Methods, systems, and computer program elements for monitoring the progression of an X-ray image series

Abstract

The present invention relates to a method, system, and computer program element for monitoring the progress of an X-ray image series, the method comprising the steps of receiving an X-ray image series captured from a patient by an X-ray system, selecting a region of interest (ROI) from at least one image of the X-ray image series, dividing the selected ROI in each image of a plurality of X-ray images into spatial patches using a processing unit, determining respiratory cycles and cardiac cycles from the patches using the processing unit, removing respiratory cycles and cardiac cycles from the patches using the processing unit, comparing the ROI patches with reference patches, determining deviating patches that deviate from the reference patches, generating a visualization map superimposed on an image of the X-ray image series, and displaying the visualization map to a user on an interface.

Description

[Technical Field]

[0001] The present invention relates to the field of monitoring the temporal evolution of a patient in X-ray images, i.e. monitoring the progression of a patient, more particularly the invention relates to progression monitoring of an X-ray image series, a system for progression monitoring of an X-ray image series, and a computer program element. [Background technology]

[0002] Despite modern imaging methods, monitoring patient progress remains a challenging task for physicians. For example, even with widely used X-ray equipment, images obtained for the same patient can differ due to changes in internal parameters and image capture conditions (e.g., radiator voltage and current, exposure time), patient position, inhalation phase, or capture equipment changes due to technical reasons or hospital workload. These factors make it difficult to directly compare images taken one after the other and / or on different days. Therefore, different settings on the same equipment can complicate patient status / progression monitoring during treatment. Modern digital X-ray detectors offer the ability to generate images in short time frames, allowing for the generation of time-series X-ray images at high resolution, at speeds of up to several frames per second. For this reason, a series of X-ray images for objective and quantitative analysis is highly desirable. Summary of the Invention [Problem to be solved by the invention]

[0003] Therefore, there is a need to optimize the progress monitoring of patient x-ray images. There is a need to optimize the image capture process and improve the visualization of x-ray images and / or x-ray image series during progress monitoring so that the functional status of the patient can be obtained.

[0004] It is an object of the present invention to provide improved methods, systems and computer program elements for the progression monitoring of X-ray image series. [Means for solving the problem]

[0005] The object of the present invention is solved by the subject matter of the independent claims, further embodiments are incorporated in the dependent claims.

[0006] It should be noted that any feature, function, and / or element described below with reference to a method applies equally to a system, and vice versa. Thus, any feature, function, step, and / or element described below with reference to one aspect of the disclosure applies equally to any other aspect of the disclosure.

[0007] According to a first aspect of the present invention, a method for monitoring the progress of an X-ray image series is described. The method includes receiving an X-ray image series captured from a patient by an X-ray system, selecting a region of interest (ROI) from at least one image of the X-ray image series, dividing the selected ROI in each image of a plurality of X-ray images into spatial patches using a processing unit, and determining respiratory cycles and cardiac cycles from the patches using the processing unit. The method further includes removing the respiratory cycles and cardiac cycles from the patches using the processing unit, comparing the ROI patches with reference patches, determining deviation patches that deviate from the reference patches, generating a visualization map from the deviation patches that is superimposed on an image of the X-ray image series, and displaying the visualization map on an interface to a user.

[0008] In the context of the present invention, the term "X-ray image series" is understood to describe a sequence of X-ray images obtained by dynamic X-ray imaging, which describes functional imaging using successive images, which offers many advantages such as high temporal resolution and flexibility in body positioning. An image series may be understood as an image series in which multiple images are generated in a time sequence. An image sequence may also be an image sequence in which multiple images of the same object are generated in succession.

[0009] In the context of the present invention, the term "region of interest (ROI)" should be understood to describe a sample within a medical image of particular interest for medical diagnosis used by a user. For example, the region of interest may be a tumor, a bronchus, a lung, a heart, a bronchial tube, or a boundary of a lung region, this list is not limited. The type and size of the ROI may depend on the medical image to be analyzed, the anatomical structures that may be found in the medical image, and the part of the patient's body that undergoes medical image analysis.

