Providing normalized medical images

Abstract

A normalized medical image 110' representing a region of interest 120 within a subject. 1..n The method provides a warped region of interest 120' for comparison with the region of interest 120 in the atlas image 130. 1..n A normalized medical image 110' having 1.. n The method also includes warping the medical image 110' to the 2D atlas image 130 to provide the normalized medical image 110' 1..n and / or outputting the normalized medical image 110' 1..n The warped region of interest 120' between 1..n The method includes outputting the magnitude of the change in

Description

[Technical field]

[0001] SUMMARY A computer-implemented method, computer program product, and system are disclosed that relate to providing a normalized medical image representative of a region of interest within a subject. [Background technology]

[0002] Clinical examinations often involve the acquisition of medical images of a subject. The images are acquired at different time points, i.e., as a time series of images. The images are used to identify changes in a region of interest over time and thereby evaluate the progression of the subject's medical condition. However, differences in the image acquisition techniques can hinder clinical examinations. For example, differences in the subject's posture, differences in the viewing angle of the medical imaging system, and differences in the amount of ionizing radiation used to acquire the images exacerbate the difficulty of identifying changes over time in the region of interest itself. Such differences can therefore reduce the diagnostic value of the images and lead to an incorrect diagnosis of the subject's condition.

[0003] In some clinical settings, it is possible to position a subject in an optimal position relative to an imaging system. In such settings, image-to-image variability resulting from different image acquisition techniques is relatively small. However, in other clinical settings, it may be impractical or impossible to position a subject in an optimal position. For example, in an intensive care setting, it is impractical to acquire images of a subject in a desired position or with the subject in a desired position relative to a medical imaging system. Summary of the Invention [Problem to be solved by the invention]

[0004] For example, acquiring diagnostic chest X-ray images in an intensive care setting to assess the progression of a pulmonary condition is a challenging task for radiologists. The immobility of the usually bedridden subject, the limited space to operate a mobile X-ray imaging system, and the bulky nature of such imaging systems are just some of the confounding factors that pose challenges for radiologists. The resulting X-ray images often suffer from poor quality as a result of suboptimal viewing, suboptimal viewpoint, limited X-ray dose, and subject posture limitations such as subject inhalation, arm position, and imperfect upright position. Thus, X-ray images acquired in an intensive care setting may be of significantly lower quality than images acquired during a standard X-ray chest examination. This makes the X-ray images difficult to interpret. Notably, it is difficult to assess long-term changes in the subject's condition because these confounding factors are not constant over time and vary from image to image. This may lead to radiologists interpreting such images unconsciously compensating for such differences, resulting in an incorrect diagnosis of the pulmonary condition.

[0005] Therefore, improvements are needed to make it easier to identify changes over time in medical images.

[0006] The US2007 / 003117A1 document discloses a technique for comparative image analysis and / or change detection using computer-aided detection and / or diagnosis "CAD" algorithms, which involves registering two or more images, comparing the images with each other to generate a change map, and detecting anomalies in the images based on the change map. [Means for solving the problem]

[0007] According to one aspect of the present disclosure, there is provided a computer-implemented method for providing a normalized medical image representative of a region of interest within a subject, the method comprising: receiving image data comprising a time series of 2D medical images including a region of interest within a subject; receiving an atlas image representative of the region of interest; For each medical image in the time series, warping the medical image to the atlas image to provide a normalized medical image having a warped region of interest for comparison with the region of interest in the atlas image; and the method further comprises outputting the normalized medical images and / or outputting a magnitude of change of the warped region of interest between the normalized medical images.

[0008] In the above method, a time series of medical images is warped into an atlas image, so that the shapes of the regions of interest become more similar in each normalized medical image, facilitating reliable comparison between regions of interest within images and enabling more reliable assessment of longitudinal changes in subjects.

[0009] Further aspects, features, and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments which proceeds with reference to the accompanying drawings. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a flow chart illustrating an example of a method for providing a normalized medical image representative of a region of interest within a subject according to some aspects of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram illustrating an example of a system 200 for providing a normalized medical image representative of a region of interest within a subject according to some aspects of the present disclosure. [Diagram 3] FIG. 3 illustrates an example of a lung atlas image 130 according to some aspects of the present disclosure. [Figure 4] FIG. 4 illustrates an example of a thorax atlas image 130 according to some aspects of the present disclosure. [Diagram 5] FIG. 5 illustrates an example of warping two 2D medical images 1101, 1102 in time series into an atlas image to provide respective normalized medical images 110'1, 110'2, according to some aspects of the present disclosure. [Figure 6]FIG. 6 illustrates an example of the results of applying a feature detector to a medical image 1101 to identify multiple landmarks in the medical image, according to some aspects of the present disclosure. [Figure 7] FIG. 7 illustrates an example of warping two 2D medical images 1101, 1102 in time series into an atlas image and adjusting the intensities of the medical images according to some aspects of the present disclosure. [Figure 8] FIG. 8 illustrates an example of warping two 2D medical images 1101, 1102 of a time series into an atlas image, adjusting the intensity of the medical images, and suppressing image features outside the lung region of interest, according to some aspects of the present disclosure. [Figure 9] FIG. 9 shows an example of a temporal sequence of 2D medical images 1101..n (top), a temporal sequence of corresponding normalized images 110'1..n in which the temporal sequence of 2D medical images 1101..n have been warped into an atlas image and their intensities adjusted to provide adjusted intensity values ​​(middle), and a temporal sequence of corresponding normalized images in which image features outside the lung region of interest have been suppressed (bottom), in accordance with some aspects of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] With reference to the following description and figures, examples of the present disclosure are provided. In the following description, for purposes of explanation, many specific details of some examples are set forth. References herein to "examples," "implementations," or similar terms mean that features, structures, or characteristics described in connection with an example are included in at least one of the examples. It is further understood that features described in connection with one example may also be used in other examples, and that not all features are necessarily duplicated in each example for the sake of brevity. For example, features described in connection with a computer-implemented method may be implemented in a corresponding manner in computer program products and systems.

