Image processing apparatus, method, and program

Abstract

To provide an image processing apparatus, method and program to enable accurate diagnosis of a target organ.SOLUTION: A processor extracts a region of a target organ from a medical image, extracts a region of at least one peripheral organ that is present in a periphery of the target organ from the medical image, derives a positional relationship between the target organ and the peripheral organ, and determines whether the target organ is compressed by the peripheral organ based on the positional relationship.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to an image processing apparatus, method, and program.

Background Art

[0002] In recent years, with the progress of medical devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices, image diagnosis using higher-quality and higher-resolution medical images has become possible. In addition, computer-aided diagnosis (CAD; Computer-Aided Diagnosis), which derives the probability of the presence of a lesion and location information, etc. by analyzing medical images and presents this to a doctor such as a radiologist, has been put into practical use. For example, Patent Document 1 proposes a method of specifying the region of a target organ and extracting a region suspected of being abnormal based on diagnostic criteria determined for each organ.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] By the way, for the diagnosis of a target organ using CAD, it is important to identify a change in the shape of the organ such as atrophy or enlargement of the target organ. For example, when the target organ is the pancreas, when a tumor of the pancreas occurs, the pancreatic parenchyma around the tumor enlarges or the pancreatic parenchyma other than the tumor atrophies. Therefore, it is important to diagnose the state of pancreatic diseases by paying attention to the size of the diameter of the pancreas included in the medical image.

[0005] In this context, the pancreas is surrounded by other organs such as the stomach and liver. Therefore, compression from these organs can sometimes cause the apparent diameter of the pancreas to decrease. In this case, medical images may show a partially narrowed pancreas, leading to the misconception of pancreatic atrophy. Consequently, even if there is no actual pancreatic disease, an abnormality may be mistakenly diagnosed.

[0006] This invention has been made in view of the above circumstances, and aims to enable accurate diagnosis of the target organ. [Means for solving the problem]

[0007] An image processing apparatus according to a first aspect of the present disclosure comprises at least one processor, The processor extracts the region of the target organ from the medical image. Extract the region of at least one surrounding organ from the medical image, The positional relationship between the target organ and surrounding organs is determined, Based on its positional relationship, it is determined whether the target organ is being compressed by surrounding organs.

[0008] An image processing apparatus according to a second aspect of the present disclosure is an image processing apparatus according to a first aspect, in which the processor further determines whether or not the target organ has atrophied.

[0009] The image processing apparatus according to the third aspect of this disclosure is an image processing apparatus according to the second aspect, wherein the processor determines whether the target organ is being compressed by surrounding organs when it determines that the target organ is atrophied.

[0010] The image processing apparatus according to the fourth aspect of this disclosure, in the image processing apparatus according to the third aspect, determines that there is no abnormality in the target organ when it is determined that there is no atrophy of the target organ, If the target organ is atrophied and is being compressed by surrounding organs, it is determined that there is no abnormality in the target organ. It is also acceptable to determine that there is an abnormality in the target organ if there is atrophy of the target organ and the target organ is not being compressed by surrounding organs.

[0011] The fifth aspect of the present disclosure is an image processing device according to any one of the first to fourth aspects, wherein the processor determines whether the target organ is being compressed by surrounding organs based on the medical image in addition to the positional relationship.

[0012] The image processing method disclosed herein extracts the region of a target organ from a medical image, Extract the region of at least one surrounding organ from the medical image, The positional relationship between the target organ and surrounding organs is determined, Based on its positional relationship, it is determined whether the target organ is being compressed by surrounding organs.

[0013] The image processing program disclosed herein includes a procedure for extracting the region of a target organ from a medical image, A procedure for extracting the region of at least one surrounding organ from a medical image, Procedures for determining the positional relationship between the target organ and surrounding organs, The computer is instructed to perform a procedure to determine whether or not a target organ is being compressed by surrounding organs based on its positional relationship. [Effects of the Invention]

[0014] According to this disclosure, accurate diagnosis of the target organ can be performed. [Brief explanation of the drawing]