[0010] In the context of the present invention, the term "patch" should be understood to describe a spatial region of a predetermined size, which may be user-defined, predefined, or defined during image analysis. In particular, a patch should be understood to describe at least one spatial region in an image that is homogeneous, in other words, contains similar image features. The minimum size of a patch may be at least a pixel, and preferably the size of a patch / patch may be larger than one pixel. A region of interest can be divided into multiple patches.

[0011] In other words, a method is described that enables analysis of the dynamics of X-ray image series, particularly chest X-ray image series, observing one or more respiratory cycles with high temporal resolution, rather than just analyzing the intensity of single chest snapshots collected at different times. On the other hand, incomplete respiratory cycles can be used, which does not mean a complete respiratory cycle of inspiration and expiration. It may be possible to estimate and correct for "globally homogeneous" contractions or expansions. Thus, respiratory motion can be estimated using image data from less than a respiratory cycle. This method involves selecting a region of interest (ROI) on the chest X-ray image series, after which a time-series dynamic analysis is performed. The time-series dynamic analysis may include the following steps: dividing the selected ROI into spatial patches and extracting the frequencies of the respiratory cycle and cardiac cycle. The patches are compared with a reference region, which is a reference patch. Extracting the respiratory cycle and cardiac cycle may involve intensity-based time-series analysis, which may include extracting dominant frequencies. To execute the method, a processing unit capable of performing one or more of the method steps may be used. For example, the X-ray image series may be received in the processing unit and / or in a memory accessed by the processing unit, the images may be received from an X-ray imaging system, or the images may be received from any computer that receives images from the X-ray system.

[0012] Removal of the respiratory and cardiac cycles allows for compensatory drift, which can be expected to detect changes in anatomical structures that may be disturbing in an X-ray image series. For example, shifts in the position of contrasting objects such as the ribs and diaphragm can be reduced or even eliminated.

[0013] The step of determining deviant patches that deviate from the reference patches may involve automatic determination of deviant regions, i.e. patches whose frequency does not correspond to respiratory and / or cardiac cycles or neighboring patches.

[0014] The present invention offers the advantage that the effective radiation dose for the patient is relatively small with modern machines, and therefore, several chest X-ray image scans do not pose significant risks or radiation burden to the patient. From the clinician's perspective, there is no need to reacquire images in the case of different machine settings or incorrect inspiration phases. Furthermore, the physician can still select individual appropriate images from a series of images, for example, for canonical analysis. More accurate patient progress monitoring can, for example, help estimate the effectiveness of treatment strategies and make necessary operational changes.

[0015] According to an exemplary embodiment of the present invention, comparing the patch with a reference patch may include extracting amplitude and / or phase information from the X-ray image based on the real and / or imaginary parts of the complex coherency. Extracting phase information may include extracting any image signal, particularly from any image in an image series. For example, for a given image, a pixel pair or pairs of pixels may be selected, and then a time series may be constructed based on using that image as a reference image. The pixel pairs may refer to portions of the corresponding patch, particularly patches, that may be tracked along the image series. Furthermore, extracting phase information may involve advanced mathematical models for extracting appearance changes in the image patch.

[0016] According to an exemplary embodiment of the present invention, determining the deviation patch may include at least one of independent component analysis, calculation of statistical moments, or maximum pixel value change rate. For example, in this step, the respiratory cycle and the cardiac cycle are removed by filtering out the corresponding independent components and restoring the original image, i.e., image signal, without them. Therefore, it may be any of the above for determining the deviation patch, or even a combination of the above.

