JP2011177241A - Medical image display controller and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To support the efficient finding of an abnormal part in medical image diagnosing by a doctor. <P>SOLUTION: By an image compression processing part 22, compressed tomographic images subjected to compression processing are generated for a plurality of kinds of tomographic images. By a feature extraction part 26, the features of division areas wherein the compressed tomographic image is divided are extracted. Whether each division area of each fault is an abnormal part is determined by an abnormality determination part 28, and the pattern of the abnormal part is generated for each fault by a pattern generation part 30. Images wherein the generated pattern is superposed on the compressed tomographic image are continuously displayed on a touch panel 14 for each fault, by an animation generating unit 36, and input from a user is received by an input reception part 37. By a 3D diagram generation part 38, a 3D diagram indicating the compressed tomographic image corresponding to the fault when receiving the input and a determination result by the abnormality determination part 28 is displayed on the touch panel 14. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a medical image display control device and program, and more particularly, to a medical image display control device and program for displaying a tomographic image representing a body part such as an organ to be diagnosed on a display device.

  It is not necessary to mention that the biggest cause of death for Japanese people, "cancer", is an important social problem that threatens the safety and security of people's lives. Efforts for early diagnosis of cancer from the viewpoints of medicine, pharmacy, science, and engineering have been actively conducted both in Japan and overseas. In response to this, “Manufacturing” as an industry that Japan excels at, has strengthened the cooperation system with medicine, and research and development of various diagnostic agents, devices, and diagnostic equipment has advanced remarkably. On the other hand, the information obtained from various diversified drugs and highly developed diagnostic equipment is overflowing as a raw voice from doctors engaged in cancer treatment and treatment in the field, and the amount of information seen by doctors Is enormous, and it is said that the process is becoming extremely complicated (Non-patent Document 1).

Atsuko Imamura, Kazuko Kobayashi, Yasuo Nakajima, “Degree of Satisfaction of Diagnostic Imaging Doctors at CT and MRI Installation Facilities”, Japanese Radiology Specialist Society, Nos. 170, 2009

  In view of the circumstances as described above, an object of the present invention is to provide a medical image display control device and a program for assisting in efficiently finding an abnormal site in medical image diagnosis by a doctor.

  In order to achieve the above object, a medical image display control device according to the present invention is captured by a plurality of types of medical imaging devices that capture tomographic images representing a plurality of tomograms in a body part such as an organ to be diagnosed. Image processing means for generating a plurality of types of compressed tomographic images obtained by performing data compression processing on each of the plurality of types of tomographic images, and a body such as an organ represented by the compressed tomographic images for the plurality of types of compressed tomographic images And a plurality of divided regions obtained by dividing the compressed tomographic image with respect to each of the plurality of types of compressed tomographic images. The feature extraction means for extracting each feature of each of the tomograms, and for each of the divided regions of each tomography, the divided regions correspond to the positions among the plurality of types of compressed tomographic images corresponding to the positions. An abnormality determining means for determining whether or not a portion represented by the divided region of a body part such as the organ is an abnormal portion based on the feature extracted for each divided region; A pattern generating means for generating a visual pattern perceived from the divided area determined to be present for each tomography, and the pattern of each tomogram generated by the pattern generating means on the compressed tomographic image of each tomography Continuous display control means for continuously displaying superimposed images on the display device for each slice, and input from the user when the superimposed images are continuously displayed by the continuous display control means An input receiving unit, and the compressed tomographic image corresponding to the tomogram represented by the superimposed image displayed when the input is received by the input receiving unit Is configured three-dimensional image representing the result of the determination for each of the divided regions of the compressed tomographic image, a three-dimensional display control means for displaying on said display device, including by the abnormality determining means.

