equal to the first preset length difference, then the right diaphragm corresponding to the first difference is determined to be an abnormal right diaphragm; otherwise, it is determined to be a normal right diaphragm.

[0097] For example, in an embodiment of this disclosure, the first preset length difference is configured as 20 mm or 20 pixels. Multiple first differences are calculated between a first length other than the reference diaphragm length of the right lung and the reference diaphragm length of the right lung. If one of the multiple differences is greater than or equal to the first preset length difference of 20 mm or 20 pixels, the right diaphragm corresponding to that first difference is identified as an abnormal right diaphragm. If one of the multiple differences is less than the first preset length difference of 20 mm or 20 pixels, the right diaphragm corresponding to that first difference is identified as a normal right diaphragm.

[0098] In embodiments of this disclosure, the method of determining the left lung baseline diaphragm length by the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and determining whether the other left lung diaphragms are normal or abnormal based on the left lung baseline diaphragm length, the second length in the second length sequence excluding the left lung baseline diaphragm length, and the second preset length difference, includes: calculating multiple second differences between the second length excluding the left lung baseline diaphragm length and the left lung baseline diaphragm length; if one of the multiple second differences is greater than or equal to the second preset length difference, then the left diaphragm corresponding to the second difference is determined to be an abnormal left diaphragm; otherwise, it is determined to be a normal left diaphragm.

[0099] For example, in an embodiment of this disclosure, the first preset length difference is configured as 20 mm or 20 pixels. Multiple second differences are calculated between a second length (excluding the reference diaphragm length for the left lung) and the reference diaphragm length for the left lung. If one of the multiple second differences is greater than or equal to the second preset length difference of 20 mm or 20 pixels, the left diaphragm corresponding to that second difference is identified as an abnormal left diaphragm. If one of the multiple second differences is less than the second preset length difference of 20 mm or 20 pixels, and if one of the multiple second differences is greater than or equal to the second preset length difference of 20 mm or 20 pixels, it indicates a normal left diaphragm.

[0100] In embodiments of this disclosure, the method further includes: acquiring at least one diaphragm sequence corresponding to a normal right diaphragm and an abnormal right diaphragm, and a normal left diaphragm and an abnormal left diaphragm, from multiple dynamic two-dimensional chest X-ray images during respiration; wherein the diaphragm sequence includes: a right diaphragm sequence and / or a left diaphragm sequence; optimizing the location of the right cardiophrenic angle corresponding to the abnormal right diaphragm based on the right cardiophrenic angle corresponding to the normal right diaphragm; and / or optimizing the location of the left cardiophrenic angle corresponding to the abnormal left diaphragm based on the left cardiophrenic angle corresponding to the normal left diaphragm.

[0101] In embodiments of this disclosure, the right cardiophrenic angle corresponding to each abnormal right diaphragm is obtained after localization optimization; the localization of each abnormal diaphragm is optimized based on the right cardiophrenic angle, right costophrenic angle point, and right lung mask edge image corresponding to each abnormal right diaphragm; and / or, the left cardiophrenic angle corresponding to each abnormal left diaphragm is obtained after localization optimization; the localization of each abnormal left diaphragm is optimized based on the left cardiophrenic angle, left costophrenic angle point, and left lung mask edge image corresponding to each abnormal left diaphragm.

[0102] In embodiments of this disclosure, the unit of the first length sequence and / or the second length sequence is configured as pixel values; wherein, the first length sequence is obtained by summing the number of first pixel values ​​corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence; and / or, the second length sequence is obtained by summing the number of second pixel values ​​corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence; and / or, the first preset length difference and the configured value of the first preset length difference are the same or different; and / or, the first value corresponding to the first preset length difference is configured as any value between 10 and 50 pixels; the second value corresponding to the second preset length difference is configured as any value between 10 and 50 pixels.

[0103] In embodiments of this disclosure, before acquiring at least one diaphragm sequence of the dynamic right lung diaphragm sequence and the dynamic left lung diaphragm sequence corresponding to the dynamic multiple X-ray two-dimensional chest images during respiration, a method for determining the corresponding dynamic right lung diaphragm sequence and / or dynamic left lung diaphragm sequence based on the dynamic multiple X-ray two-dimensional chest images during respiration includes: acquiring at least one masked edge image sequence of the right lung masked edge image sequence and the left lung masked edge image sequence corresponding to the dynamic multiple X-ray two-dimensional chest images; determining the right lung apex corresponding to the right lung masked edge image sequence; and locating the right lung diaphragm based on the right lung apex, the right costophrenic angle, and the right lung masked edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images.

[0104] In embodiments of this disclosure, before acquiring at least one diaphragm sequence corresponding to a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence from multiple dynamic X-ray two-dimensional chest images during respiration, the left lung apex corresponding to the left lung mask edge image sequence is determined, and the right costophrenic angle point corresponding to the right lung mask edge image sequence and / or the left costophrenic angle point corresponding to the left lung mask edge image sequence are determined. The left lung diaphragm is located based on the right cardiophrenic angle, the left lung apex, the left costophrenic angle point, and the left lung mask edge image corresponding to the right lung diaphragm in each of the multiple dynamic X-ray two-dimensional chest images.