[0012] In the following description, reference is made to a computer-implemented method involving providing a normalized medical image representative of a region of interest within a subject. In some examples, reference is made to the region of interest being the lungs of the subject. However, it is understood that this region of interest is merely an example and that the methods disclosed herein may alternatively be used to provide normalized medical images representative of other regions of interest in the subject.

[0013] It should be noted that the computer-implemented methods disclosed herein may be provided as a non-transitory computer-readable storage medium having computer-readable instructions stored thereon. The computer-readable instructions, when executed by at least one processor, cause the at least one processor to perform the method. That is, the computer-implemented methods may be implemented in a computer program product. The computer program product may be provided by dedicated hardware or dedicated hardware capable of executing software in association with appropriate software. When provided by a processor, the functionality of the method features may be provided by a single dedicated processor, a single shared processor, or multiple individual processors, some of which may be shared. For example, one or more functionality of the method features may be provided by a processor shared in a networked processing architecture, such as a client / server architecture, a peer-to-peer architecture, the Internet, or the cloud.

[0014] Explicit use of the terms "processor" or "controller" should not be construed as referring solely to hardware capable of executing software, but implicitly includes, but is not limited to, digital signal processor (DSP) hardware, read-only memory (ROM) for storing software, random access memory (RAM), non-volatile storage devices, and the like. Furthermore, embodiments of the present disclosure may take the form of a computer program product accessible from a computer usable or computer readable storage medium, the computer program product providing program code for use by or in connection with a computer or any instruction execution system. For purposes of this description, a computer usable or computer readable storage medium may be any apparatus that includes the storage, communication, propagation, or transport of a program for use by or in connection with an instruction execution system, apparatus, or device. Media include electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or propagation media. Examples of computer readable media include semiconductor or solid state memory, magnetic tape, removable computer disks, random access memory (RAM), read-only memory (ROM), rigid magnetic disks, and optical disks. Current examples of optical disks include compact disk-read only memory (CD-ROM), compact disk-read / write (CD-R / W), Blu-Ray, and DVD.

[0015] As previously mentioned, improvements are needed to facilitate identifying changes in medical images over time.

[0016] FIG 1 is a flow chart illustrating an example of a method for providing a normalized medical image representative of a region of interest in a subject, according to some aspects of the present disclosure. FIG 2 is a schematic diagram illustrating an example of a system 200 for providing a normalized medical image representative of a region of interest in a subject, according to some aspects of the present disclosure. Operations described in relation to the method illustrated in FIG 1 may also be performed in the system 200 illustrated in FIG 2, and vice versa. Referring to FIG 1, a normalized medical image 110' representative of a region of interest 120 in a subject is shown. 1..n A computer-implemented method for providing A time series of 2D medical images 110 including a region of interest 120 within a subject. 1..n receiving image data including the Receiving (S120) an atlas image 130 representing a region of interest 120; 110 medical images in a time series 1..n For comparison with the region of interest 120 in the atlas image 130, the warped region of interest 120' 1..n A normalized medical image 110' having 1.. n warping (S130) the medical image into an atlas image 130 to provide The method includes: 1..n and / or outputting the normalized medical image 110' 1..n The warped region of interest 120' between 1..n The method further includes outputting (S140b) a magnitude of the change in

[0017] In the above method, a time series of medical images are warped into an atlas image so that the shapes of the regions of interest become more similar in each of the normalized medical images, facilitating more reliable comparisons between regions of interest within images and allowing more reliable assessment of longitudinal changes in a subject's condition.

[0018] 1, in operation S110, image data is received. The image data includes a time series of 2D medical images 110 including a region of interest 120 within a subject. 1..nThe received 2D medical images form a time series in the sense that the images are acquired at different time points. The images may be acquired periodically, i.e. at regular intervals, or intermittently, i.e. at irregular intervals. A time series of 2D medical images is acquired over a period of time, such as minutes, hours, days, weeks, or longer. A time series of 2D medical images represents a so-called longitudinal study of a subject. In general, the region of interest represented in the images is any anatomical region. For example, the region of interest may be the lungs, the heart, the liver, the kidneys, etc. For example, the time series of 2D medical images 110 received in operation S110 may include a region of interest such as the lungs, the heart, the liver, the kidneys, etc. 1..n represents a subject's chest. For example, the time series of 2D medical images may represent daily images of the chest acquired as part of a longitudinal study of a subject to assess the progression of COVID-19 infection in the subject's lungs.

[0019] The time series of 2D medical images 110 received in operation S110 1..n The 2D medical image 110 is generally generated by any 2D medical imaging system. 2D medical images include X-ray images, ultrasound images, etc. The 2D X-ray image is generally generated by any projection X-ray imaging system. The 2D medical image 110 1..n Examples of current X-ray projection imaging systems capable of producing 2D images include the MobileDiagnost M50, a mobile X-ray imaging system, the DigitalDiagnost C90, a ceiling mounted X-ray imaging system, and the Azurion7, which includes a C-arm mounted source-detector arrangement, all available from Philips Healthcare of Best, The Netherlands. 2D ultrasound images are produced by any 2D ultrasound imaging system.