[0017] According to an exemplary embodiment of the present invention, the region of interest may be selected automatically or manually by a user. The region of interest may be an anatomical structure whose progress should be monitored. The region of interest may be determined by a user depending on the anatomical structure to be investigated. Alternatively, the region of interest may be determined automatically, for example, by artificial intelligence, which may be trained with X-ray image data containing different anatomical structures, so that the artificial intelligence can determine each anatomical structure shown in the X-ray image series. In addition, a reference patch may be selected automatically or manually by a user. The reference patch is a part of the X-ray image and is determined as a normal element in the X-ray image. For example, the reference patch may be a patch in bone, heart, or clearly healthy tissue, depending on the task to be performed from the X-ray image series. If artificial intelligence is used to determine the patch, the artificial intelligence may be trained using healthy tissue data for each anatomical structure. The reference patch as a normal element in the X-ray image may be a healthy tissue, healthy bone, or a normal element in the sense of a normally functioning anatomical structure.

[0018] According to an exemplary embodiment of the present invention, the steps of segmenting a selected ROI in each image of a plurality of X-ray images, determining respiratory cycles and cardiac cycles from the patches, determining respiratory cycles and cardiac cycles from the patches, removing respiratory cycles and cardiac cycles from the patches, comparing the patches with reference patches, determining deviation patches that deviate from the reference patches, and generating a visualization map from the deviation patches can be performed for each image in the X-ray image series, and in particular, each of the above steps can be performed for each single image in the X-ray sequence. In particular, each step can be performed one after another for each single image in the time series, or the steps can be performed one after another for each image in the time series simultaneously. In other words, all images in the image series may have to undergo all of the above steps so that estimation of tissue dynamic parameters can be performed for the entire image series.

[0019] According to an exemplary embodiment of the present invention, determining respiratory cycles and cardiac cycles may include determining respiratory cycles and cardiac cycles from at least one of dynamics of total patch intensities or based on pixel value change rates. In other words, patch intensities themselves may not be measured, but corresponding patches are spatially tracked. Corresponding patches are patches of each image in an image series. For example, a first image may include patches x1, x2, and x3, a second image may include patches y1, y2, and x3, and patch x1 may anatomically correspond to patch y1 of another image, i.e., patches x1 and y1 may depict the same anatomical structure (which may be shifted relative to the other anatomical structure due to some forms of movement), etc. Corresponding patches may be described as patches of different images that correspond to their positions within the images. The spatially tracked patches may be anatomical structures (bones, tissues, boundaries, etc.). Determining different cycles may be performed by a processing unit or any computer element.

[0020] According to an exemplary embodiment of the present invention, one or more sensors may further be used to determine respiratory and / or cardiac cycles. For example, this may include data from a respiratory sensor (spirometer) or a cardiac measurement device, cardiac electrodes, or sensor data used for electrocardiograms. This sensor signal may be used to remove respiratory and / or cardiac cycles in the time series of images.

[0021] According to an exemplary embodiment of the present invention, a dynamic X-ray series may be a time sequence of chest X-ray images, in other words, X-ray images taken of a patient's chest during X-ray imaging processing that produces a sequence of time X-ray images.

[0022] According to an exemplary embodiment of the present invention, the method may further include generating a total score for the ROI based on the ratio of normal patches to deviation (deviant) patches, and comparing the total score with previous X-ray images. The score and spatial distribution of deviation patches could be compared with previous observations, meaning previous images in a previous time series.

[0023] The method may generally involve assessment of functional properties of tissue, which may be a patch of ROI, dynamically. Therefore, at least a short time series is required to generate an image series from which functional properties can be determined.

[0024] According to an exemplary embodiment of the present invention, the method may further comprise the step of comparing patches of the received X-ray image series with patches received from a further X-ray image series. Thus, corresponding patches, which may be manually selected by a user, may then be compared with patches from a previous session. For both patches, fundamental frequencies such as breathing and heartbeat should be removed from both time series so that comparisons between patches from different time series can be performed.