  The program according to the present invention causes a computer to each of a plurality of types of tomographic images captured by a plurality of types of medical imaging devices that capture a plurality of tomographic images representing a plurality of tomograms in a body part such as an organ to be diagnosed. On the other hand, image processing means for generating a plurality of types of compressed tomographic images subjected to data compression processing, so that the positions of body parts such as organs represented by the compressed tomographic images correspond to the plurality of types of compressed tomographic images, Position associating means for associating positions on the compressed tomographic image; and feature extracting means for extracting each feature of a plurality of divided regions obtained by dividing the compressed tomographic image for each of the plurality of types of compressed tomographic images; For each of the divided areas of each slice, extraction is performed for each divided area whose position corresponds to the divided area between the plurality of types of compressed tomographic images corresponding to the position. On the basis of the characteristic, abnormality determination means for determining whether or not the part represented by the divided region of the body part such as the organ is an abnormal part, and the division determined to be the abnormal part A pattern generating unit that generates a visual pattern perceived from the region for each tomographic image, and a superimposed image obtained by superimposing the pattern of each tomographic image generated by the pattern generating unit on the compressed tomographic image of each tomographic image, Continuous display control means for continuously displaying a slice on a display device, input receiving means for receiving an input from a user when the superimposed image is continuously displayed by the continuous display control means, and the input receiving means The compressed tomographic image corresponding to the tom represented by the superimposed image that was displayed when the input was received, and the abnormality determining means A three-dimensional image representing the result of the determination for each of the divided regions of the reduced tomographic image, a program for functioning as a 3-dimensional display control means for displaying on said display device.

  According to the present invention, each of a plurality of types of tomographic images captured by a plurality of types of medical imaging devices that capture a tomographic image representing a plurality of tomograms in a body part such as an organ to be diagnosed by an image processing means. In contrast, a plurality of types of compressed tomographic images subjected to data compression processing are generated.

  Then, the position correlating means associates positions on the compressed tomographic image such that the positions of the body parts such as the organ represented by the compressed tomographic image correspond to the plurality of types of compressed tomographic images, and the feature extracting means Thus, for each of a plurality of types of compressed tomographic images, the characteristics of each of the plurality of divided regions obtained by dividing the compressed tomographic image are extracted.

  Based on the feature extracted by the abnormality determination means for each of the divided regions of each tomographic region, the divided regions corresponding to the divided regions and the positions among the plurality of types of compressed tomographic images corresponding to the positions. It is determined whether or not the part represented by the divided region of the body part such as an organ is an abnormal part. A visual pattern perceived from the divided area determined to be an abnormal part is generated for each slice by the pattern generation means.

  Then, the continuous display control means continuously displays a superimposed image obtained by superimposing each tomographic pattern generated by the pattern generating means on the compressed tomographic image of each tomographic image on the display device for each tomogram, and the input receiving means. Thus, when the superimposed image is continuously displayed by the continuous display control means, an input from the user is accepted. The compressed tomographic image corresponding to the tom represented by the superimposed image displayed when the input is accepted by the input accepting unit is determined by the three-dimensional display control unit, and each divided region of the compressed tomographic image is determined by the abnormality determining unit. A three-dimensional image representing the determination result is displayed on the display device.

  In this way, a pattern representing an abnormal location determined from a plurality of types of tomographic images is displayed superimposed on the compressed tomographic image of each tomographic image, and the tomographic compressed tomographic image and the abnormal location corresponding to the input from the user for the display are displayed. By displaying a three-dimensional image representing the determination result, it is possible to assist in efficiently finding an abnormal site in medical image diagnosis by a doctor.

  The medical image display control apparatus according to the present invention further includes a color imparting unit that imparts a predetermined color to the pattern generated by the pattern generation unit, and the continuous display control unit is provided with the predetermined color by the color imparting unit. The superimposed image obtained by superimposing the pattern on the compressed tomographic image can be continuously displayed on the display device for each tomographic image. Thereby, it can assist so that an abnormal site | part can be discovered more efficiently.

  The medical image display control apparatus according to the present invention further includes a storage control unit that stores in the storage unit a tomographic image before compression corresponding to a tomogram represented by the superimposed image displayed when the input is received by the input receiving unit. Can be included.

  The program of the present invention can be provided by being stored in a recording medium.

  As described above, according to the medical image display control apparatus and program of the present invention, while displaying a pattern representing an abnormal location determined from a plurality of types of compressed tomographic images superimposed on a tomographic image of each tomographic image, By displaying a compressed tomographic image of a tomogram corresponding to an input from the user for display and a determination result of an abnormal part, an abnormal part can be efficiently found in medical image diagnosis by a doctor. The effect that it can support is acquired.

It is the schematic which shows the structure of the medical image display system which concerns on embodiment of this invention. It is an image figure which shows the frequency division of a spatial frequency image. It is a figure which shows the example of a neural network. It is a figure for demonstrating the factor of the proximity in the law of Pregnants. It is a figure for demonstrating the similar factor in the law of Pregnants. It is a figure for demonstrating the factor of the closure in a Pregnant's law. It is an image figure which shows the example of 3D diagram. It is a flowchart which shows the content of the medical image display process routine of the computer which concerns on embodiment of this invention. It is an image figure which shows the space division of a tomographic image.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the present embodiment, a case where the present invention is applied to a medical image display system for supporting medical image diagnosis by a user who is a doctor will be described as an example.