[0105] In embodiments of this disclosure, the method for locating the right lung diaphragm based on the right lung apex, right costophrenic angle, and right lung mask edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images includes: determining corresponding first straight lines based on the right lung apex and right costophrenic angle corresponding to each of the dynamic multiple X-ray two-dimensional chest images; calculating multiple first distances from multiple first pixel positions (first pixels) on the right edge line (right heart border line near the heart) of the right lung mask edge image from the right lung apex to the right costophrenic angle to the first straight line; configuring the first pixel position corresponding to the largest distance among the multiple first distances as the right costophrenic angle, and configuring the mask edge line segment corresponding to the right lung mask edge image between the right costophrenic angle and the right lung mask edge image as the corresponding right lung diaphragm.

[0106] In embodiments of this disclosure, the method for locating the left diaphragm based on the right cardiophrenic angle, the left lung apex, the left costophrenic angle, and the left lung mask edge image corresponding to the right diaphragm in each of the dynamic multi-dimensional chest X-ray images includes: determining an auxiliary point corresponding to the lung mask edge image based on the coordinates of the right cardiophrenic angle and a set increment in the y-direction of each of the dynamic multi-dimensional chest X-ray images; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle; calculating multiple second distances from multiple second pixel positions (second pixels) on the left edge line (the left heart border line closer to the heart) of the left lung mask edge image from the right lung apex to the auxiliary point to the second straight line; configuring the second pixel position corresponding to the largest distance among the multiple second distances as the left cardiophrenic angle (left cardiophrenic angle point); and configuring the mask edge line segment of the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle as the corresponding left diaphragm.

[0107] In embodiments of this disclosure, the right or left costophrenic angle point corresponding to the left or right lung is close to the origin of the xoy coordinate system; the ordinate of the right or left lung apex corresponding to the left or right lung is greater than the ordinate of the corresponding right or left costophrenic angle point. For example, the right costophrenic angle point corresponding to the right lung is close to the origin of the xoy coordinate system, the y-axis is configured in the direction from the right costophrenic angle point to the right lung apex, and the y-axis is configured in the direction from the right costophrenic angle point to the left costophrenic angle point.

[0108] For example, in an embodiment of this disclosure, the method for determining the corresponding first straight line based on the right lung apex A1 and the right costophrenic angle B1 includes: based on the right lung apex A1 (x A1 ,y A1 ) and the right costophrenic angle point B1 (x B1 ,y B1 Determine the first coefficient a1, the second coefficient b1, and the third coefficient c1 corresponding to the first straight line Line1; determine the first straight line Line1 based on the first coefficient a1, the second coefficient b1, and the third coefficient c1.

[0109] Furthermore, before calculating the first distances from multiple first pixels to the first straight line on the right edge line A1B1 (the right heart border line closer to the heart) of the right lung mask edge image from the right lung apex A1 to the right costophrenic angle B1, the right edge line A1B1 of the right lung mask edge image is determined based on the distance from the right lung apex A1 to the right costophrenic angle B1. The method for determining this method includes: taking the right lung apex A1 as the starting point, and along the right lung mask edge line of the right lung mask edge image, calculating the distance from the right lung apex A1 to the right costophrenic angle B1. The lengths of the first and second edge lines from the right lung apex to the right costophrenic angle B1 are calculated. The lengths of the first and second edge lines from the right lung apex A1 to the right costophrenic angle B1 are also calculated. The first and second edge lines are respectively distributed on both sides of the first straight line Line1. The longest edge line among the lengths of the first and second edge lines is configured as the right edge line A1B1 of the right lung mask edge image.

[0110] For example, in an embodiment of this disclosure, calculating multiple first distances from multiple first pixels on the right edge line A1B1 (the right cardiac border line closer to the heart) of the right lung mask edge image from the right lung apex A1 to the right costophrenic angle B1 to the first straight line Line1 includes: taking the right lung apex A1 as the starting point / end point and the right costophrenic angle B1 as the end point / start point, and sequentially calculating multiple first distances from multiple first pixels to the first straight line Line1 along the right edge line A1B1 of the right lung mask edge image. Furthermore, the first pixel corresponding to the largest distance among the multiple first distances is configured as the right costophrenic angle C1, and the mask edge line segment corresponding to the right lung mask edge image between the right costophrenic angle C1 and the right costophrenic angle B1 is configured and positioned as the right diaphragm B1C1.

[0111] In embodiments of this disclosure, the method for locating the left diaphragm based on the right cardiophrenic angle corresponding to the right diaphragm, the left lung apex, the left costophrenic angle, and the left lung mask edge image includes: determining an auxiliary point corresponding to the lung mask edge image based on the coordinate point of the right cardiophrenic angle and a set increment in the y-direction; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle; calculating multiple second distances from multiple second pixels on the left edge line (the left heart border line closer to the heart) of the left lung mask edge image from the right lung apex to the auxiliary point to the second straight line; configuring the second pixel corresponding to the largest distance among the multiple second distances as the left cardiophrenic angle (left cardiophrenic angle point); and configuring the mask edge line segment corresponding to the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle point as the left diaphragm.