[0025] According to exemplary embodiments of the present invention, the visualization map can be selected from at least one of a respiration map, a perfusion map, and any visualization of a spatial-temporal map of an ROI can be applied. Furthermore, the average level of synchronization can be calculated, or the relative change in intensity of the selected ROI can be calculated. This value(s) can be compared with a threshold, for example, the average + 3 sigma from the same region (only the ROI or a patch of the ROI) or a selected reference patch. Then, for the selected region, pixels relative to this baseline can be painted. The visualization map can be selected by the user depending on the selected region of interest and / or depending on the patient's diagnosis. Furthermore, the visualization map can be automatically selected depending on the selected region of interest or the determined anatomical structure (by a processing unit using artificial intelligence or any other object detection unit) in the X-ray image (series).

[0026] According to an exemplary embodiment of the present invention, generating the visualization map may further include generating a ROI color map according to the selected visualization map, which is displayed as an overlay on the plurality of X-ray images. In particular, the visualization map visualizes the selected region of interest and indicates this region with a determined color. Furthermore, the ROI color map may be a spatial color map that can indicate color differentiation patches in the region of interest.

[0027] According to an illustrative embodiment of the present invention, the generation of the visualization map can include a description of the functional state of the ROI. In particular, the functional state of the anatomical structure of interest can be visualized. For example, whether both lobes of the lung are functioning properly, i.e., inhalation and exhalation, can be derived from the visualization map, and the expansion of the lungs during inhalation and exhalation can be derived. The same applies to other anatomical structures, such as a properly beating heart or pulmonary perfusion.

[0028] According to an exemplary embodiment of the present invention, the received x-ray image series is a time sequence of consecutive x-ray images, such that the multiple images received during x-ray imaging are successively received images and multiple x-ray images are generated during command execution of the imaging process.

[0029] According to a second aspect of the present invention, a system for monitoring the progression of an X-ray image series is described.

[0030] The system may include a processing unit configured to receive an X-ray image series from a patient, select a region of interest (ROI) from at least one image of the X-ray image series, divide each selected ROI in each image of the X-ray image series into spatial patches using the processing unit, determine respiratory cycles and cardiac cycles from the patches using the processing unit, remove respiratory cycles and cardiac cycles from the patches using the processing unit, compare the patches with reference patches, determine deviation patches that deviate from the reference patches, and generate a visualization map from the deviation patches that is overlaid on an image of the X-ray image series. Further, the system may include an interface configured to display the visualization map generated by the processing unit to a user.

[0031] The system may be a stand-alone unit that may be attached to and / or integrated with any suitable X-ray system, or the system may comprise an X-ray system including a respective X-ray source and X-ray detector for performing X-ray imaging, and including a processing unit configured to perform the steps described above.

[0032] The proposed system and method may, in principle, be applicable to any hospital with X-ray equipment capable of providing rapid X-ray acquisition speeds. All of the required method steps and / or calculations may be provided in the cloud, which may also include automatic region-of-interest selection (e.g., based on lung segmentation) using automatically uploaded chest X-ray image data. For example, user controls and result demonstrations may be provided on a display including the system's interface or in a tablet application.

[0033] According to a third aspect of the present invention, there is provided a computer program element for monitoring the progression of an X-ray image series, which when executed by a processing unit of the system may be adapted to: receive an X-ray image series captured from a patient; select a region of interest (ROI) from at least one image of the X-ray image series; divide the selected ROI in each image of the X-ray image series into spatial patches using the processing unit; determine respiratory cycles and cardiac cycles from the patches using the processing unit; remove the respiratory cycles and cardiac cycles from the patches using the processing unit; compare the patches with reference patches; determine deviation patches that deviate from the reference patches; generate a visualization map from the deviation patches overlaid on images of the X-ray image series; and display the visualization map to a user on an interface.

[0034] A computer program element may be part of a computer program, but may also be an entire program in its own right, for example a computer program element may be used to update an existing computer program to achieve the present invention.

