Endoscopic examination support device, endoscopic examination support method, and program

Abstract

Provided is an endoscopic examination assistance device, wherein a video acquisition means acquires an endoscopic video taken by an endoscope. A lesion detection means detects a lesion candidate from the endoscopic video. A heat map generation means generates a heat map expressing the lesion possibility of the lesion candidate contained in the endoscopic video. A display control means displays a lesion position on a frame of the endoscopic video on the basis of the lesion candidate and the heat map.

Description

[Technical Field]

[0001] The present disclosure relates to processing images related to endoscopy. [Background technology]

[0002] In endoscopic examinations, there is a technology that detects lesions from endoscopic images and superimposes graphics or the like on the endoscopic images to indicate the position and size of the detected lesion, but there is a problem that the endoscopic images become difficult to see as a result of the graphics or the like being superimposed.Patent Document 1 describes a method of superimposing a marker surrounding the lesion on the observation image when a lesion is detected, depending on the risk of overlooking the lesion, or a method of displaying a marker to surround the periphery of the observation image. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. WO2020 / 110214 Summary of the Invention [Problem to be solved by the invention]

[0004] However, even with Patent Document 1, it is not always possible to show the position and size of a lesion without superimposing a figure or the like on an endoscopic image.

[0005] One object of the present disclosure is to provide an endoscopic examination support device that is capable of grasping the position and size of a lesion. [Means for solving the problem]

[0006] According to one aspect of the present disclosure, an endoscopic examination support device includes: an image acquisition means for acquiring an endoscopic image captured by an endoscope; a lesion detection means for detecting lesion candidates from the endoscopic video; a heat map generating means for generating a heat map in which the lesion possibility of the lesion candidate included in the endoscopic image is expressed by color; a display control means for displaying a lesion position on a frame of the endoscopic image based on the lesion candidate and the heat map; Equipped with.

[0007] In another aspect of the present disclosure, Computer-implemented The endoscopic examination support method is Acquire endoscopic images captured by the endoscope, detecting a lesion candidate from the endoscopic image; generating a heat map that represents the lesion possibility of the lesion candidate included in the endoscopic image using color; Based on the lesion candidate and the heat map, the lesion position is displayed in a frame on the endoscopic image.

[0008] In yet another aspect of the present disclosure, program teeth, Acquire endoscopic images captured by the endoscope, detecting a lesion candidate from the endoscopic image; generating a heat map that represents the lesion possibility of the lesion candidate included in the endoscopic image using color; The computer is caused to execute a process of displaying the lesion position in a frame on the endoscopic image based on the lesion candidate and the heat map. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to grasp the position and size of a lesion without blocking part of the endoscopic image. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a schematic configuration of an endoscopic examination system. [Figure 2] FIG. 2 is a block diagram showing the hardware configuration of the endoscopic examination support device. [Figure 3] FIG. 2 is a block diagram showing the functional configuration of the endoscopic examination support device. [Figure 4] FIG. 10 is a diagram illustrating an example of a method for generating an indicator. [Figure 5] FIG. 10 is a diagram showing a display example of the endoscopic examination support device. [Figure 6] FIG. 10 is a diagram showing another display example of the endoscopic examination support device. [Figure 7] FIG. 10 is a diagram showing another display example of the endoscopic examination support device. [Figure 8] 10 is a flowchart of a display process performed by the endoscopic examination support device. [Figure 9] FIG. 10 is a block diagram showing the functional configuration of the endoscopic examination support device of the second embodiment. [Figure 10] 10 is a flowchart of processing by the endoscopic examination support device of the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, preferred embodiments of the present disclosure will be described with reference to the drawings. First Embodiment [System Configuration] Figure 1 shows the schematic configuration of an endoscopic examination system 100. The endoscopic examination system 100 detects lesions during examination (including treatment) using an endoscope, and displays an indicator showing the location and size of the lesion on a frame of the display screen of the endoscopic image. This allows the doctor to grasp the location and size of the lesion without partially obstructing the endoscopic image.

[0012] As shown in FIG. 1, the endoscopic examination system 100 mainly includes an endoscopic examination support device 1, a display device 2, and an endoscope 3 connected to the endoscopic examination support device 1.

