JP7220575B2 - Medical image diagnosis support device, medical image capturing device, image management server, and medical image diagnosis support method - Google Patents

Description

The present invention relates to a medical image diagnosis support device, a medical image capturing device, an image management server, and a medical image diagnosis support method that can quickly determine the presence of a disease condition of interest in captured medical images.

When a doctor diagnoses a patient, he/she makes a diagnosis based on his/her own experience and information obtained from medical books, case report forms, case databases, and the like. At this time, a tomographic image captured by an X-ray CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, an ultrasonic CT device, or the like is useful for assisting doctors in diagnosis.

Patent Literature 1 describes automatic detection of calcified plaque belonging to a blood vessel based on a differential image between a non-contrast-enhanced CT image and a contrast-enhanced CT image. Patent Document 1 utilizes the fact that organs and blood vessels with blood flow are emphasized in a contrast-enhanced CT image and that calcified plaque is easily found in a non-contrast CT image, and calcified intravascular calcifications are located. It detects plaque.

JP 2016-41247 A

By the way, in recent years, it has become possible to scan a CT image of the whole body of a patient at high speed, and a CT slice image of the whole body can be obtained in a short time. The amount of information in this CT image is extremely rich. However, it is not easy to pick up necessary information from this CT image in a short time. For example, in emergency medical care and acute medical care, it is important to quickly determine the presence of pathological conditions of interest, such as thrombus and hematoma. You may miss it. Oversight of the existence of this noteworthy pathological condition is fatal in emergency medical care and acute medical care.

DISCLOSURE OF THE INVENTION The present invention has been made in order to solve the above-described problems of the prior art, and is a medical image diagnosis support device and a medical image capturing device capable of quickly determining the presence of a disease condition of interest in a captured medical image. , an image management server and a medical image diagnosis support method.

In order to solve the above-described problems, the present invention provides a medical image diagnosis support apparatus that assists in determining the presence of a disease condition of interest from a medical image captured by a medical imaging apparatus, wherein the disease condition of interest occurs on the medical image. a region-of-interest setting unit that sets a region of interest including a tissue that is likely to be affected; and an information adding unit that adds display information, wherein the region of interest setting unit sets the region of interest based on a position of an anatomical structure including bones and organs.

Further, according to the present invention, in the above invention, the region-of-interest setting unit learns anatomical structure positions including bones and organs by machine learning, and uses the anatomical structure positions obtained by the machine learning as a reference. and setting the region of interest of the captured medical image.

The present invention is characterized in that, in the above-described invention, the information adding unit adds predetermined color information to a region having a pixel value indicating the possibility of existence of the disease state of interest within the region of interest. do.

Further, according to the present invention, in the above-described invention, the information provision unit determines the possibility of the presence of the target pathology based on a normal image in which the target pathology does not exist and an abnormal image in which the target pathology exists in the region of interest. is learned by machine learning, and when the region of interest of the captured medical image includes a region in which the disease condition of interest is highly likely to exist, the color information is added to the region in which the disease condition of interest is highly likely to exist. It is characterized by

Further, the present invention is characterized in that, in the above-described invention, an information addition unit is provided for adding an annotation to that effect to the medical image when there is a region in which the disease condition of interest is highly likely to exist.

Further, according to the present invention, in the above invention, the pixel values are pixel values within a predetermined range.

Further, according to the present invention, in the above invention, the medical image is a simple examination image that does not use a contrast medium.

Further, according to the present invention, in the above invention, the medical image includes an X-ray CT image, an MRI image, and an ultrasound image.

Further, according to the present invention, in the above invention, the medical image is an X-ray CT image, and the pixel values are values obtained by converting CT values.

Further, according to the present invention, in the above invention, the pathology of interest is thrombus and hematoma.

According to another aspect of the present invention, there is provided a medical imaging apparatus including the medical image diagnosis support apparatus according to any one of the above inventions.