[0015] [Figure 1] This figure shows a schematic configuration of a diagnostic support system using an image processing device according to the first embodiment of this disclosure. [Figure 2] This figure shows the hardware configuration of the image processing device according to the first embodiment. [Figure 3] Functional configuration diagram of the image processing apparatus according to the first embodiment. [Figure 4] Figure for explaining extraction of regions of pancreas and surrounding organs [Figure 5] Figure showing an image with different masks applied to each of the pancreas and surrounding organs [Figure 6] Figure showing a medical image including a pancreas with its tail compressed [Figure 7] Figure showing a display screen of the determination result of the presence or absence of compression (compression present) [Figure 8] Figure showing a display screen of the determination result of the presence or absence of compression (no compression) [Figure 9] Flowchart showing the processing performed in the first embodiment [Figure 10] Functional configuration diagram of an image processing apparatus according to the second embodiment [Figure 11] Figure showing a display screen of the determination result of the presence or absence of abnormality [Figure 12] Flowchart showing the processing performed in the second embodiment

Mode for Carrying Out the Invention

[0016] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. First, the configuration of a medical information system to which the image processing apparatus according to the present embodiment is applied will be described. FIG. 1 is a diagram showing a schematic configuration of the medical information system. The medical information system shown in FIG. 1 includes a computer 1 incorporating the image processing apparatus according to the present embodiment, an imaging device 2, and an image storage server 3, which are connected in a communicable state via a network 4.

[0017] Computer 1 contains the image processing device according to this embodiment, and the image processing program of this embodiment is installed on it. Computer 1 may be a workstation or personal computer directly operated by the physician performing the diagnosis, or it may be a server computer connected to them via a network. The image processing program is stored in a storage device of the server computer connected to the network, or in network storage, in a state that is accessible from the outside, and is downloaded and installed on Computer 1 used by the physician as needed. Alternatively, it may be recorded on a recording medium such as a DVD (Digital Versatile Disc) or CD-ROM (Compact Disc Read Only Memory) and distributed, and then installed on Computer 1 from that recording medium.

[0018] The imaging device 2 is a device that generates a three-dimensional image representing a part of the subject to be diagnosed by imaging that part of the subject. Specifically, it is a CT scanner, an MRI scanner, or a PET (Positron Emission Tomography) scanner. The three-dimensional image, consisting of multiple tomographic images, generated by this imaging device 2 is transmitted to the image storage server 3 and stored. In this embodiment, the imaging device 2 is a CT scanner, and it generates a three-dimensional image from a CT image of the subject's abdomen. The acquired CT image may be a contrast-enhanced or non-contrast-enhanced CT image.

[0019] The image storage server 3 is a computer that stores and manages various types of data, and is equipped with a large-capacity external storage device and database management software. The image storage server 3 communicates with other devices via a wired or wireless network 4 to send and receive image data, etc. Specifically, it acquires various types of data, including image data of CT images generated by the imaging device 2, via the network, and stores and manages them on a recording medium such as a large-capacity external storage device. The storage format of the image data and communication between each device via the network 4 are based on protocols such as DICOM (Digital Imaging and Communication in Medicine).

[0020] Next, an image processing apparatus according to the first embodiment will be described. Figure 2 is a diagram showing the hardware configuration of the image processing apparatus according to the first embodiment. As shown in Figure 2, the image processing apparatus 20 includes a CPU (Central Processing Unit) 11, non-volatile storage 13, and memory 16 as a temporary storage area. The image processing apparatus 20 also includes a display 14 such as a liquid crystal display, input devices 15 such as a keyboard and mouse, and a network I / F (Interface) 17 connected to a network 4. The CPU 11, storage 13, display 14, input devices 15, memory 16, and network I / F 17 are connected to a bus 18. Note that the CPU 11 is an example of a processor in this disclosure.

[0021] The storage 13 is implemented using an HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc. The image processing program 12 is stored in the storage 13 as a storage medium. The CPU 11 reads the image processing program 12 from the storage 13, expands it into memory 16, and executes the expanded image processing program 12.

[0022] Next, the functional configuration of the image processing apparatus according to the first embodiment will be described. Figure 3 is a diagram showing the functional configuration of the image processing apparatus according to the first embodiment. As shown in Figure 3, the image processing apparatus 20 includes an image acquisition unit 21, a first extraction unit 22, a second extraction unit 23, a positional relationship derivation unit 24, a compression determination unit 25, and a display control unit 26. When the CPU 11 executes the image processing program 12, the CPU 11 functions as the image acquisition unit 21, the first extraction unit 22, the second extraction unit 23, the positional relationship derivation unit 24, the compression determination unit 25, and the display control unit 26.

[0023] The image acquisition unit 21 acquires the medical image G0 to be processed from the image storage server 3 based on instructions from the operator via the input device 15. In this embodiment, the medical image G0 is a CT image consisting of multiple tomographic images including the abdomen of the human body.