[0013] The endoscopic examination support device 1 acquires images (i.e., video images; hereinafter, also referred to as "endoscopic video images Ic") captured by the endoscope 3 during endoscopic examination from the endoscope 3, and displays display data on the display device 2 for the examiner performing the endoscopic examination to check. Specifically, the endoscopic examination support device 1 acquires video images of the inside of organs captured by the endoscope 3 during endoscopic examination as the endoscopic video images Ic. The endoscopic examination support device 1 extracts still images (frame images) from the endoscopic video images Ic and detects lesions using AI (Artificial Intelligence). Furthermore, when a lesion is detected from a frame image using AI, the endoscopic examination support device 1 generates a heat map based on the frame image. The endoscopic examination support device 1 generates an indicator showing the position and size of the lesion from the heat map. The endoscopic examination support device 1 then generates display data including the endoscopic video images Ic, the heat map, the indicator, etc.

[0014] The display device 2 is a display or the like that displays an image based on a display signal supplied from the endoscopic examination support device 1.

[0015] The endoscope 3 mainly comprises an operating section 36 for the examiner to input instructions such as air supply, water supply, angle adjustment, and photography instructions, a flexible shaft 37 that is inserted into the subject's organ to be examined, a tip section 38 that incorporates a photography section such as a micro-imaging element, and a connection section 39 for connecting to the endoscopic examination support device 1.

[0016] [Hardware configuration] 2 shows the hardware configuration of the endoscopic examination support device 1. The endoscopic examination support device 1 mainly includes a processor 11, a memory 12, an interface 13, an input unit 14, a light source unit 15, a sound output unit 16, and a database (hereinafter referred to as "DB") 17. These elements are connected via a data bus 19.

[0017] The processor 11 executes predetermined processing by executing programs stored in the memory 12. The processor 11 is a processor such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a TPU (Tensor Processing Unit). The processor 11 may be composed of multiple processors. The processor 11 is an example of a computer.

[0018] The memory 12 is composed of various volatile memories used as working memories, such as RAM (Random Access Memory) and ROM (Read Only Memory), and nonvolatile memories that store information necessary for the processing of the endoscopic examination support device 1. The memory 12 may include an external storage device such as a hard disk connected to or built into the endoscopic examination support device 1, or may include a storage medium such as a removable flash memory or disk medium. The memory 12 stores programs that enable the endoscopic examination support device 1 to execute each process in this embodiment.

[0019] The memory 12 also temporarily stores a series of endoscopic images Ic captured by the endoscope 3 during the endoscopic examination under the control of the processor 11. The memory 12 also temporarily stores still images acquired from the endoscopic images Ic during the endoscopic examination. These images are stored in the memory 12 in association with, for example, the subject's identification information (e.g., patient ID), timestamp information, etc.

[0020] The interface 13 acts as an interface between the endoscopic examination support device 1 and an external device. For example, the interface 13 supplies the display data Id generated by the processor 11 to the display device 2. The interface 13 also supplies illumination light generated by the light source unit 15 to the endoscope 3. The interface 13 also supplies an electrical signal indicating the endoscopic video Ic supplied from the endoscope 3 to the processor 11. The interface 13 may be a communication interface such as a network adapter for wired or wireless communication with an external device, or may be a hardware interface compliant with USB (Universal Serial Bus), SATA (Serial AT Attachment), or the like.

[0021] The input unit 14 generates an input signal based on an operation by the examiner. The input unit 14 is, for example, a button, a touch panel, a remote controller, or a voice input device. The light source unit 15 generates light to be supplied to the tip 38 of the endoscope 3. The light source unit 15 may also have a built-in pump for sending water or air to be supplied to the endoscope 3. The sound output unit 16 outputs sound based on the control of the processor 11.

[0022] The DB 17 stores endoscopic images acquired by past endoscopic examinations of the subject and lesion information. The lesion information includes lesion images and related information. The lesions include polyps (protruding lesions). The DB 17 may include an external storage device such as a hard disk connected to or built into the endoscopic examination support device 1, or may include a storage medium such as a removable flash memory. Instead of providing the DB 17 within the endoscopic examination system 100, the DB 17 may be provided in an external server, and the lesion information may be obtained from the server via communication.

[0023] [Function Configuration] 3 is a block diagram showing the functional configuration of the endoscopic examination support device 1. The endoscopic examination support device 1 functionally includes an interface 13, a lesion detection unit 21, a heat map generation unit 22, and a display control unit 23.

[0024] An endoscopic video Ic is input to the endoscopic examination support device 1 from the endoscope 3. The endoscopic video Ic is input to the interface 13. The interface 13 extracts frame images (hereinafter also referred to as "endoscopic images") from the input endoscopic video Ic, and outputs them to the lesion detection unit 21 and the heat map generation unit 22. The interface 13 also outputs the input endoscopic video Ic to the display control unit 23.