Further, the present invention is an image management server that receives and manages the medical images captured by the medical imaging apparatus, and performs at least interpretation support for the medical images, wherein the image management server according to any one of the above inventions. It is characterized by comprising a medical image diagnosis support device.

Further, the present invention is an image management server on the cloud that receives and manages the medical images captured by the medical image capturing device and supports at least interpretation of the medical images, wherein any one of the above inventions 2. A medical image diagnosis support device according to 1.

Further, the present invention provides a medical image diagnosis support method for a medical image diagnosis support apparatus that assists in determining the presence of a disease state of interest from a medical image captured by a medical imaging apparatus, wherein the disease state of interest occurs on the medical image. a region of interest setting step of setting a region of interest including a tissue that is likely to be affected; and an information providing step of providing display information, wherein the region of interest setting step sets the region of interest based on a position of an anatomical structure including bones and organs.

Further, in the present invention, in the above invention, the region-of-interest setting step learns anatomical structure positions including bones and organs by machine learning, and uses the anatomical structure positions obtained by the machine learning as a reference. and setting the region of interest of the captured medical image.

The present invention is characterized in that, in the above-described invention, the information adding step adds predetermined color information to a region having a pixel value indicating the possibility of existence of the disease state of interest within the region of interest. do.

Further, according to the present invention, in the above-described invention, the information provision step includes determining the possibility of the presence of the target pathology based on a normal image in which the target pathology does not exist and an abnormal image in which the target pathology exists in the region of interest. is learned by machine learning, and when the region of interest of the captured medical image includes a region in which the disease condition of interest is highly likely to exist, the color information is added to the region in which the disease condition of interest is highly likely to exist. It is characterized by

In the above-described invention, the present invention is characterized by including an information addition step of adding an annotation to that effect to the medical image when there is a region in which the pathological condition of interest is highly likely to exist.

Advantageous Effects of Invention According to the present invention, it is possible to rapidly determine the presence of a pathological condition of interest in a captured medical image.

FIG. 1 is an explanatory diagram for explaining the outline of the medical image diagnosis support apparatus according to the present embodiment. FIG. 2 is a functional block diagram showing the configuration of the image management server shown in FIG. 1. As shown in FIG. FIG. 3 is a flowchart showing a medical image diagnosis support processing procedure by the image management server. FIG. 4 is a functional block diagram showing the configuration of a medical imaging apparatus according to Modification 1. As shown in FIG. FIG. 5 is a functional block diagram showing the configuration of an image management server according to modification 2. As shown in FIG. FIG. 6 is a functional block diagram showing the configuration of the image management server according to this application example. FIG. 7 is an explanatory diagram showing an example of medical image diagnosis support processing according to this application example.

BEST MODE FOR CARRYING OUT THE INVENTION Preferred embodiments of a medical image diagnosis support apparatus, a medical image photographing apparatus, an image management server, and a medical image diagnosis support method according to the present invention will be described below in detail with reference to the accompanying drawings.

<Overview of Medical Image Diagnosis Support Device>
First, an overview of the medical image diagnosis support apparatus 10 according to the present embodiment will be described. FIG. 1 is an explanatory diagram for explaining an overview of a medical image diagnosis support apparatus 10 according to this embodiment.

As shown in FIG. 1, the image management server 2 has a medical image diagnosis support device 10 . An image management server 2 is connected to the modality 1 . The modality 1 is, for example, an X-ray CT apparatus, and medical images captured by the X-ray CT apparatus are sequentially sent to the image management server 2 . Also, the image management server 2 is connected to the terminal device 13 . The terminal device 13 is, for example, a terminal operated by an interpreting doctor, and interprets medical images stored in the image management server 2 . The image management server 2 manages medical images according to, for example, the DICOM standard.