[0020] For example, the 2D medical image 110 received in operation S110 1..n5 includes X-ray images generated by a projection X-ray imaging system 220 shown in FIG. 2. The projection X-ray imaging system shown in FIG. 2 is a so-called mobile X-ray imaging system that is often used in intensive care settings to acquire images of subjects with limited mobility. The projection X-ray imaging system 220 shown in FIG. 2 includes an X-ray source 230 and a wirelessly coupled X-ray detector 240. The versatility of this type of X-ray imaging system facilitates imaging of subjects in complex settings where the subject's mobility is limited, such as the bedridden setting shown in FIG. 2. However, as mentioned above, it is difficult to assess the subject's condition from images acquired in such settings, given the subject's limited mobility (the subject cannot position himself / herself in an optimal or even repeatable posture for each imaging session). An example of the pose and image quality variability of images acquired from the bedridden setting shown in FIG. 2 is shown on the left side of FIG. 5. FIG. 5 illustrates an example of warping two 2D medical images 1101, 1102 in time series into an atlas image to provide respective normalized medical images 110'1, 110'2, according to some aspects of the present disclosure. The two 2D X-ray images 1101 and 1102 on the left side of FIG. 5 represent a subject's chest at two different time points. As will be appreciated, identifying changes in the subject's lung condition in these images is complicated by the subject's different postures and the different viewpoints of the X-ray imaging system relative to the subject. It should be appreciated that the setup shown in FIG. 2 is merely an example, and the principles disclosed herein are not limited to this type of imaging system or this type of setup.

[0021] Returning to FIG. 1, generally, a time series of 2D medical images 110 are received in operation S110. 1..n The time series of 2D medical images 110 may be received via any form of data communication, such as wired, optical, and wireless communication. As some examples, when wired or optical communication is used, the communication is via signals transmitted through electrical or optical cables, and when wireless communication is used, the communication is via, for example, RF or optical signals.1..n 2, from a 2D medical imaging system, such as the projection x-ray imaging system 220 shown in FIG. 2, from a 2D ultrasound imaging system, or from another source, such as a computer readable storage medium, the internet, or the cloud. 1..n can be received.

[0022] With continued reference to FIG. 1, in operation S120, an atlas image 130 representing the region of interest 120 is received. FIG. 3 illustrates an example of a lung field atlas image 130 according to some aspects of the present disclosure. FIG. 4 illustrates an example of a thorax atlas image 130 according to some aspects of the present disclosure. The atlas images 130 illustrated in FIG. 3 and FIG. 4 respectively indicate the probability of a structure belonging to the lung border and the probability of a structure belonging to the ribs by their intensity values. The atlas image 130 is received, for example, by one or more processors 210 illustrated in FIG. 2. The atlas image can be received from a database of atlas images. The atlas image may be selected from the database based on the similarity of the subject and a reference subject represented in the atlas image. For example, the atlas image is selected based on the similarity of the age, sex, and size of the subject and the reference subject. The atlas image serves as a reference image of the region of interest. The atlas image represents a preferred perspective of the region of interest within the reference subject. The atlas images are acquired while the reference subject maintains a preferred posture. For example, if the region of interest is the lung, the atlas image of the lung is a so-called dorso-ventral (PA) view of the chest, which represents the lungs, the bony thoracic cavity, the mediastinum, and the great vessels. Such atlas images are acquired with the subject standing upright and facing an upright X-ray detector, in a specified inspiration state, with the top surface of the X-ray detector at a specified distance above the shoulder joint, with the chin raised out of the image field, and with the shoulders rotated forward to move the scapula laterally out of the lung field, under specified operating settings of the X-ray imaging system (e.g., X-ray kVp energy, exposure time). More generally, the atlas images 130 are generated by combining the time series of 2D medical images 110. 1..nAtlas images represent preferred viewpoints of regions of interest for assessing pathology in 2D medical images. The use of such atlas images facilitates reliable and clinically meaningful comparisons between regions of interest in 2D medical images. For example, they may be used to determine clinically meaningful changes in a subject's lung volume, because these changes are observed from a clinically recognized viewpoint.

[0023] In one embodiment, the atlas image 130 is a time series of 2D medical images 110 1..n 1 represents a preferred perspective of a region of interest for assessing a medical condition in a subject. The method described with reference to FIG. 1 then includes selecting an atlas image 130 from the database of atlas images based on the medical condition. In this embodiment, the atlas image 130 may be selected from the database of atlas images further based on a similarity between the subject and a reference subject represented in the atlas image, as described in the embodiment above.

[0024] In another embodiment, the atlas image 130 is a time series of 2D medical images 110 1..n The atlas image 130 represents a preferred viewpoint of the region of interest for evaluating a pathology in the lung. The method described with reference to FIG. 1 then includes selecting an atlas image 130 from a database of atlas images based on a type of imaging examination performed on the region of interest. In this embodiment, if the region of interest is the lung, for example, the atlas image of the lung is a so-called postero-anterior (PA) view of the chest, which represents the lungs, the bony thoracic cavity, the mediastinum, and the great vessels. Such an atlas image is referred to as a "PA" chest view type of imaging examination. A plurality of atlas images are stored in the database, each representing a different preferred viewpoint of a different type of imaging examination. In this embodiment, the atlas image is selected from the atlas images in the database based on the type of imaging examination. In this embodiment, the atlas image 130 may be selected from the database of atlas images further based on a similarity between the subject and a reference subject represented in the atlas image, as described in the embodiment above.

[0025] Returning to FIG. 1, in operation S130, the time-series medical images 110 received in operation S110 are 1..n The medical image and the atlas image 130 are warped into the atlas image. The warping operation can be performed using a variety of known transformations. One example of a suitable transformation is an affine transformation. Other examples of suitable transformations include B-splines, thin plate splines, radial basis functions, etc. The warping operation S130 uses a number of corresponding landmarks 140 represented in both the medical image and the atlas image 130. 1..k The warping operation S130 may be performed using a neural network. If the warping is performed by a neural network, the neural network may or may not explicitly use such landmarks. 1..k are provided by anatomical features or fiducial markers. In some embodiments, anatomical features of bones (e.g., ribs, scapula, etc.) or organ contours (e.g., lung contour, diaphragm, heart shadow, etc.) serve as anatomical landmarks. Such features are identifiable in 2D medical images by their X-ray attenuation. Fiducial markers made from X-ray attenuating materials are also identifiable in medical images and may also serve as landmarks. Fiducial landmarks can be placed at known reference locations, either superficially or internally. In the latter case, fiducial markers may be implanted for use as surgical guides, etc. Implantable devices, such as pacemakers, may also serve as fiducial markers. Fiducial markers may also be provided by interventional devices inserted into the body.