[0112] In an embodiment of this disclosure, the method for determining the auxiliary point corresponding to the lung mask edge image based on the coordinate point of the right cardiophrenic angle and a set increment in the y-direction includes: adding the set increment in the y-direction to the ordinate of the coordinate point to obtain an auxiliary line parallel to the x-direction; and determining the intersection of the auxiliary line and the left lung mask edge image as the auxiliary point corresponding to the lung mask edge image.

[0113] In an embodiment of this disclosure, the method of determining the intersection of the auxiliary line and the left lung mask edge image as the auxiliary point corresponding to the lung mask edge image includes: the intersection of the auxiliary line and the left lung mask edge image includes: a first set of intersections and a second set of intersections; and determining the intersection with the smaller / smallest abscissa among the first set of intersections and the second set of intersections as the auxiliary point corresponding to the lung mask edge image.

[0114] For example, in an embodiment of this disclosure, the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle is... C1Adding / subtracting the aforementioned y-direction increment ∆y yields the corresponding auxiliary line (y) parallel to the x-direction. C1 + / - ∆ y); the auxiliary line (y C1 The intersection of the auxiliary line (+ / - ∆ y) with the edge image of the left lung mask is determined as the auxiliary point C2' corresponding to the edge image of the lung mask. Specifically, the intersection of the auxiliary line with the edge image of the left lung mask includes: a first set of intersections and a second set of intersections; the intersection with the smaller / smallest x-coordinate among the first set of intersections and the second set of intersections is determined as the auxiliary point C2' corresponding to the edge image of the lung mask.

[0115] Specifically, the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle is... C1 When adding the set increment ∆y in the y-direction, the set increment ∆y is configured to be negative; or, the ordinate y of the coordinate point C1(x, y) of the right diaphragm angle is set to... C1 When subtracting the set increment ∆y in the y-direction, the set increment ∆y is configured to be a positive value.

[0116] Further, in embodiments of this disclosure, a corresponding second straight line Line2 is determined based on the left lung apex A2 and the left costophrenic angle B2; the method for determining the corresponding second straight line Line2 based on the left lung apex A2 and the left costophrenic angle B2 includes: based on the left lung apex A2 (x A2 , y A2 ) and the left costophrenic angle point B2 (x B2 , y B2 Determine the fourth coefficient a2, the fifth coefficient b2, and the sixth coefficient c2 corresponding to the second line Line2; based on the fourth coefficient a2, the fifth coefficient b2, and the sixth coefficient c2, determine the second line Line2.

[0117] Furthermore, before calculating multiple second distances from multiple second pixels to the second straight line on the left edge line A2B2 (the left heart border line closer to the heart) of the left lung mask edge image from the left lung apex A2 to the ischiocostal angle point B2, the left edge line A2B2 of the left lung mask edge image is determined based on the left lung apex A2 to the ischiocostal angle point B2. The method for determining this method includes: taking the left lung apex A2 as the starting point, and along the left lung mask edge line of the left lung mask edge image, calculating the distances from multiple second pixels to the second straight line. The lengths of the third and fourth edge lines from the left lung apex A2 to the left costophrenic angle B2 are calculated. The third and fourth edge lines are located on opposite sides of the second straight line Line2. The longest edge line between the lengths of the first and second edge lines is designated as the left edge line A2B2 of the right lung mask edge image.

[0118] For example, in an embodiment of this disclosure, calculating multiple second distances from multiple second pixels on the left edge line A1B1 (the left heart border line closer to the heart) of the right lung mask edge image from the left lung apex A2 to the ischiocostal angle B2 to the second straight line includes: taking the left lung apex A2 as the starting / ending point and the ischiocostal angle B2 as the ending / starting point, and sequentially calculating multiple second distances from multiple second pixels to the second straight line Line2 along the left edge line A1B1 of the left lung mask edge image. Furthermore, the second pixel corresponding to the largest distance among the multiple second distances is configured as the right cardiodiaphragm angle C2, and the mask edge line segment corresponding to the right lung mask edge image between the left cardiodiaphragm angle C2 and the ischiocostal angle B2 is configured and positioned as the left diaphragm B2C2.

[0119] In embodiments of this disclosure, the method for optimizing the localization of the abnormal right diaphragm sequence using the normal right diaphragm sequence and the normal left diaphragm sequence includes: optimizing the localization of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence of the same second X-ray two-dimensional chest image using the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence, to obtain the localized optimized right cardiophrenic angle corresponding to the second X-ray two-dimensional chest image; and based on the localized optimized right cardiophrenic angle, the right costophrenic angle point corresponding to the second X-ray two-dimensional chest image, and the right lung mask edge in the right lung mask edge image, locating and optimizing the corresponding right diaphragm (right lung diaphragm).

[0120] In embodiments of this disclosure, the method for optimizing the localization of the abnormal right diaphragm sequence using the normal right diaphragm sequence and the normal left diaphragm sequence includes: optimizing the localization of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence of the same first X-ray two-dimensional chest image using the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence, to obtain the optimized left cardiophrenic angle corresponding to the first X-ray two-dimensional chest image; and optimizing the localization of the corresponding left diaphragm (left lung diaphragm) based on the optimized left cardiophrenic angle, the left costophrenic angle point corresponding to the first X-ray two-dimensional chest image, and the left lung mask edge in the left lung mask edge image.