[0035] The program elements may be stored on a computer readable medium, which may be considered as a storage medium such as a USB stick, a CD, a DVD, a data storage device, a hard disk or any other medium on which such program elements may be stored.

[0036] According to various embodiments of the present disclosure, the methods described herein may be implemented using a hardware computer system executing a software program. Furthermore, in exemplary, non-limiting embodiments, implementations may include distributed processing, component / object distributed processing, and parallel processing. A virtual computer system process may implement one or more of the methods or functions described herein, and the processors described herein may be used to support a virtual processing environment.

[0037] It should be noted that embodiments of the present invention are described with reference to different subject matters. In particular, some embodiments are described with reference to apparatus / system type claims, while other embodiments are described with reference to method type claims. However, those skilled in the art will know from the above and following description that, unless otherwise notified, any combination of features belonging to one type of subject matter, as well as any combination of features relating to different subject matters, such as between features of a particular apparatus type claim and features of a method type claim, is considered to be disclosed in the present application.

[0038] The above and further aspects of the present invention will be apparent from and explained with reference to the following examples of embodiments. The present invention will be explained in more detail below with reference to the following examples, but the present invention is not limited to the embodiments. [Brief explanation of the drawings]

[0039] [Figure 1] 1 shows a flow diagram of a method according to one embodiment of the present invention. [Figure 2] 10A-10C show different images of an image series according to an embodiment of the present invention. [Figure 3] 1 illustrates the determination of a deviant patch according to one embodiment of the present invention. [Figure 4] 1 illustrates the generation of a visualization map according to one embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0040] The figures in the drawings are schematic and it should be noted that in different figures, similar or identical elements are provided with the same reference signs.

[0041] FIG. 1 shows a flow diagram including method steps according to an embodiment of the present invention. The method for monitoring the progress of an X-ray image series includes steps S1 to S9, although more method steps may also be applied. The order of the steps described above is merely exemplary, and the order is not limited to the order described. For example, the order of one or more steps may be changed relative to one another, or one or more steps may be repeated before another step is performed. The method includes step S1 of receiving an X-ray image series captured from a patient by an X-ray system; step S2 of selecting a region of interest (ROI) from at least one image of the X-ray image series; and step S3 of dividing the selected ROI into spatial patches in each of the X-ray images using a processing unit. Step S3 may comprise a further substep in which, for each image in the image series, the ROI is divided into patches. Meanwhile, in step S3, the ROI is divided into patches simultaneously for each image in the image series. Furthermore, the other described method steps may be performed sequentially for each image in the image series, or simultaneously for each image in the image series. The method further includes step S4 of determining respiratory cycles and cardiac cycles from the patches using a processing unit, step S5 of removing respiratory cycles and cardiac cycles from the patches using the processing unit, step S6 of comparing the patches of the ROI with reference patches, step S7 of determining deviation patches that deviate from the reference patches, step S8 of generating a visualization map from the deviation patches that is superimposed on an image of the X-ray image series, and step S9 of displaying the visualization map on an interface to a user. The display of the visualization map can be displayed on the interface to a user, on a display of the interface, on a display of the X-ray device, or on the X-ray system. Alternatively, the display can be performed on a mobile device such as a tablet.

[0042] Step S6 may further include comparing the patch with a reference patch, which may involve extracting amplitude and / or phase information from the X-ray image based on the real and / or imaginary parts, respectively, of a complex coherency, which may be calculated as a correlation function between the spectral components of two time series for a given frequency set, which may be performed in a substep of step S6. Furthermore, step S7 may include at least one of independent component analysis, calculation of statistical moments, or maximum pixel value change rate, each of which may be performed independently from the other as a substep of step S7, or may be an additional step after step S7.

[0043] Steps S3 to S8 are performed for each image in the X-ray image series either one after the other or simultaneously for each image in the image series.