[0026] 2D medical images in time series 110 1..n 140 landmarks in 1..k The landmarks and corresponding landmarks in the atlas images can be identified using a variety of techniques. In one embodiment, a feature detector is used to detect the landmarks in the time series of 2D medical images 110. 1..nThe method further comprises: identifying anatomical landmarks in the atlas image; mapping the identified landmarks to corresponding anatomical landmarks labeled in the atlas image; and mapping the identified landmarks to corresponding anatomical landmarks labeled in the atlas image. In this embodiment, the atlas image 130 includes a plurality of labeled anatomical landmarks. And, the method described with reference to FIG. 1 also includes: For each medical image 110 in the time series, a plurality of landmarks are identified in the medical image that correspond to the labeled anatomical landmarks. 1..n applying a feature detector to The mapping is determined using the identified corresponding landmarks.

[0027] In this embodiment, a time series of medical images 110 1..n The operation of applying a feature detector to the medical image 1101 may be performed using an edge detector, model-based segmentation, or a neural network, etc. For example, FIG. 6 illustrates an example of a result of applying a feature detector to a medical image 1101 to identify a plurality of landmarks in the medical image, according to some aspects of the present disclosure. The 2D medical image 1101 illustrated in FIG. 6 represents a chest and includes bony regions such as the ribs and spine, as well as the outline of the heart shadow and the lungs. In this example, the region of interest is the lungs, and the feature detector identifies landmarks 140 in the 2D medical image 1101, including outlines representing the right lung, the right side of the heart shadow, the right side of the diaphragm, the left lung, the left side of the heart shadow, and the left side of the diaphragm, respectively. 1..6 These landmarks correspond to landmarks in an atlas image, such as the lung atlas image shown in FIG. 3. The landmarks 140 identified in the 2D medical image 1101 1..6 are mapped to corresponding landmarks in the atlas image to warp the medical image 1101 to the atlas image in operation S130. As shown in Figure 6, one or more of the landmarks identified and used in the mapping operation represent a region of interest, which in this example is the lung.

[0028] The result of the warping operation S130 is a time sequence of medical images 110 1..nFor each of the atlas images 130, a warped region of interest 120' is generated for comparison with the region of interest 120 in the atlas image 130. 1..n A normalized medical image 110' having 1..n The objective of the present invention is to provide a normalized medical image 110'. 1..n , a warped region of interest 120' in each normalized medical image 110' 1 ..n is 1..n and the warped region of interest 120' for comparison with the region of interest 120 in the atlas image 130 in the sense that the difference in shape between the region of interest 120 in the atlas image 130 and the warped region of interest 120' is reduced. 1..n The warped regions of interest 120'1 and 120'2 are suitable for comparison with the region of interest 120 in the atlas image 130, and therefore can be compared with each other. The warping operation S130 thus reduces the difference in shape between the regions of interest 120'1 and 120'2, allowing for more reliable identification of changes in the regions of interest over time resulting from changes in the subject's condition. In other words, the warping operation S130 warps the normalized medical image 110' 1..n The warped region of interest 120' in 1..n The image on the right side of FIG. 5 shows a normalized medical image 110′ obtained in this way. 1..n As can be seen, the lung regions of interest 120'1 and 120'2 in these images have more similar shapes in the normalized medical images 110'1 and 110'2, which allows for more reliable identification of changes in the regions of interest over time due to progression of the lung condition.

[0029] Returning to FIG. 1, in operations S140a and S140b, the method comprises: 1..n and / or an operation S140a outputting the normalized medical image 110' 1..n The warped region of interest 120' between 1..n The normalized medical image 110' in operation S140a is output in operation S140b. 1..n The output of the normalized medical image 110' 1..nThe normalized medical image 110' may be displayed, printed, and saved in a variety of ways. The image may be displayed on a display device such as a monitor 250 shown in FIG. 5. For example, the normalized medical image 110' 1..n may be displayed side-by-side as shown in FIG. 5, as a time sequence or overlay images, or in other ways.

[0030] Outputting the magnitude of change in the warped region of interest in operation S140b can also be done in a variety of ways, such as displaying, printing, and saving the magnitude of change. In general, this change is expressed as 1..n 110' represents a change in intensity or a change in shape of the region of interest between any two of the images. The change may be determined, for example, between successive images. In some embodiments, a statistical analysis is applied to the warped region of interest to determine the magnitude of the change. In some embodiments, if the region of interest is the lung, the magnitude of the change may quantify the volume of a pneumothorax (i.e., the volume of the "collapsed lung"), the amount of pleural effusion (i.e., the amount of "fluid around the lung"), the amount of pulmonary edema (i.e., the amount of "fluid in the lung"), or a certain stage of pneumonia. Such changes may be calculated based on the normalized medical image 110' 1..n The change can be calculated by determining the change in intensity values ​​over time within the lungs in the atlas image or by comparing the image intensity to a normal reference value for the lungs in the atlas image. 1..n In this way, the contours of the lungs can be determined by assigning pixels within the lungs to either air or water based on their intensity values, and estimating the volumes of the respective air and water regions for each of the normalized medical images 110'1.