[0024] The first extraction unit 22 extracts the region of the target organ from the medical image G0. In this embodiment, the target organ is the pancreas. Therefore, the first extraction unit 22 has a semantic segmentation model (hereinafter referred to as the SS (Semantic Segmentation) model) that has been machine-trained to extract the pancreas from the medical image G0. As is well known, the SS model is a machine learning model that outputs an output image in which each pixel of the input image is labeled to represent the object (class) to be extracted. In this embodiment, the input image is a tomographic image constituting the medical image G0, the object to be extracted is the pancreas, and the output image is an image with the region of the pancreas labeled. The SS model is constructed using a convolutional neural network (CNN) such as ResNet (Residual Networks) or U-Net (U-shaped Networks).

[0025] As a result, the first extraction unit 22 extracts the region of the pancreas 30 included in the medical image G0 shown in Figure 4.

[0026] The extraction of target organs is not limited to methods using the SS model. Any method for extracting target organs from medical image G0 can be applied, such as template matching or thresholding of CT values.

[0027] The second extraction unit 23 extracts the region of at least one surrounding organ located around the target organ. In this embodiment, since the target organ is the pancreas, the second extraction unit 23 extracts the stomach, duodenum, liver, blood vessels, etc., located around the pancreas. In this embodiment, the second extraction unit 23 extracts the stomach, duodenum, and liver as surrounding organs. For this purpose, the second extraction unit 23 has an SS model that has been machine-learned to extract the stomach, duodenum, and liver from the medical image G0. In the SS model of the second extraction unit 23, the input image is a tomographic image constituting the medical image G0, the objects to be extracted are the stomach, duodenum, and liver, and the output image is an image with the regions of the stomach, duodenum, and liver labeled.

[0028] As a result, the second extraction unit 23 extracts the regions of the stomach 31, duodenum 32, and liver 33 contained in the medical image G0 shown in Figure 4.

[0029] Extraction of surrounding organ regions is not limited to methods using the SS model. Any method for extracting surrounding organ regions from medical image G0 can be applied, such as template matching or thresholding of CT values.

[0030] The positional relationship derivation unit 24 derives the positional relationship between the target organ and surrounding organs. Specifically, the positional relationship derivation unit 24 derives the shortest distance between the pancreas 30 and the stomach 31, duodenum 32, and liver 33 as the positional relationship. To derive the positional relationship, the positional relationship derivation unit 24 extracts the contour lines of the pancreas 30, stomach 31, duodenum 32, and liver 33. Then, the positional relationship derivation unit 24 derives the shortest distance between the contour line of the pancreas 30 and the contour lines of the stomach 31, duodenum 32, and liver 33 as the positional relationship. Note that if the contour lines are touching, the shortest distance is 0.

[0031] The positional relationship derivation unit 24 may also derive the positional relationships of the pancreas 30, stomach 31, duodenum 32, and liver 33 themselves, which are included in the medical image G0. The region itself is an image in which different masks are applied to the pancreas 30 and the surrounding organs, as shown in Figure 5. In Figure 5, the stomach 31, duodenum 32, and liver 33 are treated as surrounding organs and are given the same mask.

[0032] The compression determination unit 25 determines whether the target organ, namely the pancreas 30, is being compressed by surrounding organs based on the positional relationship derived by the positional relationship derivation unit 24. To this end, the compression determination unit 25 has a classifier 25A that outputs an evaluation value indicating whether or not the pancreas 30 is being compressed by surrounding organs based on the positional relationship.

[0033] The classifier 25A is constructed by machine learning a convolutional neural network using multiple training data sets in which the positional relationship and the presence or absence of compression of the pancreas 30 are known. When the positional relationship is the shortest distance between the pancreas 30 and the stomach 31, duodenum 32, and liver 33, training data in which the shortest distance and the presence or absence of compression are known are used to train the classifier 25A. When the positional relationship is the region itself, the pancreas 30 and surrounding organs (i.e., stomach 31, duodenum 32, and liver 33) are masked, and training data in which the presence or absence of compression is known is used to train the classifier 25A.

[0034] The evaluation value output by the classifier 25A, which indicates whether or not the pancreas is compressed, is a probability that the pancreas is being compressed, and will be a value between 0 and 1.