[0121] In the embodiments of this disclosure, before optimizing the localization of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence within the same first X-ray two-dimensional chest image using the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence, the right diaphragm corresponding to the same first X-ray two-dimensional chest image is a normal right diaphragm. Similarly, before optimizing the localization of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence within the same second X-ray two-dimensional chest image using the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence, the left diaphragm corresponding to the same second X-ray two-dimensional chest image is a normal left diaphragm.

[0122] In embodiments of this disclosure, the method of optimizing the localization of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence within the same second X-ray two-dimensional chest image by utilizing the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence to obtain the localized optimized right cardiophrenic angle corresponding to the second X-ray two-dimensional chest image includes: determining standard X-ray two-dimensional chest images corresponding to the normal left diaphragm and normal right diaphragm in the dynamic multi-image X-ray two-dimensional chest images; and configuring the normal right cardiophrenic angle corresponding to the normal right diaphragm in the standard X-ray two-dimensional chest image to the same second X-ray two-dimensional chest image. The initial right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence is calculated; the second distance in the y-direction between the normal left cardiophrenic angle corresponding to the normal left diaphragm in the standard X-ray two-dimensional chest image and the normal left cardiophrenic angle corresponding to the normal left diaphragm in the second X-ray two-dimensional chest image is calculated; the initial right cardiophrenic angle is adjusted using the second distance in the y-direction to obtain the adjusted right cardiophrenic angle; based on the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image, the abnormal right cardiophrenic angle is optimized for localization to obtain the optimized right cardiophrenic angle corresponding to the second X-ray two-dimensional chest image.

[0123] In embodiments of this disclosure, the method of optimizing the localization of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence within the same first X-ray two-dimensional chest image by utilizing the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence, to obtain the localized optimized left cardiophrenic angle corresponding to the first X-ray two-dimensional chest image, includes: determining standard X-ray two-dimensional chest images corresponding to the normal right diaphragm and normal left diaphragm in the dynamic multi-image X-ray two-dimensional chest images; and configuring the normal left cardiophrenic angle corresponding to the normal left diaphragm in the standard X-ray two-dimensional chest image onto the same first X-ray two-dimensional chest image. The initial left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence is calculated; the first distance in the y-direction between the normal right cardiophrenic angle corresponding to the normal right diaphragm in the standard X-ray two-dimensional chest image and the normal right cardiophrenic angle corresponding to the normal right diaphragm in the first X-ray two-dimensional chest image is calculated; the initial left cardiophrenic angle is adjusted using the first distance in the y-direction to obtain the adjusted left cardiophrenic angle; based on the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image, the abnormal left cardiophrenic angle is optimized for localization to obtain the optimized left cardiophrenic angle corresponding to the second X-ray two-dimensional chest image.

[0124] In an embodiment of this disclosure, the method of adjusting the initial right diaphragm angle using the second distance in the y-direction to obtain the adjusted right diaphragm angle includes: adjusting the y-direction coordinate point of the initial right diaphragm angle using the second distance in the y-direction to obtain the adjusted right diaphragm angle.

[0125] In an embodiment of this disclosure, the method of adjusting the y-direction coordinate point of the initialized right diaphragm angle using the second distance in the y-direction to obtain the adjusted right diaphragm angle includes: if the second distance in the y-direction is greater than or equal to 0, then the y-direction coordinate point of the initialized right diaphragm angle is added to the second distance in the y-direction to obtain the adjusted right diaphragm angle; wherein, the x-direction coordinate point corresponding to the adjusted right diaphragm angle remains unchanged.

[0126] In an embodiment of this disclosure, the method for optimizing the location of the abnormal right cardiophrenic angle based on the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second two-dimensional chest X-ray image includes: configuring the intersection point of the second straight line parallel to the x-direction corresponding to the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second two-dimensional chest X-ray image as the optimized right cardiophrenic angle.

[0127] In an embodiment of this disclosure, the method of configuring the focal point of the second straight line parallel to the x-direction corresponding to the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image as the optimized right cardiophrenic angle includes: drawing a second straight line parallel to the x-direction using the y-direction coordinate point corresponding to the adjusted right cardiophrenic angle; and configuring the intersection point with the largest x-direction coordinate point among the intersection points of the second straight line and the right lung mask edge in the right lung mask edge image corresponding to the second X-ray two-dimensional chest image as the optimized right cardiophrenic angle.

[0128] In an embodiment of this disclosure, the method for determining the standard two-dimensional chest images corresponding to the normal left diaphragm and the normal right diaphragm in the dynamic multi-image two-dimensional chest X-ray images includes: acquiring a second time corresponding to the second two-dimensional chest image; and determining the two-dimensional chest image corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multi-image two-dimensional chest X-ray images closest to the second time as the standard two-dimensional chest image.