[0031] In some embodiments, outputting the magnitude of change of the warped region of interest in operation S140b includes outputting a numerical value of the magnitude (e.g., as a percentage) or outputting the magnitude of change in a graphical form. In one embodiment, the magnitude of change is calculated based on the normalized medical image 110' 1..nThe lung volume can be graphically represented as an overlay on one or more of the normalized medical images by representing increases in lung volume between successive images in green and decreases in lung volume between successive images in red.

[0032] By outputting a normalized medical image in operation S140a and / or outputting the magnitude of change in the warped regions of interest in operation S140b, the method facilitates a reviewing clinician to make more reliable comparisons between regions of interest in the images, thereby enabling the clinician to more accurately assess long-term changes in a subject's condition.

[0033] Various additional operations may also be performed in accordance with the method described above with reference to FIG.

[0034] In some embodiments, the method described with reference to FIG. Normalized medical image 110' 1..n based on the intensity at one or more locations in the atlas image 130 to provide adjusted intensity values ​​in the time series of medical images 110. 1..n or based on the intensity at one or more locations in the reference image. 1..n and / or Normalized medical image 110' 1..n 10. An image style transfer algorithm is used to provide adjusted intensity values ​​in each medical image 110 of the time series. 1..n This includes adjusting the intensity of the

[0035] Next, the normalized medical image 110' 1..n The warped region of interest 120' between 1..n The magnitude of the change in can be calculated and output based on the adjusted intensity values ​​in the normalized medical image.

[0036] The inventors have observed that not only is the evaluation of changes in medical images over time hindered by differences in the shape of the region of interest between images, but the evaluation of such changes may also be hindered by differences in the intensity scale of the images. More specifically, differences in intensity scale resulting from differences in the technique by which the time series of 2D medical images were acquired may hinder comparison. For example, the intensity at any point in a 2D X-ray image depends on the value of the X-ray energy "kVp" used to acquire the images, the exposure time, and the sensitivity of the X-ray detector. Because the images in the time series are acquired over a period of time, the images in the time series may have been generated by X-ray imaging systems with different settings, and indeed different X-ray imaging systems. In a computed tomography image, a Hounsfield unit value can be assigned to each voxel, but in a 2D X-ray image, there is no absolute attenuation scale for the corresponding pixel intensity value. Normalized medical image 110' 1..n based on the intensity at one or more locations in the atlas image 130 to provide adjusted intensity values ​​in the time series of medical images 110. 1..n or based on the intensity at one or more locations in the reference image. 1..n By adjusting the intensities of the atlas images 130, image-to-image variability resulting from differences in the technique by which the 2D medical images were acquired is further reduced. 1..n The operation of adjusting the intensity of the atlas image 130 produces a normalized medical image 110' that is the same as the intensity value at one or more locations in the atlas image 130. 1..n Similarly, the time series of medical images 110 can provide adjusted intensity values ​​at one or more corresponding positions in the image. 1..n Each medical image 110 in the time series is imaged based on the intensity at one or more locations in the 1..n The operation of adjusting the intensity of a time series of medical images 110 1..n The normalized medical image 110' has intensity values ​​at one or more locations in 1..nSimilarly, each medical image 110 in the time series can be adjusted based on the intensity at one or more locations in the reference image. 1..n The operation of adjusting the intensity of the medical image 110' produces a normalized medical image 110' that is the same as the intensity value at one or more locations in the reference image. 1..n The adjusted intensity values ​​at the corresponding one or more positions in the image may be provided.

[0037] Techniques such as windowing and histogram normalization can be used to normalize the intensity values ​​according to this embodiment. The location in the atlas image 130 can be defined manually or automatically. For example, if the region of interest is the lung, the location can be defined within the lung field, within the mediastinum, etc. The location can be predefined in the atlas image or based on user input provided from a user input device in combination with the displayed image. This embodiment is also described with reference to FIG. 7. FIG. 7 illustrates an example of warping two 2D medical images 1101, 1102 in time series into an atlas image and adjusting the intensities of the medical images according to some aspects of the present disclosure. The intensity of the image on the right side of FIG. 7 has been adjusted in the manner described above to facilitate more reliable identification of changes in the region of interest between the images.

[0038] Alternatively or additionally, an image style transfer algorithm may be used to generate the normalized medical image 110' 1..n It is also possible to provide adjusted intensity values ​​in . For this purpose, various image style transfer transformations are known. These are for example based on Laplace pyramids or (convolutional) neural networks. An example of an image style transfer algorithm is disclosed in International Patent Publication WO 2013 / 042018 A1. In this document, a technique is disclosed for transforming a slave image, which involves generating a color or grayscale transformation based on a master image and a slave image. This transformation is used to optically match the slave image to the master image. Using this technique, a normalized medical image 110' 1..nThe time series of medical images 110 are sorted so that the adjusted intensity values ​​in have a similar appearance or style. 1..n The intensity of the image can be adjusted. 1..n The slave images are used to generate atlas images and time-series medical images. 1..n The techniques disclosed in this document can be applied by using either the above or another reference image as the master image.