[0035] The compression determination unit 25 determines that the pancreas is being compressed if the evaluation value output by the classifier 25A is equal to or greater than a predetermined threshold. In the medical image G0 shown in Figures 4 and 5, the pancreas 30 is not in contact with surrounding organs, so the classifier output by the classifier 25A is below the threshold, and the compression determination unit 25 determines that there is no compression of the pancreas 30. On the other hand, as shown in Figure 6, the tail of the pancreas 30 is in contact with surrounding organs (in Figure 6, the stomach 31 and part of the duodenum 32), so the evaluation value output by the classifier 25A is equal to or greater than the threshold, and the compression determination unit 25 determines that there is compression of the pancreas 30.

[0036] The display control unit 26 displays the result of determining whether or not the pancreas 30 is compressed on the display 14. Figure 7 shows the display screen of the determination result. As shown in Figure 7, the medical image G0 is displayed on the display screen 40 when compression is determined to be present. The determination result 41 of compression is also displayed.

[0037] If the pancreas 30 is not compressed, the compression detection unit 25 determines that there is no compression of the pancreas 30. Figure 8 shows the display screen of the detection result when there is no compression. As shown in Figure 8, the display screen 40 shows the medical image G0 when it is determined that there is no compression. The detection result 41 of no compression is also displayed. However, as can be seen in Figure 8, the tail of the pancreas 30 is atrophied. In this case, the doctor can determine that there is an abnormality in the pancreas 30 based on the detection result.

[0038] Next, the processing performed in the first embodiment will be described. Figure 9 is a flowchart showing the processing performed in the first embodiment. First, the image acquisition unit 21 acquires a medical image G0 from the storage 13 (step ST1), and the first extraction unit 22 extracts the region of the target organ from the medical image G0 (step ST2). Next, the second extraction unit 23 extracts the region of at least one surrounding organ located around the target organ (step ST3), and the positional relationship derivation unit 24 derives the positional relationship between the target organ and the surrounding organs (step ST4). Subsequently, the compression determination unit 25 determines whether the target organ, i.e., the pancreas 30, is being compressed by the surrounding organs based on the positional relationship derived by the positional relationship derivation unit 24 (step ST5). Then, the display control unit 26 displays the determination result of whether or not the pancreas 30 is being compressed on the display 14 (step ST6), and the processing ends.

[0039] Thus, in this embodiment, the system determines whether the target organ, i.e., the pancreas 30, is being compressed by surrounding organs based on the positional relationship between the target organ and surrounding organs. Therefore, by referring to the determination result, an accurate diagnosis of the target organ can be made.

[0040] Next, a second embodiment of the present disclosure will be described. Figure 10 is a diagram showing the functional configuration of the image processing apparatus according to the second embodiment. In Figure 10, the same reference numerals are used for components identical to those in Figure 3, and detailed explanations are omitted. The image processing apparatus 20A according to the second embodiment differs from the first embodiment in that it further includes a sagging determination unit 27 and an abnormality determination unit 28.

[0041] The atrophy determination unit 27 derives the pancreatic features extracted by the first extraction unit 22 and determines whether or not the target organ (i.e., the pancreas) is atrophied based on the derived features. For this purpose, the atrophy determination unit 27 has a classifier 27A that outputs an evaluation value indicating whether or not the pancreas is atrophied based on the pancreatic features. The classifier 27A is constructed by machine learning a convolutional neural network using multiple training data sets in which the presence or absence of pancreatic atrophy is known. The evaluation value indicating whether or not the pancreas is atrophied, output by the classifier 27A, is a probability that the pancreas is atrophied and is a value between 0 and 1.

[0042] The characteristics of the pancreas include at least one of the following: diameter, size, and texture. The diameter of the pancreas can be measured using the diameter of a cross-section intersecting the pancreas's long axis. Since the diameter of the pancreas differs at each position along the pancreas's long axis, multiple cross-sections intersecting the long axis can be set at predetermined intervals along the pancreas, and representative values ​​of the diameters at these cross-sections (e.g., maximum, minimum, median, and mean) can be used as the diameter of the pancreas. Furthermore, since the cross-sections intersecting the pancreas's long axis are not circular, representative values ​​of the diameters in multiple directions intersecting the pancreas's long axis (e.g., maximum, minimum, median, and mean) can be used as the diameter of the pancreas. The size of the pancreas can be calculated from the number of voxels in the pancreatic region of the medical image G0 and the spacing between voxels. The texture of the pancreas is the pixel value of each pixel of the pancreas in the medical image G0 (CT value in the case of a CT image).