  As shown in FIG. 1, a medical image display system 10 according to an embodiment of the present invention receives a plurality of types of tomographic images obtained from a plurality of types of medical imaging devices such as MRI, CT, and PET as medical images. The computer 12 which produces | generates the image for a diagnosis and displays it on the touch panel 14 and the touch panel 14 are provided.

  The touch panel 14 displays the display data output from the computer 12 and outputs an operation input by the user to the computer 12.

  The computer 12 includes a CPU, a ROM, a RAM, and an HDD, and a program for a medical image display processing routine to be described later is stored in the HDD.

  The computer 12 is functionally configured as follows. As shown in FIG. 1, the computer 12 includes an image acquisition unit 20, an image compression processing unit 22, a registration processing unit 24, a feature extraction unit 26, an abnormality determination unit 28, a pattern generation unit 30, a normal pattern acquisition unit 32, and coloring. A processing unit 34, an animation generation unit 36, an input reception unit 37, a 3D diagram generation unit 38, and a data storage unit 40 are provided. The image compression processing unit 22 is an example of an image processing unit, and the animation generation unit 36 is an example of a continuous display control unit. Further, the coloring processing unit 34 is an example of a color providing unit, and the 3D diagram generation unit 38 is an example of a three-dimensional display control unit. The data storage unit 40 is an example of a storage control unit, and the computer 12 is an example of a medical image display control device.

  DICOM (Digital Imaging and Communication in Medicine) data captured by multiple types of medical imaging devices such as CT, MRI, and PET that captures tomographic images representing multiple tomographic images of a body part such as an organ to be diagnosed Are input to the computer 12 by the operator, and the image acquisition unit 20 acquires the multiple types of tomographic images (original data) and temporarily stores them in the memory.

  The image compression processing unit 22 cuts out a portion representing a body part such as an organ to be diagnosed from each tomographic image, and performs wavelet transform or DCT transform on the cut out image to obtain the obtained spatial frequency Frequency division is performed on the image as shown in FIG. In addition, the image compression processing unit 22, for example, compresses tomographic images obtained by compressing image data by performing data compression processing that removes high-frequency components from the result of frequency division and performs Wavelet inverse transform or DCT inverse transform. Is generated. At this time, for example, by using a lifting structure, a compressed tomographic image in which image data is compressed by reversible conversion may be generated, or a compressed tomographic image in which image data is compressed by irreversible conversion is generated. You may do it. Further, the image compression processing unit 22 may perform noise removal processing for better compression when performing Wavelet conversion or DCT conversion and compression processing.

  The alignment processing unit 24 performs feature point extraction such as edge extraction on a plurality of types of compressed tomographic images, and associates the extracted feature points between the plurality of types of compressed tomographic images, thereby compressing a plurality of types of compression. Alignment processing for associating the position of a body part such as an organ represented by the tomographic image is performed. Based on the result of the alignment process, the alignment processing unit 24 associates the divided areas corresponding to the positions among the plurality of types of compressed tomographic images with respect to the divided areas obtained by dividing the compressed tomographic images. The data which shows the correspondence of the division area matched between the said compression tomographic images is produced | generated. Note that the above-described alignment is a three-dimensional position alignment including a tomographic alignment, and represents the same tomography among a plurality of types of compressed tomographic images and is on the same tomography (two-dimensionally). The divided areas representing the positions of the areas are associated.

  Hereinafter, although the process performed about a certain fault is demonstrated, each process is performed about each fault.

  The feature extraction unit 26 extracts each feature of the plurality of divided regions for each of the plurality of types of compressed tomographic images. The features to be extracted are, for example, whether or not the shape is prepared, whether the signal is strong, whether the signal is uniform, whether the distribution is single or frequent. These feature extraction methods are performed by an individual extraction method. In addition, processing is performed using a separate extraction method for a real organ such as a brain, liver, or kidney and a tissue having a luminal structure such as a digestive tract or a blood vessel.

  The abnormality determination unit 28, for each of the plurality of divided regions, based on the features extracted for each divided region corresponding to the position among the plurality of types of compressed tomographic images, It is determined whether or not the part is an abnormal part. For example, it is determined whether or not it is an abnormal location by a neural network as shown in FIG. 3, a fuzzy vector quantization method, a method solved by an optimization problem such as GA or Particle Swam Optimization.