[0039] In a related embodiment, each medical image 110 in the time sequence is imaged based on intensity at one or more locations in the atlas image 130. 1..n The operation to adjust the strength of Calculating a mean intensity value within a portion of the atlas image 130; The average intensity value is used to compute the mean intensity for each medical image 110 in the time series. 1..n and normalizing the intensity values ​​in the

[0040] In this embodiment, each medical image 110 in the time sequence 1..n The operation of normalizing the intensity values ​​in each medical image 110 in the time series using the average intensity value is 1..n , to the average intensity value in a portion of the atlas image 130. 1..n The portion of the atlas image 130 used to normalize the intensity values ​​in the time series of 2D medical images 110 1..n A portion of the atlas image is selected over a period of time where the image intensity is expected to be time-invariant. For example, if the region of interest is the lung, the selected portion of the atlas image corresponds to a portion of the spine, since the attenuation of the spine is expected to be constant over time. Alternatively, if the region of interest is the lung, the selected portion may correspond to a portion of the time series of 2D medical images 110. 1..n1 corresponds to a portion of the lung in the atlas image 130 that is expected to be disease-free in each medical image 110. For example, if the condition of the subject under examination is pulmonary edema, then the collection of fluid over time would be expected to result in a change in image intensity over time in the lower portion of the lung, while the upper portion of the lung is expected to remain disease-free and therefore have a stable image intensity. In this case, the upper portion of the lung in the atlas image 130 would be 1..n It can be used as part of the atlas image 130 used to normalize the intensity values ​​in

[0041] In an embodiment where the region of interest is the lung, these operations are performed by identifying a portion of the lung in the atlas image. The portion of the lung may be identified automatically or based on user input received via a user input device in combination with a display device. The portion of the atlas image may represent a combination of air within the lung and the ribs surrounding the lung. An average intensity of pixel values ​​of this portion of the atlas image is then calculated. This average is then used to generate a time series of medical images 110. 1..n 5, this may include, for example, identifying a disease-free corresponding portion of the lung (e.g., toward the top of the lung in the medical image 1101), calculating the average of the intensity values ​​in that corresponding disease-free portion, calculating a scaling factor as the ratio of the average intensity value in the disease-free region of the medical image 1101 to the average intensity value of the portion of the lung in the atlas image, and scaling the image intensity values ​​in the medical image 1101 using the scaling factor to provide adjusted intensity values ​​in the normalized medical image 110'1. These operations may then be applied to other medical images 110 in the time series. 1..n The process is repeated for each medical image 110 in the time series using the portion of the lung in the atlas image. 1..n To normalize, the medical images are scaled to a common reference intensity, facilitating more reliable comparisons between image intensities in different parts of the image.

[0042] Additional portions of the atlas image may also be used to perform the intensity normalization described above. For example, a second region of interest may be identified in the mediastinum or bone region of the atlas image and used to perform the intensity normalization. 1..n Normalizing the intensities within facilitates more accurate mapping of intensity values, resulting in more reliable identification of changes in regions of interest in the image.

[0043] In this embodiment, the normalized medical image 110' 1..n The quality metric value may also be calculated and output for the adjusted intensity values ​​in the atlas image 110'. 1..n The quality metric can be calculated based on a statistic of image intensity values ​​within a corresponding portion of the atlas image, or based on the quality of the mapping between the landmarks in operation S130. If the variance of image intensity values ​​in a portion of the atlas image is high, the value of the quality metric will be relatively low, and vice versa. Outputting the value of the quality metric allows a reviewing clinician to reassure the accuracy of the method.

[0044] In one embodiment, the operation S130 of warping the medical image to the atlas image 130 includes: 1..n In this embodiment, the adjustment of the intensities of the medical images is performed according to the above embodiment. Thus, the adjustment is performed based on the intensities at one or more locations in the atlas image 130, prior to the adjustment of the intensities of the time series of medical images 110. 1..n The normalized medical image 110' may be based on the intensity at one or more locations in the atlas image, or based on the intensity at one or more locations in the reference image, or using an image style transfer algorithm. As explained above with reference to FIG. 5, warping has the effect of making the warped regions of interest have a more similar shape. Therefore, warping each medical image to the atlas image before adjusting the intensities provides a more reliable basis for adjusting the intensity values. Thus, the normalized medical image 110' 1..nThe reliability of the adjusted intensity values ​​in the atlas image is improved. In contrast, if the medical image was normalized before warping, the adjusted intensity values ​​do not take into account the adjustment of pixel intensity values ​​provided by the warp. For example, if normalization is provided based on the lung region of the atlas image, the normalization should be performed on the warped image since the warped lungs have a comparable shape. As a result, the image intensity values ​​in the lungs more accurately represent the warped shape of the lungs.

[0045] We also consider the normalized medical image 110' following the warping operation S130. 1..n We have observed that some regions outside the region of interest of the CT scan may be warped into unnatural shapes, which may be confusing to a reviewing physician. Normalized medical image 110' 1..n Region of interest within 120' 1..n This involves suppressing one or more extraneous image features.

[0046] Region of interest 120' 1..n Suppressing one or more image features outside the lung region of interest avoids presenting confounding information to the reviewing clinician. This example is described with reference to FIG. 8, which illustrates an example of warping two 2D medical images 1101, 1102 in a time series into an atlas image, adjusting the intensity of the medical images, and suppressing image features outside the lung region of interest, according to some aspects of the present disclosure. In the image on the right of FIG. 8, a normalized medical image 110' 1..n8, image features outside the lung region of interest are suppressed by mapping their pixel values ​​to a black level pixel intensity value. However, these features can be suppressed in different ways. For example, their pixel values ​​can be mapped to a pixel intensity value different from the black level pixel intensity value, or they can be gradually adjusted to a predetermined value to "feather-out" the region of interest. This suppression of image features outside the region of interest is performed using an atlas image. For example, in this embodiment, the method described with reference to FIG. 1 also includes: Identifying a region of interest 120 in an atlas image 130; The outline of the region of interest 120 from the atlas image 130 is then added to the normalized medical image 110' 1..n and mapping each of Region of interest 120' 1..n A normalized medical image 110' outside the mapped contour to suppress one or more image features outside the normalized medical image 110' 1..n and adjusting image intensity values ​​within the image.

[0047] In this embodiment, various examples of regions of interest are predefined in the atlas image to define the regions of interest 120' 1..n Alternatively, the atlas image can be segmented to define the region of interest. In this embodiment, the contour from the atlas image is used to define the region of interest 120' 1..n The reliable contour is used to suppress one or more extraneous image features. In operation S130, the normalized medical image 110' 1..n The contours are reliable because the,are warped to the atlas image using landmarks in the,atlas image, and therefore the shape of the region of interest in the,normalized image is similar to the shape of the region of interest in the,atlas image.