[0044] The method may further comprise, for example, generating a total score for the ROI based on the ratio of normal patches to deviant patches, and comparing the total score with previous X-ray images. Thus, the present X-ray image series may be compared with another X-ray image series, for example a historical image series, in order to analyze changes in the patient's condition or the progression of the condition of the functional properties of the analyzed anatomical structure.

[0045] 2 shows three different images 101-103 of a patient's chest. This shows an example of a series of lateral chest X-ray images observed on a patient during treatment. Different patient positions and acquisition settings of the same device can complicate patient status monitoring; when applying methods such as those described above, these complications can be overcome, as a region of interest can be determined for each image and analyzed using the methods described herein.

[0046] FIG. 3 shows a diagram of a deviation patch determination and visualization map 310 according to an embodiment of the present invention. A region of interest 321 is selected manually by a user, a physician, or automatically. In FIG. 3, the region of interest 321 is the lung, and both lobes of the lung are shown as regions of interest 321. As can be seen, at least five X-ray images 101-105 from the X-ray image series are displayed. Therefore, it can be said that the image series of FIG. 3 includes at least five chest X-ray images 101-105. For each image 101-105, a region of interest 321 is displayed. Furthermore, in each image 101-105, the region of interest 321 is divided into patches. Starting with image 101, the right lobe of the lung is completely displayed in the region of interest. In contrast, the left lobe of the lung is not completely visible. When comparing images 101-105, differences between the displayed regions of interest, and therefore between the patches of the left and right lobes of the lung, can be compared. FIG. 3 further illustrates a respiratory cycle 320 determined from a patch of the region of interest 321, where the respiratory cycle 320 is determined from / across all images in the image series 101-105. The respiratory cycle 320 is shown as a frequency plot and generated for the selected patch. The respiratory cycle 320 can be divided into an inhalation portion and an exhalation portion, and a determination of the rate of pixel value change can be performed to identify deviation patches within the region of interest. For example, increasing pixel values ​​can be determined during exhalation, and decreasing pixel values ​​can be determined for inhalation. Thus, the functional condition of the lungs can be illustrated via a visualization map 310, which can be displayed to the user via a display on the interface, showing the patient's functional condition observed over time. The illustrated chest x-ray images can also be available to the user for standalone observation / analysis.

[0047] 4 illustrates the generation of a visualization map 410 according to an embodiment of the present invention. In particular, the visualization map 410 illustrates a perfusion map generation process based on a dynamic X-ray time series of lung images 101-105. From the time series of X-ray images 101-105, a pulmonary signal 413, which may be a respiratory cycle and a cardiac signal 412, i.e., a cardiac cycle, can be determined. These signals can then be removed, for example, an inverted cardiac signal 411 can be applied to eliminate the cardiac signal 412. Furthermore, depending on the signals to be removed and the signals to be obtained, it may be possible to apply filters such as a high-pass filter or a low-pass filter.

[0048] While the present invention has been illustrated and described in detail in the drawings and the foregoing description, such illustration and description are to be considered exemplary or illustrative and not restrictive, and the present invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. It should be noted that the term "comprising" does not exclude other elements or steps, and that "a" or "an" does not exclude a plurality. Also, elements described in association with different embodiments may be combined. It should also be noted that reference signs in the claims should not be construed as limiting the scope of the claims. [Explanation of symbols]

[0049] S1 to S9 Method steps 101, 102, 103 X-ray image 105 X-ray image 310 Visualization Map 320 Breathing Cycle 321 Areas of Interest 410 Visualization Map 411 Inverted Heart Signal 412 Heart Signal 413 Lung Signal 421 Areas of Interest

Claims

1. 1. A method for monitoring the progression of an x-ray image series, comprising: receiving the series of x-ray images captured from the patient by an x-ray system; selecting a region of interest from at least one image of said series of X-ray images; dividing, using a processing unit, a selected region of interest in each of the plurality of X-ray images into spatial patches; determining respiratory and cardiac cycles from the patch using the processing unit; removing the respiratory and cardiac cycles from the patch using the processing unit; comparing the patch of the region of interest with a reference patch; determining a deviant patch that deviates from the reference patch; generating a visualization map from the deviation patches that is superimposed on an image of the X-ray image series; displaying the visualization map on an interface to a user; A method comprising:

2. The method of claim 1 , wherein comparing the patch to the reference patch comprises extracting amplitude and / or phase information from the X-ray image based on a real and / or imaginary part of a complex coherency.