  The pattern generation unit 30 uses a Pregnant's law (proximity (see FIG. 4), similarity (see FIG. 5), closure (see FIG. 5), which is a law for perceiving gestalt from an image representing the determination results of abnormal locations for a plurality of divided regions. According to the factor (see FIG. 6), a pattern of perceived visual abnormal points is generated.

  The normal pattern acquisition unit 32 acquires a normal pattern image stored in advance in the HDD. The pattern image at the normal time is an image representing a pattern of abnormal portions obtained when the above-described processes are similarly performed on a plurality of types of tomographic images obtained by imaging a body part such as a normal organ. It is generated in advance and stored in the HDD.

  The coloring processing unit 34 applies a semi-transparent color to the abnormal part pattern generated by the pattern generation unit 30, and also applies an abnormality to the normal pattern image acquired by the normal pattern acquisition unit 32. A semi-transparent color is given to the pattern of the location.

  Here, the assigned color is determined in consideration of an efficient balance of saturation, brightness, and hue in order to improve accessibility. For example, the colors are determined so as to reduce oversight and illusion by considering the balance of adjacent colors using colors that jump into the eyes or colors that are shifted from a perfect complementary relationship.

  In addition, information to be known may be arranged and expressed by performing color settings in accordance with contents to be displayed such as a medical condition, normality, and abnormality.

  Further, by clarifying the balance between the colors used for the pattern and the colors used for the display screen displayed on the touch panel 14, the things to be viewed and the operations to be performed may be efficiently separated.

  The animation generating unit 36 superimposes a colored pattern on any one type of compressed tomographic image and superimposes the colored normal pattern on the same type of normal compressed tomographic image. Animation data for continuously displaying the superposed image for each slice is generated and output to the touch panel 14, and the animated superposed image is displayed on the touch panel 14.

  The animation generation unit 36 may output a warning sound from a speaker (not shown) when displaying a superimposed image of a tomography in which an abnormal part pattern exists. By voice announcements, changes that are often overlooked by vision or abnormalities judged by the computer are automatically notified, which can be used to reduce the diagnosis of the doctor.

  The doctor sees the animated superimposed image displayed on the touch panel 14 and, if there is a tomographic section to be carefully diagnosed, can input a position (tomographic section) to be diagnosed by performing an input operation on the touch panel 14 and accepting the input. The unit 37 receives the operation input of the touch panel 14.

  Further, the input receiving unit 37 receives input operations such as a change in animation speed or the like, a pause at a place that must be carefully determined, and an enlargement instruction by pinch.

  Note that an interface that can be treated sensibly on the display screen of the touch panel 14 may be constructed by using the theory of (Affordance), which is the field of cognitive science. In addition to CT and other tomographic images, colors and animations are added to the icons for prompting the operation, making it easier to operate, reducing operational errors, and discovering pathogens. Good procedures may be supported. In addition, a function of adding a comment to the abnormal part may be provided, or a thumbnail display of the compressed tomographic image may be performed. In addition, two display screens, an input liquid crystal screen and a viewer liquid crystal screen, may be prepared as the display screen on the touch panel 14 and displayed in a mirroring manner.

  The 3D diagram generation unit 38 determines the compressed tomographic image corresponding to the tom represented by the superimposed image displayed when the input is received by the touch panel 14, and the abnormal determination unit 28 determines each divided region of the compressed tomographic image. A three-dimensional image (3D diagram) as shown in FIG. 7 is generated by superimposing the three-dimensional symbolized image representing the determination result and displayed on the touch panel 14. As a result, the doctor can visually recognize the peculiar part in a plural manner.

  The data storage unit 40 stores a plurality of types of tomographic images (original data) before compression corresponding to the tomographic image represented by the superimposed image displayed when the input is received by the touch panel 14 from a temporarily stored memory. Acquire it and store it in the HDD.

  Next, the operation of the medical image display system 10 according to the present embodiment will be described.

  First, an operator uses a plurality of types of medical imaging devices such as CT, MRI, and PET to capture a plurality of types of tomographic images representing a body part such as an organ to be diagnosed for each of a plurality of tomographic images. A plurality of types of tomographic images of each tomographic image are input to the computer 12.

  When an instruction is input through the touch panel 14 to display a medical image from a doctor who performs a medical image diagnosis, the computer 12 executes a medical image display processing routine shown in FIG.