[0048] As a further example, FIG. 9 illustrates a time series of 2D medical images 110 in accordance with some aspects of the present disclosure. 1..n (Top) A time series of 110 2D medical images.1..n is warped to the atlas image and its intensity adjusted to provide adjusted intensity values, 1..n 9 shows an example of a temporal sequence of a pulmonary pulmonary stenosis image 110 (center) and a corresponding temporal sequence of normalized images (bottom) in which image features outside the lung region of interest are suppressed. FIG. 9 illustrates the above operation on more images than the two images shown in FIGS. 5, 7, and 8, and also illustrates a 2D medical image 110 from a longitudinal study of a subject. 1..n and the amount of variation that can be observed in the normalized medical image 110'1 provided by the method described herein. ..n The advantages of the above will be further shown.

[0049] In another embodiment, the method described with reference to FIG. Normalized medical image 110' 1..n Region of interest within 120' 1..n performing a statistical analysis of image intensity values ​​in Normalized medical image 110' 1..n The warped region of interest 120' between 1..n Outputting the magnitude of the change in (S140b) Normalized medical image 110' 1..n and outputting the results of the statistical analysis of the data.

[0050] Normalized medical image 110' 1..n Region of interest within 120' 1..n Various statistical analysis methods can be applied to the image intensity values ​​in. One exemplary implementation of such statistical analysis is shown in FIG. 1..n In this example, the normalized medical image 110' 1..n Statistics are generated for the patches in each of the normalized medical images 110'. This involves determining the mean and standard deviation of the pixel values ​​within the patch. For example, a Gaussian distribution is assumed. 1..nWhen comparing corresponding patches of two images, for example, A and B, the Gaussian statistics of the patch in image A can be used to estimate how likely the measured intensity value in the patch in image B is. This likelihood can be thresholded to provide a prediction of changes within the patch. This likelihood can also be visualized as an overlay of images A and B, allowing the reviewing clinician to analyze changes detected in the images over time. This visualization in turn allows the reviewing clinician to assess whether the detected changes are statistically relevant or due to an imperfect normalization procedure.

[0051] In a related embodiment, the normalized medical image 110' 1..n The operation of outputting the results of the statistical analysis of the normalized medical image 110' 1..n and displaying the spatial map of the statistical analysis as an overlay on one or more of the plurality of nodes in the plurality of nodes. By providing the results of the statistical analysis in this manner, a clinician can efficiently analyze the progression of the subject's disease condition.

[0052] In another embodiment, a computer program product is provided that, when executed by one or more processors, causes the one or more processors to generate a normalized medical image 110' representing a region of interest 120 within a subject. 1..n The method includes instructions for performing a method for providing a A time series of 2D medical images 110 including a region of interest 120 within a subject. 1..n receiving image data including the image data (S110); Receiving (S120) an atlas image 130 representing a region of interest 120; For each medical image in the time series, For comparison with the region of interest 120 in the atlas image 130, a warped region of interest 120' 1..n A normalized medical image 110' having 1.. n warping (S130) the medical image into an atlas image 130 to provide The method includes: 1..n and / or outputting the normalized medical image 110' 1..n The warped region of interest 120' between 1..n and outputting (S140b) the magnitude of the change in the

[0053] In another embodiment, a normalized medical image 110' representing a region of interest 120 within a subject is 1..n A system 200 for providing a method for detecting a plurality of sigma-based ... A time series of 2D medical images 110 including a region of interest 120 within a subject. 1..n receiving image data including the image data (S110); Receiving (S120) an atlas image 130 representing a region of interest 120; For each medical image in the time series, For comparison with the region of interest 120 in the atlas image 130, a warped region of interest 120' 1..n A normalized medical image 110' having 1.. n warping (S130) the medical image into an atlas image 130 to provide and the one or more processors generate a normalized medical image 110' 1..n and / or outputting the normalized medical image 110' 1..n The warped region of interest 120' between 1..n and outputting the magnitude of the change in (S140b).

[0054] An embodiment of the system 200 is shown in Figure 2. Note that the system 200 also includes a 2D medical imaging system (such as, for example, a projection x-ray imaging system 220 shown in Figure 2) for generating the image data received in operation S110, and an output normalized medical image 110' 1..n and / or displaying the normalized medical image 110' 1..n The warped region of interest 120' between 1..nThe system may include one or more of a display device (monitor 250, tablet, etc.) for outputting the magnitude of change in image intensity, results of statistical analysis of image intensity values, etc., a patient bed 260, and a user input device (not shown in FIG. 2) (keyboard, mouse, touch screen, etc.) for receiving user input related to operations performed by the system.

[0055] It is to be understood that the above embodiments are illustrative of the present disclosure, but not limiting. Other embodiments are contemplated. For example, an embodiment described in connection with a computer-implemented method may also be provided in a corresponding manner by a computer program product, a computer-readable storage medium, or the system 200. It is to be understood that a feature described in connection with any one embodiment may be used alone or in combination with other described features, or in combination with one or more features of another embodiment, or in combination with other embodiments. Moreover, equivalents and modifications not described above may be used without departing from the scope of the invention as defined in the appended claims. In the claims, the word "comprises" does not exclude other elements or operations, and singular elements do not exclude a plurality. The mere fact that certain features are recited in mutually different dependent claims does not indicate that a combination of these features cannot be advantageously used. Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. 1. A computer-implemented method for providing a normalized medical image representing a region of interest within a subject, the computer-implemented method comprising: receiving image data including a time series of 2D medical images including a region of interest within the subject; receiving a 2D atlas image representing the region of interest; for each 2D medical image in the time series, warping the 2D medical image to the 2D atlas image to provide a normalized medical image having a warped region of interest for comparison with the region of interest in the 2D atlas image; Including, outputting the normalized medical image; and / or outputting a magnitude of change of the warped region of interest between the normalized medical images; The computer-implemented method further comprising:

2. The computer-implemented method of claim 1 , wherein the 2D atlas image represents a preferred viewpoint of the region of interest for assessing a pathology in the time series of 2D medical images.