[0025] Lesion detection unit 21 performs image analysis based on the endoscopic image input from interface 13 and determines whether or not the endoscopic image contains a lesion. Lesion detection unit 21 detects lesion-like areas (hereinafter also referred to as "lesion candidates") contained in the endoscopic image using a previously prepared image recognition model or the like. This image recognition model is a model that has been trained in advance to estimate lesion candidates contained in the endoscopic image, and is hereinafter also referred to as the "lesion detection model." If lesion detection unit 21 detects a lesion candidate, it outputs a determination result that a lesion is present, together with information such as a timestamp, to heat map generation unit 22 and display control unit 23. On the other hand, if lesion detection unit 21 does not detect a lesion candidate, it outputs a determination result that a lesion is not present to heat map generation unit 22 and display control unit 23.

[0026] The heat map generating unit 22 generates a heat map based on the endoscopic image input from the interface 13 and the determination result input from the lesion detecting unit 21 .

[0027] Specifically, when a determination result indicating the presence of a lesion is input from lesion detection unit 21, heat map generation unit 22 acquires an endoscopic image including a lesion candidate from the endoscopic image input from interface 13 based on information such as a timestamp. Then, heat map generation unit 22 uses a pre-prepared image recognition model or the like to estimate whether each pixel in the endoscopic image is within a region of a lesion candidate (hereinafter also referred to as a "lesion region"). This image recognition model is a model that has been trained in advance to estimate whether each pixel in the endoscopic image is a pixel in a lesion region, and is hereinafter also referred to as a "lesion score estimation model."

[0028] The heat map generator 22 uses the lesion score estimation model to estimate whether each pixel in the endoscopic image is a pixel in a lesion area, and calculates a score (hereinafter also referred to as a "lesion score") indicating the probability that the pixel is in a lesion area. The lesion score is, for example, a numerical value greater than or equal to 0 and less than or equal to 1, and the closer the lesion score is to 1, the more likely the pixel is in a lesion area. The heat map generator 22 then generates a heat map based on a predetermined relationship between the lesion score and color. The heat map generator 22 outputs the generated heat map to the display controller 23.

[0029] In the above description, the heat map generator 22 generates a heat map when the lesion detector 21 inputs a determination result indicating the presence of a lesion, but the timing of generating the heat map is not limited to this. For example, the heat map generator 22 may generate a heat map each time an endoscopic image is input from the interface 13 and output the heat map to the display controller 23.

[0030] The display control unit 23 generates display data based on the endoscopic image Ic input from the interface 13, the judgment result input from the lesion detection unit 21, and the heat map input from the heat map generation unit 22, and outputs it to the display device 2.

[0031] Specifically, when the display control unit 23 receives a determination result indicating the presence of a lesion from the lesion detection unit 21, the display control unit 23 generates an indicator indicating the position and size of the lesion candidate based on the heat map. Then, the display control unit 23 includes the indicator in the display data and outputs it to the display device 2. Furthermore, when the display control unit 23 receives a predetermined number of consecutive determination results indicating the presence of a lesion from the lesion detection unit 21, the display control unit 23 determines that the lesion candidate has been stably detected. Then, the display control unit 23 includes an endoscopic image and a heat map including the lesion candidate in the display data as a lesion history and a heat map corresponding to the lesion history, which will be described later, and outputs this to the display device 2. On the other hand, when the display control unit 23 receives a determination result indicating the absence of a lesion from the lesion detection unit 21, the display control unit 23 outputs the endoscopic video Ic as display data to the display device 2.

[0032] Fig. 4 shows an example of a method for generating an indicator by display control unit 23. Fig. 4 shows a heat map 31, a lesion area 32, a rectangle 33, indicator information 34a, and indicator information 34b.

[0033] The heat map 31 is input from the heat map generator 22. The lesion area 32 indicates lesion candidates. The display controller 23 compares the lesion score of each pixel in the heat map 31 with a predetermined threshold TH1 and sets the area consisting of pixels whose lesion score is equal to or greater than the threshold TH1 as the lesion area 32. The rectangle 33 is a rectangle that surrounds the lesion area 32. The display controller 23 surrounds the lesion area 32 with the rectangle 33 and generates coordinate information for the rectangle 33. The coordinate information can be represented, for example, by the coordinates (x, y) of the upper left point of the rectangle 33, and the width w and height h of the rectangle 33 when that point is the origin. The display controller 23 calculates the display position and size of an indicator (hereinafter also referred to as "indicator information") based on the coordinate information of the rectangle 33. Then, the display controller 23 uses the calculation results to generate an indicator on the frame of the display screen of the endoscopic video and outputs it to the display device 2.