[0129] In an embodiment of this disclosure, the method of adjusting the initial left diaphragm angle using the first distance in the y-direction to obtain the adjusted left diaphragm angle includes: adjusting the y-direction coordinate point of the initial left diaphragm angle using the first distance in the y-direction to obtain the adjusted left diaphragm angle.

[0130] In an embodiment of this disclosure, the method of adjusting the y-direction coordinate point of the initialized left diaphragm angle using the first distance in the y-direction to obtain the adjusted left diaphragm angle includes: if the first distance in the y-direction is greater than or equal to 0, then the y-direction coordinate point of the initialized left diaphragm angle is added to the first distance in the y-direction to obtain the adjusted left diaphragm angle; wherein, the x-direction coordinate point corresponding to the adjusted left diaphragm angle remains unchanged.

[0131] In an embodiment of this disclosure, the method for optimizing the location of the abnormal left cardiophrenic angle based on the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first two-dimensional chest X-ray image includes: configuring the intersection point of the first straight line parallel to the x-direction corresponding to the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first two-dimensional chest X-ray image as the optimized left cardiophrenic angle.

[0132] In an embodiment of this disclosure, the method of configuring the focal point of the first straight line parallel to the x-direction corresponding to the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image as the optimized left cardiophrenic angle includes: drawing a first straight line parallel to the x-direction using the y-direction coordinate point corresponding to the adjusted left cardiophrenic angle; and configuring the intersection point with the smallest x-direction coordinate point among the intersection points of the first straight line and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image as the optimized left cardiophrenic angle.

[0133] In an embodiment of this disclosure, the method for determining the standard two-dimensional chest images corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multi-image two-dimensional chest X-ray images includes: acquiring a first moment corresponding to the first two-dimensional chest image; and determining the two-dimensional chest image corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multi-image two-dimensional chest X-ray images closest to the first moment as the standard two-dimensional chest image.

[0134] In embodiments of this disclosure, the method for locating and optimizing the corresponding right diaphragm based on the optimized right cardiophrenic angle, the right costophrenic angle point corresponding to the second two-dimensional chest X-ray image, and the right lung mask edge in the right lung mask edge image includes: configuring the line segment of the right lung mask edge image between the optimized right cardiophrenic angle and the right costophrenic angle point corresponding to the second two-dimensional chest X-ray image as the optimized right diaphragm.

[0135] In embodiments of this disclosure, the method for locating and optimizing the corresponding left diaphragm based on the optimized left cardiophrenic angle, the left costophrenic angle point corresponding to the first two-dimensional chest X-ray image, and the left lung mask edge in the left lung mask edge image includes: configuring the line segment of the left lung mask edge in the lung mask edge image between the optimized left cardiophrenic angle and the left costophrenic angle point corresponding to the first two-dimensional chest X-ray image as the optimized left diaphragm.

[0136] In embodiments of this disclosure, the right cardiophrenic angle corresponding to each abnormal right diaphragm is obtained after localization optimization; the localization of each abnormal diaphragm is optimized based on the right cardiophrenic angle, right costophrenic angle point, and right lung mask edge image corresponding to each abnormal right diaphragm; and / or, the left cardiophrenic angle corresponding to each abnormal left diaphragm is obtained after localization optimization; the localization of each abnormal left diaphragm is optimized based on the left cardiophrenic angle, left costophrenic angle point, and left lung mask edge image corresponding to each abnormal left diaphragm.

[0137] In embodiments of this disclosure, a method for optimizing the localization of each abnormal right diaphragm based on the optimized right cardiophrenic angle, right costophrenic angle, and right lung mask edge image corresponding to each abnormal right diaphragm includes: configuring the line segment between the optimized right cardiophrenic angle and the right costophrenic angle point in the right lung mask edge image as the optimized right diaphragm.

[0138] Similarly, in the embodiments of this disclosure, the method for optimizing the positioning of each abnormal left diaphragm based on the optimized left cardiophrenic angle, left costophrenic angle point, and left lung mask edge image corresponding to each abnormal left diaphragm includes: configuring the line segment between the optimized left cardiophrenic angle and the left costophrenic angle point corresponding to each abnormal left diaphragm and the left lung mask edge in the left lung mask edge image as the optimized left diaphragm.

[0139] In embodiments of this disclosure, the step of matching the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: calculating the plurality of cardiac edge distance differences between each of the plurality of first cardiac edge distances and the plurality of second cardiac edge distances; matching the lung airflow and blood flow mixed image corresponding to the first cardiac edge distance with the smallest difference among the plurality of cardiac edge distances with the lung blood flow image corresponding to the second cardiac edge distance to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

[0140] In embodiments of this disclosure, the method further includes: determining one or more of the following lung ventilations based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence, according to the corresponding matching relationship: dynamic left lung ventilation, dynamic right lung ventilation, and dynamic lung ventilation.