3. The method of claim 1 or 2, wherein determining the deviant patches comprises at least one of independent component analysis, calculation of statistical moments, or maximum pixel value change rate.

4. the region of interest is selected automatically or manually by the user; and / or the reference patch is selected automatically or manually by the user; the reference patch is a part of the X-ray image and is determined as a normal element in the X-ray image; 4. The method according to any one of claims 1 to 3.

5. 5. The method of claim 1, wherein the steps of segmenting a selected region of interest in each of the plurality of X-ray images, determining respiratory cycles and cardiac cycles from the patches, determining respiratory cycles and cardiac cycles from the patches, removing the respiratory cycles and cardiac cycles from the patches, comparing the patches with reference patches, determining deviant patches that deviate from the reference patches, and generating a visualization map from the deviant patches are performed for each image of the X-ray image series.

6. 6. The method of claim 1, wherein determining the respiratory and cardiac cycles comprises determining the respiratory and cardiac cycles from at least one of dynamic intensities of all the patches or based on pixel value change rates.

7. 7. The method of claim 1, wherein the dynamic X-ray series is a time sequence of chest X-ray images.

8. The method comprises: generating an overall score for the region of interest based on the ratio of normal patches to deviant patches; comparing all of said scores with a previous x-ray image; The method of any one of claims 1 to 7, further comprising:

9. comparing the patches of the received X-ray image series with patches received from further X-ray image series. The method of any one of claims 1 to 8, further comprising:

10. The method according to claim 1 , wherein the visualization map is selected from at least one of a respiration map, a perfusion map.

11. 11. The method of claim 1, wherein generating the visualization map further comprises generating a region of interest color map dependent on the selected visualization map, the region of interest color map being displayed as an overlay on the plurality of X-ray images.

12. 12. The method of claim 1, wherein the generation of the visualization map comprises an illustration of the functional state of the region of interest.

13. 13. The method of any one of claims 1 to 12, wherein the received X-ray image series is a time sequence of consecutive X-ray images.

14. 1. A system for monitoring the progression of an X-ray image series, comprising: A processing unit comprising: receiving said X-ray image series from a patient; selecting a region of interest from at least one image of said series of X-ray images; dividing a selected region of interest in each image of the X-ray image series into spatial patches using the processing unit; determining respiratory and cardiac cycles from the patch using the processing unit; removing the respiratory and cardiac cycles from the patch using the processing unit; comparing said patch with a reference patch; determining a deviant patch that deviates from the reference patch; generating a visualization map from the deviation patches, the visualization map being overlaid on an image of the X-ray image series; a processing unit configured to execute The system further comprises an interface configured to display to the user a visualization map generated by the processing unit. system.

15. 1. A computer program element for monitoring the progression of an X-ray image series, said computer program element, when executed by a processing unit of a system, providing said system with: receiving the series of x-ray images captured from a patient; selecting a region of interest from at least one image of said series of X-ray images; dividing a selected region of interest in each image of the X-ray image series into spatial patches using the processing unit; determining respiratory and cardiac cycles from the patch using the processing unit; removing the respiratory and cardiac cycles from the patch using the processing unit; comparing said patch with a reference patch; determining a deviant patch that deviates from the reference patch; generating a visualization map from the deviation patches that is superimposed on an image of the X-ray image series; displaying a visualization map on the interface to the user; A computer program element configured to cause the execution of

Images