[0034] The display control unit 23 generates an indicator that allows the position and size of a lesion candidate to be recognized by using at least one of the left and right edges and at least one of the top and bottom edges of the display screen of the endoscopic image. Therefore, indicator information is calculated in two places for one lesion area 32, as shown by indicator information 34a and 34b in FIG. 4.

[0035] In the above configuration, the interface 13 is an example of an image acquisition means, the lesion detection unit 21 is an example of a lesion detection means, the heat map generation unit 22 is an example of a heat map generation means, and the display control unit 23 is an example of a display control means.

[0036] [Display example] Next, a display example on the display device 2 will be described.

[0037] 5 is an example of a display on the display device 2. In this example, the display device 2 displays an endoscopic image 41, a lesion history 42, a heat map 43, a display screen frame 44, and indicators 44a and 44b.

[0038] The endoscopic video 41 is the endoscopic video Ic during the examination and is updated as the endoscopic camera moves. The lesion history 42 is an endoscopic image containing a lesion candidate detected during the endoscopic examination. If there are multiple endoscopic images containing a lesion candidate, the lesion history 42 displays the endoscopic image containing the most recent lesion candidate. The heat map 43 is a heat map of the endoscopic image corresponding to the lesion history 42.

[0039] Display screen frame 44 is the frame of the display screen for endoscopic image 41. Indicators 44a and 44b are indicators that show the position and size of a lesion candidate. Indicators 44a and 44b are displayed on display screen frame 44 when a lesion candidate is detected during endoscopic examination. Indicator 44a shows the vertical size and vertical position of the lesion candidate. Indicator 44b shows the horizontal size and horizontal position of the lesion candidate. By displaying indicators 44a and 44b, the doctor can grasp the position and size of the lesion candidate.

[0040] FIG. 6 shows another example of display by display device 2. This example shows a display when two lesion candidates are detected. Specifically, in FIG. 6, the position and size of one lesion candidate are indicated by gray indicators 44a and 44b, and the position and size of the other lesion candidate are indicated by diagonally hatched indicators 45a and 45b. As shown in FIG. 6, by generating indicators with different display modes for each lesion candidate and displaying them on display screen frame 44, a doctor can grasp the position and size of each lesion candidate even when multiple lesion candidates are detected simultaneously.

[0041] FIG. 7 shows another example of display by the display device 2. This example is a display example when two lesion candidates are detected. In FIG. 6, indicators 44a and 44b and indicators 45a and 45b are displayed at the bottom and right ends of the endoscopic image 41. However, when multiple lesion candidates are detected, the indicators may overlap depending on their relative positions, making it difficult for the doctor to grasp the position and size of the lesion candidates. Therefore, in FIG. 7, in addition to the bottom and right ends of the endoscopic image 41, the top and left ends of the endoscopic image 41 are used as display locations for the indicators. This makes it possible to prevent the indicators from overlapping when multiple lesion candidates are detected.

[0042] [Image display processing] Next, a description will be given of the display process for performing the above-mentioned display. Fig. 8 is a flowchart of the process performed by the endoscopic examination support device 1. This process is realized by the processor 11 shown in Fig. 2 executing a program prepared in advance and operating as each element shown in Fig. 3.

[0043] First, the endoscopic video Ic is input from the endoscope 3 to the interface 13. The interface 13 acquires an endoscopic image from the input endoscopic video Ic (step S11). The interface 13 outputs the endoscopic image to the lesion detection unit 21 and the heat map generation unit 22. The interface 13 also outputs the endoscopic video Ic to the display control unit 23. Next, the lesion detection unit 21 detects a lesion from the endoscopic image (step S12). Specifically, the lesion detection unit 21 uses a lesion detection model to determine whether or not the endoscopic image contains a lesion. Then, the lesion detection unit 21 outputs the determination result to the heat map generation unit 22 and the display control unit 23.