[0043] The atrophy determination unit 27 determines that there is atrophy in the pancreas if the evaluation value output by the classifier 27A is equal to or greater than a predetermined threshold.

[0044] Furthermore, the classifier 27A is not limited to determining the presence or absence of pancreatic atrophy based on the characteristics of the pancreas. The classifier 27A may be constructed to extract pancreatic characteristics from the medical image G0 when it is input and determine the presence or absence of pancreatic abnormalities.

[0045] On the other hand, if the atrophy determination unit 27 determines that there is atrophy in the pancreas, it is not possible to determine whether the atrophy is caused by a disease of the pancreas or by compression from surrounding organs. For this reason, in the second embodiment, if the atrophy determination unit 27 determines that there is atrophy in the pancreas, the compression determination unit 25 determines whether or not there is compression of the pancreas.

[0046] The abnormality detection unit 28 determines that there is no abnormality in the pancreas if the atrophy detection unit 27 determines that there is atrophy in the pancreas and the compression detection unit 25 determines that the pancreas is being compressed, since the atrophy is caused by compression from surrounding organs. If the atrophy detection unit 27 determines that there is atrophy in the pancreas and the compression detection unit 25 determines that the pancreas is not being compressed, the abnormality detection unit 28 determines that there is an abnormality in the pancreas, since the atrophy is caused by a disease of the pancreas. If the atrophy detection unit 27 determines that there is no atrophy in the pancreas, the abnormality detection unit 28 determines that there is no abnormality in the pancreas.

[0047] In the second embodiment, the display control unit 26 displays the determination result from the abnormality determination unit 28 on the display 14. Figure 11 is a diagram showing the display screen of the determination result in the second embodiment. As shown in Figure 11, the display screen 40 shows medical image G0 when an abnormality is determined. Also, in the medical image G0 shown in Figure 11, the pancreas is atrophied but not compressed by surrounding organs, so the determination result 42 of an abnormality is displayed.

[0048] Next, the process performed in the second embodiment will be described. Figure 12 is a flowchart showing the process performed in the second embodiment. First, the image acquisition unit 21 acquires a medical image G0 from the storage 13 (step ST11), and the first extraction unit 22 extracts the region of the target organ from the medical image G0 (step ST12). Next, the atrophy determination unit 27 determines whether or not the target organ, the pancreas 30, has atrophied (step ST13).

[0049] If atrophy is determined to be present (Step ST13: YES), the second extraction unit 23 extracts the region of at least one surrounding organ located around the target organ (Step ST14), and the positional relationship derivation unit 24 derives the positional relationship between the target organ and the surrounding organs (Step ST15). Subsequently, the compression determination unit 25 determines, based on the positional relationship derived by the positional relationship derivation unit 24, whether or not the target organ, i.e., the pancreas 30, is being compressed by the surrounding organs (Step ST16).

[0050] If compression is detected (step ST16: YES), the abnormality detection unit 28 determines that there is no abnormality in the pancreas (step ST17). If compression is detected (step ST16: NO), the abnormality detection unit 28 determines that there is an abnormality in the target organ (step ST18). On the other hand, if atrophy of the target organ is detected (step ST13: NO), the process proceeds to step ST17, where the abnormality detection unit 28 determines that there is no abnormality in the target organ. The display control unit 26 then displays the result of the determination of whether or not there is an abnormality in the target organ on the display 14 (step ST19), and the process ends.

[0051] Thus, in the second embodiment, the presence or absence of atrophy of the target organ is determined, and the abnormality of the target organ is determined according to the presence or absence of atrophy and compression of the target organ. Therefore, if the target organ is atrophied, it is possible to know whether it is due to disease or compression by surrounding organs.

[0052] In addition, in each of the above embodiments, when determining whether or not the target organ is compressed, a medical image G0 may be used in addition to the positional relationship. In this case, the classifier 25A of the compression determination unit 25 is constructed by machine learning to output an evaluation value indicating whether or not the target organ is compressed when the medical image G0 is input in addition to the positional relationship.

[0053] Furthermore, in each of the above embodiments, the compression determination unit 25 determines whether or not the target organ is compressed using the classifier 25A based on the positional relationship, but it is not limited to this. If the positional relationship is the shortest distance between the contours of the target organ and surrounding organs, the system may determine that the target organ is compressed if the representative value of the shortest distance between the target organ and at least one surrounding organ, or the shortest distance between the target organ and all surrounding organs, is less than a predetermined threshold. As the representative value, the average, maximum, minimum, or median of the shortest distance between the target organ and all surrounding organs can be used.