The medical image diagnosis support apparatus 10 supports the determination of the presence of a noteworthy pathological condition such as a thrombus or hematoma from medical images captured by a modality 1 as a medical image capturing apparatus. FIG. 1(a) shows an example of a medical image D. FIG. A medical image D is an abdominal CT image. A CT image is a grayscale image corresponding to the degree of absorption of X-rays, and bones that absorb large amounts of X-rays are white. For example, in FIG. 1(a), the spine 101 and ribs 111 are white because they absorb a lot of X-rays. In addition, the black portion in FIG. 1(a) is fat that absorbs little X-rays. The CT value is expressed as a relative value with water as the origin, and has a value of -1000 to 1000, under the condition that water is set to 0 and air is set to -1000. Therefore, a CT image is also a distribution image of CT values. The medical image D is a non-contrast CT image (simple examination image).

Here, the CT values of noteworthy pathological conditions such as thrombus and hematoma are 45-75. Although the CT value is a three-dimensional minimum cubic voxel value, it can be converted into a general 256-gradation pixel value. Locations (regions of interest) where thrombosis and hematoma of interest occur are the descending aorta 102 , inferior vena cava 103 , superior mesenteric artery 104 , and superior mesenteric vein 105 . These locations represent the CT values of blood, but since the CT values of other tissues such as the liver 106 are 45 to 75, it is difficult to distinguish them from the region of interest.

Therefore, as shown in FIG. 1B, the medical image diagnosis support apparatus 10 first sets a region of interest E on a medical image D including a tissue in which a disease condition of interest may occur. This region of interest E is set based on the position of the anatomical structure including bones and organs. An anatomical structure position including bones and organs serves as a reference index for setting the region of interest E. FIG. For example, the medical image diagnosis support apparatus 10 determines a center line C passing through the center P of the spinal column 101 based on the spinal canal shape of the spinal column 101, sets the center P as the center of a circle, and sets the center line C at an angle θ , a fan-shaped region with a radius R is set as a region of interest E. In FIG. 1B, the angle θ is 45 degrees and the radius R is 5 cm. This region of interest E includes the descending aorta 102, descending vena cava 103, superior mesenteric artery 104, and superior mesenteric vein 105 described above. When setting the region of interest E, the elliptical shape formed by the ribs 111 other than the spine 101 may be considered. Also, the region of interest E may be set based on a three-dimensional tissue obtained based on not only one medical image but also adjacent medical images (slice images).

Since there are individual differences in tissues in which the pathological condition of interest may occur, this region of interest E is set based on tissues such as bones, which have relatively small individual differences and have clear CT values. It identifies the relative position of the tissue in which the pathological condition of interest may occur from the reference position. Therefore, the region of interest is not limited to a fan shape, and may be, for example, a circular region surrounding the descending aorta 102 .

Thereafter, as shown in FIG. 1(c), the medical image diagnosis support apparatus 10 assigns predetermined color information, such as red and yellow, to pixels with CT values of 45 to 75 in the region of interest E. . Therefore, only the descending aorta 102, descending vena cava 103, superior mesenteric artery 104, and superior mesenteric vein 105 are provided with color information.

A region to which this color information is added is a region in which there is a possibility that the pathological condition of interest such as thrombus and hematoma exists, and this region is emphasized. This allows the radiologist to quickly determine the presence of the disease state of interest. Specifically, the interpreting doctor can determine that the area to which the color information has been added differs from the original tissue shape, such as the descending aorta 102, descending vena cava 103, superior mesenteric artery 104, and superior mesenteric vein 105. , or if the colored portion has a different shape from the original tissue shape, it can be determined that there is a thrombus or hematoma.

In FIG. 1(c), the presence of hematomas 102a and 104a can be confirmed in the descending aorta 102 and the superior mesenteric artery 104, respectively. The CT value of the thrombus and hematoma was set in the range of 45 to 75 as the CT value of blood, but this range may be narrowed or widened in consideration of the freshness of the blood. good.