[0044] Next, when a lesion is detected, the heat map generator 22 generates a heat map from the endoscopic image (step S13). Specifically, the heat map generator 22 estimates a lesion score for each pixel of the endoscopic image using a lesion score estimation model. The heat map generator 22 then generates a heat map based on a predetermined relationship between the score and color. The heat map generator 22 then outputs the generated heat map to the display controller 23.

[0045] Next, the display control unit 23 generates display data from the endoscopic video input from the interface 13, the determination result input from the lesion detection unit 21, and the heat map input from the heat map generation unit 22, and outputs the display data to the display device 2 (step S14). If the endoscopic image contains a lesion candidate, the display control unit 23 generates an indicator indicating the position and size of the lesion. The display control unit 23 then includes the indicator in the display data and outputs the data to the display device 2.

[0046] [Variations] Next, a description will be given of modifications of the first embodiment. The following modifications can be applied to the first embodiment in appropriate combinations.

[0047] (Variation 1) In the first embodiment described above, the indicator is displayed in a single color, but the display mode within the indicator may be changed depending on the lesion score. Specifically, the display control unit 23 may change the display mode within the indicator depending on the lesion score of the pixels in the lesion area. For example, if the lesion score is high in the center of the lesion area and decreases with increasing distance from the center of the lesion area, the display control unit 23 may add shading to the indicator, such as by making the color of the center of the indicator darker and the other parts lighter. In this way, changing the display mode within the indicator allows the doctor to grasp the location of lesion candidates that require more attention.

[0048] (Variation 2) The display control unit 23 may change the indicator display mode according to the lesion score of the entire lesion area. Specifically, the display control unit 23 may calculate the average value of the lesion scores assigned to each pixel in the lesion area (hereinafter also referred to as the "lesion area score") and change the indicator display mode according to the lesion area score. For example, the display control unit 23 may change the color of the indicator to red when the lesion area score is equal to or greater than a predetermined threshold TH2, and change the color of the indicator to yellow when the lesion area score is less than the predetermined threshold TH2. In this way, for lesion candidates with high lesion area scores, the indicator may be displayed in a manner that attracts the doctor's attention.

[0049] (Variation 3) In the first embodiment described above, an indicator is displayed whenever a lesion candidate is detected, but display control unit 23 may display or hide the indicator depending on the lesion area score. For example, the indicator may be displayed only when the lesion area score is equal to or greater than a predetermined threshold value TH3.

[0050] (Variation 4) In the first embodiment described above, an indicator is displayed whenever a lesion candidate is detected, but display control unit 23 may display or hide the indicator depending on the size of the lesion candidate. For example, the indicator may be displayed only when the area of ​​the lesion candidate is equal to or greater than a predetermined threshold value TH4.

[0051] (Variation 5) The display mode of the indicator may be changed for each doctor. For example, the display location of the indicator may be selected from at least one of the left and right ends and at least one of the top and bottom ends for each doctor. Also, the color and pattern of the indicator may be selected for each doctor. This makes it possible to display the indicator in a display mode that is easy for each doctor to see.

[0052] (Variation 6) In the first embodiment described above, lesion detection unit 21 detects lesion candidates. Alternatively, heat map generation unit 22 may detect lesion candidates. In this case, heat map generation unit 22 performs image analysis based on the endoscopic image input from interface 13 and determines whether or not the endoscopic image contains a lesion. If the endoscopic image contains a lesion, heat map generation unit 22 generates a heat map. Then, heat map generation unit 22 inputs the lesion presence / absence determination result and the heat map to display control unit 23. The lesion score estimation model used by heat map generation unit 22 is a trained model that has been trained in advance to calculate a lesion score for each pixel of the endoscopic image and detect lesion candidates.

[0053] Second Embodiment 9 is a block diagram showing the functional configuration of an endoscopic examination support device according to the second embodiment. The endoscopic examination support device 70 includes an image acquisition means 71, a lesion detection means 72, a heat map generation means 73, and a display control means 74.

[0054] 10 is a flowchart of processing by the endoscopic examination support device of the second embodiment. The image acquisition means 71 acquires an endoscopic image captured by an endoscope (step S71). The lesion detection means 72 detects lesion candidates from the endoscopic image (step S72). The heat map generation means 73 generates a heat map that uses colors to represent the lesion possibility of the lesion candidates included in the endoscopic image (step S73). The display control means 74 displays the lesion position within a frame on the endoscopic image based on the lesion candidates and the heat map (step S74).