[0141] In embodiments of this disclosure, determining one or more of the following lung ventilation volumes—dynamic left lung ventilation, dynamic right lung ventilation, and dynamic lung ventilation (bi-lung ventilation)—based on the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: registering the left lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence with its matching left lung blood flow image to obtain a left lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the left lung airflow and blood flow mixed registration image sequence and its matching left lung blood flow image to determine the dynamic left lung ventilation; and / or The right lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence is registered with its matching right lung blood flow image to obtain a right lung airflow and blood flow mixed registration image sequence; pixel-level subtraction processing is performed on the right lung airflow and blood flow mixed registration image sequence and its matching right lung blood flow image to determine the dynamic right lung ventilation; and / or, the lung airflow and blood flow mixed image sequence is registered with its matching lung blood flow image to obtain a lung airflow and blood flow mixed registration image sequence; pixel-level subtraction processing is performed on the lung airflow and blood flow mixed registration image sequence and its matching lung blood flow image to determine the dynamic lung ventilation.

[0142] In embodiments of this disclosure, the method further includes: acquiring the volume of the maximum exhaled volume in the first second during the breathing process and the dynamic lung ventilation determined by the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence based on the corresponding matching relationship; training the preset neural network using the lung ventilation and the corresponding volume of the maximum exhaled volume in the first second to construct a relationship model between the lung ventilation and the volume of the maximum exhaled volume in the first second.

[0143] In embodiments of this disclosure, the step of training the preset neural network using the dynamic lung ventilation and the corresponding volume of the maximum exhaled volume in the first second to construct a relationship model between the lung ventilation and the volume of the maximum exhaled volume in the first second includes: configuring the dynamic lung ventilation and the corresponding volume of the maximum exhaled volume in the first second as feature vectors and their corresponding labels; and training the preset neural network based on the feature vectors and their corresponding labels to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhaled volume in the first second.

[0144] In embodiments of this disclosure, the preset neural network includes: an input layer, an intermediate layer connected to the input layer, and an output layer connected to the intermediate layer; for example, the preset neural network includes: a normalization processing layer corresponding to the input layer, an intermediate layer connected to the normalization processing layer including: multiple fully connected layers and a dropout layer; and an output layer connected to the intermediate layer including: a linearly connected layer.

[0145] The executing entity of the dynamic X-ray image processing method can be a dynamic X-ray image processing device or system. For example, the dynamic X-ray image processing method can be executed by a terminal device, 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 dynamic X-ray image processing method can be implemented by a processor calling computer-readable instructions stored in memory.

[0146] Those skilled in the art will understand that in the above-described dynamic X-ray image processing method of the specific implementation, the order in which each step is 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.

[0147] According to one aspect of this disclosure, a dynamic X-ray image processing system is provided, comprising: an acquisition unit, configured to acquire multiple first cardiac border distances of a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac border distances of a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during breath-holding; a matching unit, configured to match the multiple first cardiac border distances and the multiple second cardiac border distances to determine a corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence; or, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the above-described dynamic X-ray image processing method; or, comprising: a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by the processor, implement the above-described dynamic X-ray image processing method; or, comprising: a computer program product, wherein the computer program product sets computer program instructions, wherein the computer program instructions, when executed by the processor, implement the above-described dynamic X-ray image processing method.

[0148] According to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: an acquisition unit, configured to acquire multiple first cardiac distances of a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac distances of a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple times during breath-holding; a matching unit, configured to match the multiple first cardiac distances and the multiple second cardiac distances to determine a corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence; or, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the above-described dynamic X-ray image processing method; or, according to one aspect of this disclosure, a dynamic X-ray camera is provided, comprising: a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the above-described dynamic X-ray image processing method; or, comprising: a computer program product, wherein the computer program product sets computer program instructions, wherein the computer program instructions, when executed by a processor, implement the above-described dynamic X-ray image processing method; or, comprising: the dynamic X-ray image processing system as described above.

[0149] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to execute the dynamic X-ray image processing method described in the above method embodiments. The specific implementation can be referred to the description of the dynamic X-ray image processing method embodiments above, which will not be repeated here for the sake of brevity.

[0150] 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 embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A dynamic X-ray image processing method, characterized in that, include: This method acquires multiple first cardiac border distances from a sequence of mixed lung airflow and blood flow images corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac border distances from a sequence of lung blood flow images corresponding to multiple two-dimensional chest X-ray images at multiple time points during breath-holding. Determining the multiple first cardiac border distances includes: determining the corresponding right and left cardiac border points based on the right and left lung mask edge images of each mixed lung airflow and blood flow image in the sequence; calculating the horizontal distance between the right and left cardiac border points corresponding to each mixed lung airflow and blood flow image to determine the multiple first cardiac border distances; determining the multiple second cardiac border distances includes: determining the corresponding right and left cardiac border points based on the right and left lung mask edge images of each lung blood flow image in the sequence; calculating the horizontal distance between the right and left cardiac border points corresponding to each lung blood flow image to determine the multiple second cardiac border distances. The plurality of first cardiac edge distances and the plurality of second cardiac edge distances are matched to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

2. The dynamic X-ray image processing method according to claim 1, characterized in that, Determining the right lung mask edge image and left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence includes: acquiring multiple first right lung mask registration images corresponding to multiple first right lung X-ray registration images during the determination of the lung airflow and blood flow mixed image sequence, and multiple first left lung mask registration images corresponding to multiple first left lung X-ray registration images during the determination of the lung airflow and blood flow mixed image sequence; Edge detection is performed on the plurality of first right lung mask registration images and the plurality of first left lung mask registration images respectively to obtain the right lung mask edge image and the left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence.