  First, in step 100, a plurality of inputted tomographic images are acquired for each tomographic image and temporarily stored in a memory. In step 102, an image representing a body part such as an organ to be diagnosed is cut out from each tomographic image. In the next step 104, a plurality of types of compressed tomographic images are obtained by performing spatial frequency transformation, data compression processing, spatial frequency inverse transformation, and noise removal processing on each of the cutout images obtained in step 102. Generate for each fault.

  In step 106, each compressed tomographic image is divided into a plurality of divided areas, and the divided areas are associated with each other between a plurality of types of compressed tomographic images to perform alignment. In the next step 108, feature extraction is performed for each divided region of each compressed tomographic image, and in step 110, for each of the plurality of divided regions, divided regions of a plurality of types of compressed tomographic images associated with the divided region. Based on the feature extracted for each of the above, it is determined whether or not the body part such as the organ represented by the divided region is an abnormal part. The determination of the abnormal location in step 110 is performed for each fault.

  In step 112, a pattern of the divided region of the abnormal part is generated for each slice based on the determination result for each of the plurality of divided regions determined in step 110. In step 114, an abnormal portion pattern obtained from a tomographic image representing a body part such as a normal organ prepared in advance is acquired for each tomography.

  In the next step 116, the coloring process is performed on each tomographic pattern generated in step 114 and each tomographic pattern obtained in step 114. In step 118, the tomographic images obtained by superimposing the tomographic patterns to which the coloring process has been applied in step 116 on the corresponding tomographic compressed tomographic images are converted into diagnostic images and normal images. Animation data that is animated so that each slice is continuously displayed is generated and output to the touch panel 14 for display.

  As a result, on the touch panel 14, the superimposed images of the respective slices are arranged for the diagnosis target image and the normal image and displayed continuously.

  In step 120, it is determined whether or not an input operation on the touch panel 14 has been performed by the doctor. If there is an input operation for instructing the diagnosed tomography, the animation display is stopped, and the process proceeds to step 122. Data corresponding to the tomogram instructed by the input operation on the touch panel 14 and indicating the determination result of the abnormal part for each divided region in step 110 is acquired. In step 124, any type of compressed tomographic image corresponding to the tomographic image instructed by the input operation on the touch panel 14 is acquired from the memory.

  In step 126, a three-dimensional symbolized image representing data indicating the determination result of the abnormal part acquired in step 122 is generated, and a 3D diagram in which the compressed tomographic image acquired in step 124 is superimposed is generated. Display on the touch panel 14. In step 128, a plurality of types of tomographic images corresponding to the tomogram instructed by the input operation of the touch panel 14 and acquired in step 100 are acquired from the memory, stored in the HDD, and medical image display processing is performed. End the routine.

  If it is desired to continue diagnosis for other faults, the display of animation is resumed in step 118, and the processing in steps 120 to 128 may be performed in the same manner.

  As described above, according to the medical image display system according to the embodiment of the present invention, a pattern representing an abnormal location determined based on a plurality of types of compressed tomographic images such as CT, MRI, and PET is displayed for each tomographic image. By displaying a 3D diagram representing the compressed tomographic image of the tomography corresponding to the input operation from the doctor for the display and the determination result of the abnormal part, the multidimensional tertiary is displayed. Since the doctor can efficiently recognize the original information, the medical image diagnosis by the doctor can be supported so that the abnormal site can be found efficiently. Moreover, it can assist so that an abnormal site | part can be discovered more efficiently by giving a color to the pattern showing an abnormal location.

  In addition, by presenting medical information to a doctor in an easy-to-understand manner, it is possible to detect a lesion early while reducing the burden on the doctor.

  In addition, by generating animation data that continuously displays an image obtained by superimposing the compressed tomographic image of each tomography and the abnormal part, it is possible to make the change of the abnormal part difficult to see easy to see.

  In addition, by displaying a 3D diagram in which information related to abnormal point determination is displayed in an easy-to-understand manner together with a specific tomographic image, it is possible to express where the problem is.

  In addition, by using devices that can perform sensory operations such as touch panels as input devices and using appropriate intuitive operation feelings (slides, pinches, taps, double taps), etc., doctors can quickly become a problem (pathogenic Etc.) can be reached.

  In the above embodiment, the case where the touch panel type hardware input method is used has been described as an example. However, the present invention is not limited to this, and deep diagnosis is performed using an input operation terminal such as a mouse or a keyboard. The fault to be performed may be indicated.