As described above, in this embodiment, a region of interest E including tissues in which there is a possibility of the pathological condition of interest such as thrombus and hematoma is set, and pixel values indicating the possibility of presence of the pathological condition of interest are set within this region of interest E. Since predetermined color information is given to the region, it is possible to objectively discriminate the disease state of interest, and the rate of overlooking the disease state of interest by radiologists can be reduced. In particular, in emergency medical care or acute medical care, speedy image interpretation is required, and even if there is such a time limit, it is easy to distinguish the pathological condition of interest.

<Configuration of Image Management Server Including Medical Image Diagnosis Support Device>
Next, the configuration of the image management server 2 shown in FIG. 1 will be described. FIG. 2 is a functional block diagram showing the configuration of the image management server 2 shown in FIG. The image management server 2 has an input unit 3 , a display unit 4 , a communication unit 5 , a storage unit 6 , a control unit 7 and a medical image diagnosis support device 10 .

The input unit 3 is an input device such as a keyboard or a mouse, the display unit 4 is a display device such as a liquid crystal panel, and the communication unit 5 is the modality 1, the terminal device 13, or another device via a network (not shown). A communication interface unit for connecting to the device.

The storage unit 6 is a storage device composed of a hard disk device, a nonvolatile memory, or the like, and stores medical information D10 including medical images D1.

The medical image diagnosis support apparatus 10 has a region of interest setting section 11 and a color information providing section 12 . The region-of-interest setting unit 11 sets a region-of-interest E including a tissue in which the pathological condition of interest may occur from the modality 1 on a medical image. The color information imparting unit 12 imparts predetermined color information to regions within the region of interest E having pixel values indicating the possibility of presence of the disease state of interest.

The control unit 7 is a control unit that controls the entire image management server 2 and has an information processing control unit 8 . The control unit 15 stores programs corresponding to the information processing control unit 8 in a storage device such as a non-volatile memory or a magnetic disk device, loads these programs into the memory, and executes them by the CPU. will cause the process to run.

The information processing control unit 8 performs information processing such as accumulation, viewing, copying, moving, and deletion of the medical information D10, deletion of specific information, and extraction of specific information in response to requests from connected devices. In particular, the information processing control unit 8 executes a process of generating a medical image D1 in which the medical image D imaged by the modality 1 is subjected to a discrimination support process for the existence of the target pathological condition in the connected medical image diagnosis support apparatus 10. Let The functions of the medical image diagnosis support apparatus 10, that is, the medical image diagnosis support functions may be provided in the control unit 7 as software or hardware.

<Medical image diagnosis support processing>
Next, medical image diagnosis support processing by the image management server 2 will be described. FIG. 3 is a flow chart showing a medical image diagnosis support processing procedure by the image management server 2. As shown in FIG. As shown in FIG. 3, when the control unit 7 receives a medical image D from the modality 1 (step S101), the region-of-interest setting unit 11 is instructed that a disease state of interest such as thrombus and hematoma occurs on the medical image D. A process of setting a region of interest E containing a possible tissue is performed (step S102). After that, the control unit 7 causes the color information adding unit 12 to perform a process of adding predetermined color information to a region having a pixel value indicating the possibility of presence of the disease state of interest within the region of interest E (step S103), the image is stored in the medical information D10 in the storage unit 6 as the medical image D1, and the process is terminated.

<Modification 1>
Note that the medical image diagnosis support apparatus 10 may be installed in the modality 1 as shown in FIG. The modality 1 sends the captured medical image D to the medical image diagnosis support apparatus 10, and sends out the medical image D1 processed by the medical image diagnosis support apparatus 10 to the outside.

<Modification 2>
Further, as shown in FIG. 5, an image management server 32 corresponding to the image management server 2 including the medical image diagnosis support apparatus 10 may be arranged on the cloud 30 . In this case, for example, the local server 22 in the medical institution that connects the modality 1 and the terminal device 13 is connected to the image management server 32 . The local server 22 transmits the medical image D captured by the modality 1 to the image management server 32 . The image management server 32 generates and stores a medical image D1 obtained by performing medical image diagnosis support processing on the received medical image D using the medical image diagnosis support apparatus 10 . Further, the terminal device 13 operated by the radiologist accesses the image management server 32 via the local server 22 and interprets the generated medical image D1.