3. The computer-implemented method of claim 1 , wherein the warping step is based on a mapping between corresponding landmarks represented in both the 2D medical image and the 2D atlas image.

4. the 2D atlas image includes a plurality of labeled anatomical landmarks; The computer-implemented method comprises: applying a feature detector to each 2D medical image in the time series to identify a plurality of landmarks in the 2D medical image that correspond to the labeled anatomical landmarks; The computer-implemented method of claim 1 , wherein the mapping is determined using the identified corresponding landmarks.

5. The computer-implemented method of claim 4 , wherein applying the feature detector is performed using an edge detector, model-based segmentation, or a neural network.

6. adjusting the intensity of each 2D medical image of the time series based on the intensity at one or more locations in the 2D atlas image, based on the intensity at one or more locations in the medical images of the time series, or based on the intensity at one or more locations in a reference image to provide adjusted intensity values ​​in the normalized medical image; and / or 2. The computer-implemented method of claim 1, further comprising adjusting the intensity of each 2D medical image in the time series using an image style transfer algorithm to provide adjusted intensity values ​​in the normalized medical image.

7. The computer-implemented method of claim 6 , wherein warping the 2D medical image into the 2D atlas image occurs before adjusting the intensity of the 2D medical image.

8. calculating a magnitude of change in the warped region of interest between the normalized medical images based on the adjusted intensity values ​​in the normalized medical images; 7. The computer-implemented method of claim 6, wherein outputting a magnitude of change in the warped region of interest between the normalized medical images comprises outputting the calculated magnitude of the change.

9. adjusting the intensity of each 2D medical image of the time series based on the intensity at one or more locations in the 2D atlas image provides adjusted intensity values ​​at corresponding one or more locations in the normalized medical image that are the same as the intensity values ​​at the one or more locations in the 2D atlas image; adjusting the intensity of each 2D medical image of the time series based on the intensity at one or more locations within the 2D medical images of the time series provides adjusted intensity values ​​at corresponding one or more locations within the normalized medical image that are the same as the intensity values ​​at the one or more locations within the 2D medical images of the time series; 7. The computer-implemented method of claim 6, wherein adjusting the intensity of each 2D medical image in the time series based on the intensity at one or more locations in a reference image provides adjusted intensity values ​​at corresponding one or more locations in the normalized medical image that are the same as the intensity values ​​at the one or more locations in the reference image.

10. adjusting the intensity of each 2D medical image of the time series based on the intensity at one or more locations within the 2D atlas image, calculating a mean intensity value within a portion of the 2D atlas image; normalizing the intensity values ​​in each 2D medical image of the time series using the average intensity value; The computer-implemented method of claim 6, comprising:

11. 7. The computer-implemented method of claim 6, wherein normalizing the intensity values ​​in each 2D medical image in the time series using the average intensity value comprises mapping the intensity values ​​in a corresponding portion of each 2D medical image in the time series to the average intensity value in the portion of the 2D atlas image.

12. The computer-implemented method of claim 1 , further comprising suppressing one or more image features outside the region of interest in the normalized medical image.

13. identifying the region of interest within the 2D atlas image; mapping the outline of the region of interest from the 2D atlas image onto each of the normalized medical images; adjusting image intensity values ​​in the normalized medical image outside the mapped contour to suppress the one or more image features outside the region of interest; The computer-implemented method of claim 12 further comprising:

14. performing a statistical analysis of image intensity values ​​within the region of interest in the normalized medical image; The step of outputting a magnitude of change of the warped region of interest between the normalized medical images includes: The computer-implemented method of claim 1 , further comprising outputting results of the statistical analysis of the normalized medical image.

15. 15. The computer-implemented method of claim 14, wherein outputting results of the statistical analysis of the normalized medical images comprises displaying a spatial map of the statistical analysis as an overlay on one or more of the normalized medical images.

16. The computer-implemented method of claim 1 , wherein the time series of 2D medical images comprises X-ray images or ultrasound images.

17. The computer-implemented method of claim 1 , wherein the time series of 2D medical images comprises X-ray images produced by a mobile X-ray imaging system.

18. The computer-implemented method of claim 1 , wherein the time series of 2D medical images represents a longitudinal study of the subject.

19. 1. A computer program comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method for providing a normalized medical image representative of a region of interest within a subject, the computer program comprising: The method comprises: receiving image data including a time series of 2D medical images including a region of interest within the subject; receiving a 2D atlas image representing the region of interest; for each 2D medical image in the time series, warping the 2D medical image to the 2D atlas image to provide a normalized medical image having a warped region of interest for comparison with the region of interest in the 2D atlas image; Including, The method comprises: outputting the normalized medical image; and / or outputting a magnitude of change of the warped region of interest between the normalized medical images; Also included are computer programs.

20. 1. A system for providing a normalized medical image representing a region of interest within a subject, the system comprising: one or more processors; receiving image data including a time series of 2D medical images including a region of interest within the subject; receiving a 2D atlas image representing the region of interest; for each 2D medical image in the time series, warping the 2D medical image to the 2D atlas image to provide a normalized medical image having a warped region of interest for comparison with the region of interest in the 2D atlas image; and The one or more processors: outputting the normalized medical image; and / or outputting a magnitude of change of the warped region of interest between the normalized medical images; A system that further

Images