[0055] Although the present disclosure has been described above with reference to the embodiments and examples, the present disclosure is not limited to the above-described embodiments and examples. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0056] (Appendix 1) an image acquisition means for acquiring an endoscopic image captured by an endoscope; a lesion detection means for detecting lesion candidates from the endoscopic video; a heat map generating means for generating a heat map in which the lesion possibility of the lesion candidate included in the endoscopic image is expressed by color; a display control means for displaying a lesion position on a frame of the endoscopic image based on the lesion candidate and the heat map; An endoscopic examination support device equipped with the device.

[0057] (Appendix 2) The heat map generating means represents the possibility of a lesion for each pixel included in a frame image of the endoscopic video as a score, and the display control means displays the location of the lesion on the frame of the endoscopic video in a display mode according to the score.

[0058] (Appendix 3) The endoscopic examination support device described in Appendix 1, wherein the heat map generation means represents the possibility of a lesion for each pixel included in a frame image of the endoscopic video as a score, and the display control means calculates an average value of the scores and displays the lesion position on the frame of the endoscopic video in a display mode corresponding to the average value.

[0059] (Appendix 4) The heat map generation means expresses the lesion possibility as a score, and the display control means displays the lesion position on a frame of the endoscopic image when the score is equal to or greater than a predetermined threshold.

[0060] (Appendix 5) An endoscopic examination support device as described in Appendix 1, wherein, when the lesion detection means detects multiple lesion candidates, the display control means displays the lesion positions of the multiple lesion candidates in different display modes on the frame of the endoscopic image.

[0061] (Appendix 6) Acquire endoscopic images captured by the endoscope, detecting a lesion candidate from the endoscopic image; generating a heat map that represents the lesion possibility of the lesion candidate included in the endoscopic image using color; An endoscopic examination support method for displaying a lesion position in a frame on the endoscopic image based on the lesion candidate and the heat map.

[0062] (Appendix 7) Acquire endoscopic images captured by the endoscope, detecting a lesion candidate from the endoscopic image; generating a heat map that represents the lesion possibility of the lesion candidate included in the endoscopic image using color; A recording medium having recorded thereon a program that causes a computer to execute a process of displaying the lesion position in a frame on the endoscopic image based on the lesion candidate and the heat map. [Explanation of symbols]

[0063] 1 Endoscopy support device 2 Display device 3 Endoscope 11 processors 12 Memory 13 Interface 21 Lesion detection unit 22 Heat map generation section 23 Display control unit 100 Endoscopy System

Claims

1. an image acquisition means for acquiring an endoscopic image captured by an endoscope; a lesion detection means for detecting lesion candidates from the endoscopic video; a heat map generating means for generating a heat map in which the lesion possibility of the lesion candidate included in the endoscopic image is expressed by color; a display control means for displaying a lesion position on a frame of the endoscopic image based on the lesion candidate and the heat map; An endoscopic examination support device equipped with the device.

2. The endoscopic examination support device according to claim 1, wherein the heat map generating means represents the lesion possibility for each pixel included in the frame image of the endoscopic video as a score, and the display control means displays the lesion position on the frame of the endoscopic video in a display mode corresponding to the score.

3. The endoscopic examination support device of claim 1, wherein the heat map generation means represents the lesion possibility for each pixel included in the frame image of the endoscopic video as a score, and the display control means calculates an average value of the scores and displays the lesion position on the frame of the endoscopic video in a display mode corresponding to the average value.

4. the heat map generation means expresses the lesion possibility as a score, 2. The endoscopic examination support device according to claim 1, wherein the display control means displays the lesion position in a frame on the endoscopic image when the score is equal to or greater than a predetermined threshold value.

5. The endoscopic examination support device according to claim 1, wherein, when the lesion detection means detects a plurality of lesion candidates, the display control means displays the lesion positions of the plurality of lesion candidates in different display modes on the frame of the endoscopic image.

6. A computer-implemented method for assisting endoscopic examination, comprising: Acquire endoscopic images captured by the endoscope, detecting a lesion candidate from the endoscopic image; generating a heat map that represents the lesion possibility of the lesion candidate included in the endoscopic image using color; An endoscopic examination support method for displaying a lesion position in a frame on the endoscopic image based on the lesion candidate and the heat map.

7. Acquire endoscopic images captured by the endoscope, detecting a lesion candidate from the endoscopic image; generating a heat map that represents the lesion possibility of the lesion candidate included in the endoscopic image using color; A program that causes a computer to execute a process of displaying a lesion position in a frame of the endoscopic image based on the lesion candidate and the heat map.

Images