[0054] Furthermore, in each of the above embodiments, the positional relationship derivation unit 24 may derive the distance between the center of gravity of the target organ and the center of gravity of the surrounding organs as the positional relationship, instead of the shortest distance between the contours of the target organ and the surrounding organs.

[0055] Furthermore, while the pancreas is used as the target organ in each of the above embodiments, it is not limited to this. Any organ other than the pancreas, such as the brain, heart, lungs, and liver, can be used as the target organ.

[0056] Furthermore, while CT images are used as medical image G0 in each of the above embodiments, the invention is not limited to this. Any image can be used as medical image G0, including 3D images such as MRI images, or radiographic images obtained by simple radiography.

[0057] Furthermore, in each of the above embodiments, the hardware structure of the Processing Unit that performs various processes such as the image acquisition unit 21, the first extraction unit 22, the second extraction unit 23, the positional relationship derivation unit 24, the compression determination unit 25, the display control unit 26, the atrophy determination unit 27, and the abnormality determination unit 28 can be the various processors shown below. As mentioned above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as a Programmable Logic Device (PLD), which is a processor whose circuit configuration can be changed after manufacturing, such as an FPGA (Field Programmable Gate Array), and a dedicated electrical circuit, which is a processor with a circuit configuration specifically designed to perform a particular process, such as an ASIC (Application Specific Integrated Circuit).

[0058] A single processing unit may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs or a combination of a CPU and an FPGA). Alternatively, multiple processing units may be composed of a single processor.

[0059] Examples of configuring multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software combine to form a single processor, as exemplified by client and server computers, and this processor functions as multiple processing units. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as exemplified by System-on-a-Chip (SoC). Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned processors.

[0060] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits (Circuitry) that combine circuit elements such as semiconductor elements. [Explanation of symbols]

[0061] 1 Computer 2. Imaging device 3. Image storage server 4 Network 11 CPU 12 Image Processing Programs 13 Storage 14 displays 15 Input Devices 16 memory 17 Network Interface 18 bus 20,20A Image Processing Device 21 Image acquisition unit 22 1st extraction part 23 Second extraction part 24 Positional relationship derivation section 25 Compression detection section 25A discriminator 26 Display Control Unit 27 Atrophy determination section 27A Discriminator 28 Abnormality determination section 30 Pancreas 31 Stomach 32 Duodenum 33 Liver 40 display screen 41,42 Judgment result D0 fault image G0 Medical Images

Claims

1. Equipped with at least one processor, The aforementioned processor, Extract the region of the target organ from the medical image, From the aforementioned medical image, extract the region of at least one surrounding organ located around the target organ. The positional relationship between the target organ and the surrounding organs is derived, An image processing device that determines whether or not the target organ is being compressed by the surrounding organs based on the aforementioned positional relationship.

2. The image processing apparatus according to claim 1, wherein the processor further determines whether or not the target organ has atrophied.

3. The image processing apparatus according to claim 2, wherein the processor determines whether the target organ is being compressed by surrounding organs when it is determined that the target organ is atrophied.

4. The processor determines that there is no abnormality in the target organ if it determines that there is no atrophy in the target organ. If the target organ is atrophied and is being compressed by the surrounding organs, it is determined that there is no abnormality in the target organ. The image processing apparatus according to claim 3, which determines that there is an abnormality in the target organ when the target organ is atrophied and the target organ is not compressed by the surrounding organs.

5. The image processing apparatus according to any one of claims 1 to 4, wherein the processor determines whether the target organ is being compressed by the surrounding organs based on the medical image in addition to the positional relationship.

6. Extract the region of the target organ from the medical image, From the aforementioned medical image, extract the region of at least one surrounding organ located around the target organ. The positional relationship between the target organ and the surrounding organs is derived, An image processing method for determining whether the target organ is being compressed by surrounding organs based on the aforementioned positional relationship.

7. Procedures for extracting the region of the target organ from medical images, A procedure for extracting the region of at least one surrounding organ located around the target organ from the aforementioned medical image, A procedure for deriving the positional relationship between the target organ and the surrounding organs, An image processing program that causes a computer to perform a procedure for determining whether or not the target organ is being compressed by the surrounding organs based on the aforementioned positional relationship.

Images