  In addition, although the case where the frequency compression is performed on the tomographic image and the data compression process is performed has been described as an example, the present invention is not limited to this, and as shown in FIG. Thus, data compression processing may be performed.

  In addition, in the case of displaying an animated image or a 3D diagram, the case of displaying using one type of compressed tomographic image has been described as an example. However, the present invention is not limited to this, and two or more types of compressed tomographic images are synthesized. The synthesized image may be used to display an animated image or 3D diagram.

DESCRIPTION OF SYMBOLS 10 Medical image display system 12 Computer 14 Touch panel 20 Image acquisition part 22 Image compression process part 24 Position adjustment process part 26 Feature extraction part 28 Abnormality determination part 30 Pattern generation part 32 Normal pattern acquisition part 34 Coloring process part 36 Animation generation part 37 Input Reception unit 38 3D diagram generation unit 40 Data storage unit

Claims (4)

Compression obtained by performing data compression processing on each of a plurality of types of tomographic images captured by a plurality of types of medical imaging devices that capture a plurality of types of tomographic images representing a plurality of tomograms in a body part such as an organ to be diagnosed Image processing means for generating a plurality of types of tomographic images;
Position association means for associating positions on the compressed tomographic image such that positions of body parts such as organs represented by the compressed tomographic image correspond to the plurality of types of compressed tomographic images;
For each of the plurality of types of compressed tomographic images, feature extraction means for extracting the characteristics of each of the plurality of divided regions obtained by dividing the compressed tomographic image;
For each of the divided regions of each tomography, based on the features extracted for each of the divided regions whose positions correspond to the divided regions between the plurality of types of compressed tomographic images corresponding to the positions, An abnormality determining means for determining whether or not the part represented by the divided region of the part is an abnormal part;
Pattern generating means for generating a visual pattern perceived from the divided area determined to be the abnormal part for each tomography;
Continuous display control means for continuously displaying a superimposed image obtained by superimposing the pattern of each tomogram generated by the pattern generation means on the compressed tomographic image of each tomography on a display device;
An input receiving unit that receives an input from a user when the superimposed image is continuously displayed by the continuous display control unit;
The compressed tomographic image corresponding to the tom represented by the superimposed image displayed when the input is accepted by the input accepting unit, and the determination result determined for each divided region of the compressed tomographic image by the abnormality determining unit; 3D display control means for displaying a 3D image representing the above on the display device;
A medical image display control device. Further comprising color imparting means for imparting a predetermined color to the pattern generated by the pattern generating means;
The continuous display control means causes a display device to continuously display a superimposed image obtained by superimposing the pattern, to which the predetermined color is given by the color giving means, on the compressed tomographic image. The medical image display control device described.   3. The storage control unit according to claim 1, further comprising: a storage control unit that stores the tomographic image before compression corresponding to the tom represented by the superimposed image displayed when the input is received by the input receiving unit. Medical image display control device. Computer
Compression obtained by performing data compression processing on each of a plurality of types of tomographic images captured by a plurality of types of medical imaging devices that capture a plurality of types of tomographic images representing a plurality of tomograms in a body part such as an organ to be diagnosed Image processing means for generating a plurality of types of tomographic images;
Position association means for associating positions on the compressed tomographic image such that positions of body parts such as organs represented by the compressed tomographic image correspond to the plurality of types of compressed tomographic images;
For each of the plurality of types of compressed tomographic images, feature extraction means for extracting the characteristics of each of a plurality of divided regions obtained by dividing the compressed tomographic image;
For each of the divided regions of each tomography, based on the features extracted for each of the divided regions whose positions correspond to the divided regions between the plurality of types of compressed tomographic images corresponding to the positions, Abnormality determination means for determining whether or not the portion represented by the divided region of the part is an abnormal part,
Pattern generating means for generating a visual pattern perceived from the divided region determined to be the abnormal part for each tomography;
Continuous display control means for continuously displaying a superimposed image obtained by superimposing the pattern of each tomogram generated by the pattern generation means on the compressed tomographic image of each tomography on a display device;
When the superimposed image is continuously displayed by the continuous display control unit, an input receiving unit that receives an input from a user, and the superimposed image that is displayed when an input is received by the input receiving unit is 3D display control means for causing the display device to display a 3D image representing the compressed tomographic image corresponding to the tomogram to be represented and a determination result determined for each divided region of the compressed tomographic image by the abnormality determination means. A program to make it work.

Images