3. The dynamic X-ray image processing method according to claim 1, characterized in that, Determining the right lung mask edge image and left lung mask edge image of each lung airflow-bloodflow mixed image in the lung airflow-bloodflow mixed image sequence includes: Acquire multiple first right lung mask images corresponding to multiple first right lung X-ray images during the process of determining the lung airflow and blood flow mixed image sequence, and multiple first left lung mask images corresponding to multiple first left lung X-ray images during the process of determining the lung airflow and blood flow mixed image sequence; Edge detection is performed on the plurality of first right lung mask images and the plurality of first left lung mask images respectively to obtain the right lung mask edge image and the left lung mask edge image of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence.

4. The dynamic X-ray image processing method according to any one of claims 1-3, characterized in that, Determining the right lung mask edge image and left lung mask edge image of each lung blood flow image in the lung blood flow image sequence includes: Acquire multiple second right lung mask registration images corresponding to multiple second right lung X-ray registration images during the determination of the lung blood flow image sequence, and multiple second left lung mask registration images corresponding to multiple second left lung X-ray registration images during the determination of the lung blood flow image sequence; Edge detection is performed on the multiple second right lung mask registration images and the multiple second left lung mask registration images respectively to obtain the right lung mask edge image and the left lung mask edge image of each lung blood flow image in the lung blood flow image sequence.

5. The dynamic X-ray image processing method according to any one of claims 1-3, characterized in that, Determining the right lung mask edge image and left lung mask edge image of each lung blood flow image in the lung blood flow image sequence includes: Acquire multiple second right lung mask images and multiple second left lung mask images corresponding to the second fixed registration X-ray images of multiple second right lung X-ray images to be registered and multiple second left lung X-ray images to be registered during the process of determining the lung blood flow image sequence; Edge detection is performed on the multiple second right lung mask images and multiple second left lung mask images respectively to obtain the right lung mask edge image and the left lung mask edge image of each lung blood flow image in the lung blood flow image sequence.

6. The dynamic X-ray image processing method according to any one of claims 1-3, characterized in that, The step of matching the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: Calculate the differences between each of the plurality of first centripetal distances and the plurality of second centripetal distances; The lung airflow and blood flow mixed image corresponding to the first heart edge distance with the smallest difference among the multiple heart edge distances is matched with the lung blood flow image corresponding to the second heart edge distance to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

7. The dynamic X-ray image processing method according to claim 4, characterized in that, The step of matching the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: Calculate the differences between each of the plurality of first centripetal distances and the plurality of second centripetal distances; The lung airflow and blood flow mixed image corresponding to the first heart edge distance with the smallest difference among the multiple heart edge distances is matched with the lung blood flow image corresponding to the second heart edge distance to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

8. The dynamic X-ray image processing method according to claim 5, characterized in that, The step of matching the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence includes: Calculate the differences between each of the plurality of first centripetal distances and the plurality of second centripetal distances; The lung airflow and blood flow mixed image corresponding to the first heart edge distance with the smallest difference among the multiple heart edge distances is matched with the lung blood flow image corresponding to the second heart edge distance to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

9. The dynamic X-ray image processing method according to any one of claims 1-3, 7, and 8, characterized in that, Also includes: Based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence with the corresponding matching relationship, one or more lung ventilations among dynamic left lung ventilation, dynamic right lung ventilation and dynamic lung ventilation are determined.

10. The dynamic X-ray image processing method according to claim 4, characterized in that, Also includes: Based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence with the corresponding matching relationship, one or more lung ventilations among dynamic left lung ventilation, dynamic right lung ventilation and dynamic lung ventilation are determined.

11. The dynamic X-ray image processing method according to claim 5, characterized in that, Also includes: Based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence with the corresponding matching relationship, one or more lung ventilations among dynamic left lung ventilation, dynamic right lung ventilation and dynamic lung ventilation are determined.

12. The dynamic X-ray image processing method according to claim 6, characterized in that, Also includes: Based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence with the corresponding matching relationship, one or more lung ventilations among dynamic left lung ventilation, dynamic right lung ventilation and dynamic lung ventilation are determined.

13. The dynamic X-ray image processing method according to claim 9, characterized in that, Determining one or more of the following lung ventilation volumes: dynamic left lung ventilation, dynamic right lung ventilation, and dynamic lung ventilation, including: registering the left lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence with its matching left lung blood flow image to obtain a left lung airflow and blood flow mixed registration image sequence; and performing pixel-level subtraction processing on the left lung airflow and blood flow mixed registration image sequence and its matching left lung blood flow image to determine the dynamic left lung ventilation.

14. The dynamic X-ray image processing method according to any one of claims 10-12, characterized in that, Determining the dynamic left lung ventilation includes: registering the left lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence with its matching left lung blood flow image to obtain a left lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the left lung airflow and blood flow mixed registration image sequence and its matching left lung blood flow image to determine the dynamic left lung ventilation.

15. The dynamic X-ray image processing method according to claim 9, characterized in that, Determining dynamic right lung ventilation includes: registering the right lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence with its matching right lung blood flow image to obtain a right lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the right lung airflow and blood flow mixed registration image sequence and its matching right lung blood flow image to determine dynamic right lung ventilation.

16. The dynamic X-ray image processing method according to any one of claims 10-12, characterized in that, Determining dynamic right lung ventilation includes: registering the right lung airflow and blood flow mixed image sequence in the lung airflow and blood flow mixed image sequence with its matching right lung blood flow image to obtain a right lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the right lung airflow and blood flow mixed registration image sequence and its matching right lung blood flow image to determine dynamic right lung ventilation.

17. The dynamic X-ray image processing method according to claim 9, characterized in that, Determining dynamic lung ventilation includes: registering the lung airflow and blood flow mixed image sequence with its matching lung blood flow image to obtain a lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the lung airflow and blood flow mixed registration image sequence and its matching lung blood flow image to determine dynamic lung ventilation.

18. The dynamic X-ray image processing method according to any one of claims 10-12, characterized in that, Determining dynamic lung ventilation includes: registering the lung airflow and blood flow mixed image sequence with its matching lung blood flow image to obtain a lung airflow and blood flow mixed registration image sequence; performing pixel-level subtraction processing on the lung airflow and blood flow mixed registration image sequence and its matching lung blood flow image to determine dynamic lung ventilation.

19. The dynamic X-ray image processing method according to any one of claims 1-3, 7, 8, 10-13, 15, and 17, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

20. The dynamic X-ray image processing method according to claim 4, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

21. The dynamic X-ray image processing method according to claim 5, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

22. The dynamic X-ray image processing method according to claim 6, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

23. The dynamic X-ray image processing method according to claim 9, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

24. The dynamic X-ray image processing method according to claim 14, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

25. The dynamic X-ray image processing method according to claim 16, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

26. The dynamic X-ray image processing method according to claim 18, characterized in that, Also includes: Acquire the volume of the maximum exhaled air volume in the first second during the breathing process; Dynamic lung ventilation determined based on the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence according to the corresponding matching relationship; A preset neural network is trained using the dynamic lung ventilation and the corresponding volume of the maximum exhalation volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhalation volume in the first second.

27. The dynamic X-ray image processing method according to claim 19, characterized in that, The step of training a preset neural network using the dynamic lung ventilation and the corresponding volume of the maximum expiratory volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum expiratory volume in the first second includes: The dynamic lung ventilation and the corresponding volume of the maximum expiratory volume in the first second are configured as feature vectors and their corresponding labels, respectively. The preset neural network is trained based on the feature vector and its corresponding label to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhaled air volume in the first second.

28. The dynamic X-ray image processing method according to any one of claims 20-26, characterized in that, The step of training a preset neural network using the dynamic lung ventilation and the corresponding volume of the maximum expiratory volume in the first second to construct a relationship model between the dynamic lung ventilation and the volume of the maximum expiratory volume in the first second includes: The dynamic lung ventilation and the corresponding volume of the maximum expiratory volume in the first second are configured as feature vectors and their corresponding labels, respectively. The preset neural network is trained based on the feature vector and its corresponding label to construct a relationship model between the dynamic lung ventilation and the volume of the maximum exhaled air volume in the first second.

29. A dynamic X-ray image processing system, characterized in that, include: The acquisition unit is used to acquire multiple first cardiac border distances for a lung airflow and blood flow mixed image sequence corresponding to multiple dynamic two-dimensional chest X-ray images during respiration, and multiple second cardiac border distances for a lung blood flow image sequence corresponding to multiple two-dimensional chest X-ray images at multiple time points under breath-holding conditions. Determining the multiple first cardiac border distances includes: determining the corresponding right and left cardiac border points based on the right and left lung mask edge images of each lung airflow and blood flow mixed image in the lung airflow and blood flow mixed image sequence; calculating the horizontal distance between the right and left cardiac border points corresponding to each lung airflow and blood flow mixed image to determine the multiple first cardiac border distances; determining the multiple second cardiac border distances includes: determining the corresponding right and left cardiac border points based on the right and left lung mask edge images of each lung blood flow image in the lung blood flow image sequence; calculating the horizontal distance between the right and left cardiac border points corresponding to each lung blood flow image to determine the multiple second cardiac border distances. A matching unit is used to match the plurality of first cardiac edge distances and the plurality of second cardiac edge distances to determine the corresponding matching relationship between the lung airflow and blood flow mixed image sequence and the lung blood flow image sequence.

30. A dynamic X-ray image processing system, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the dynamic X-ray image processing method according to any one of claims 1 to 28.

31. A dynamic X-ray image processing system, characterized in that, include: A computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the dynamic X-ray image processing method according to any one of claims 1 to 28.

32. A dynamic X-ray image processing system, characterized in that, include: A computer program product; the computer program product is configured with computer program instructions that, when executed by a processor, implement the dynamic X-ray image processing method according to any one of claims 1 to 28.

33. A dynamic X-ray camera, characterized in that, include: The dynamic X-ray image processing system as described in any one of claims 29 to 32.

Images