<Application example>
In this application example, the medical image diagnosis support processing by the medical image diagnosis support apparatus 10 is performed by a function learned by machine learning including deep learning.

FIG. 6 is a functional block diagram showing the configuration of the image management server 2 according to this application example. As shown in FIG. 6, the image management server 2 according to this application example has a function of learning the processing of the region-of-interest setting unit 41 and the color information adding unit 42 in the medical image diagnosis support apparatus 10 by machine learning including deep learning. by Further, if there is a region with a high probability of presence of the pathological condition of interest, it has an information addition unit 43 that adds an annotation to that effect to the medical image D1. Other configurations are the same as those shown in FIG.

The region-of-interest setting unit 41 learns the anatomical structure positions including bones and organs by machine learning, and based on the anatomical structure positions obtained by the machine learning, the region-of-interest E of the imaged medical image D is determined. set.

For example, as shown in FIG. 7( a ), the anatomical structure positions including bones and organs are machine-learned in advance using a large number of medical images, and the machine-learned anatomical structure positions such as the spine are calculated. Regions of interest E102 to E105 of the captured medical image D are set as a reference. Each region of interest E102-E105 corresponds to the tissues of the descending aorta 102, descending vena cava 103, superior mesenteric artery 104, and superior mesenteric vein 105, respectively. In addition, the anatomical structure positions of the descending aorta 102, descending vena cava 103, superior mesenteric artery 104, and superior mesenteric vein 105 are further learned, and the descending aorta 102, inferior vena cava The tissues of 103, superior mesenteric artery 104, and superior mesenteric vein 105 may be specified in more detail. In this case, the three-dimensional structures of the descending aorta 102, descending vena cava 103, superior mesenteric artery 104, and superior mesenteric vein 105 may be referred to for identification. In FIG. 7A, the descending aorta 102, descending vena cava 103, superior mesenteric vein 105, descending aorta 102, descending vena cava 103, and superior mesenteric vein 105 are shown. Circular regions including the tissues of the mesenteric artery 104 and the superior mesenteric vein 105 are regions of interest E102 to E105.

The color information providing unit 42 can detect the presence of a pathological condition of interest based on a normal image in which a pathological condition of interest such as a thrombus and hematoma does not exist and an abnormal image in which a pathological condition of interest such as a thrombus and hematoma exists in the regions of interest E102 to E105. 7(b), it is determined whether or not there is a region of interest in the imaged medical image D where there is a high possibility that the pathological condition of interest exists. If there is a region with a high possibility of existence, color information is given to the region with a high possibility of existence of the pathological condition of interest, as shown in FIG. 7(c).

The difference between the color information providing unit 42 and the color information providing unit 12 is that the color information is applied only to regions where the pathological condition of interest is likely to exist, specifically, not to tissues where the pathological condition of interest may exist. It is to give. As a result, the medical image diagnosis support apparatus 10 preliminarily interprets the medical image, and the interpreting doctor confirms the interpretation result.

In addition, in this application example, when the color information adding unit 12 has areas with a high probability of presence of the pathological condition of interest, for example, hematomas 102a and 104a, as shown in FIG. 7C, annotations A1 and A2 to that effect is added to the medical image D1.

In this application example, the machine-learned medical image diagnosis support device 10 is used to detect areas where there is a high possibility that the pathological condition of interest exists, and color information is added to the area. can be determined.

Although the above medical image has been described as a two-dimensional image, it is not limited to this, and color information may be added to the three-dimensional shape of the target pathological condition based on a plurality of slice images.

In the above description, the medical image D is an X-ray CT image. It may be a sound wave image.

Furthermore, although thrombi and hematomas have been described above as examples of noteworthy pathological conditions, there are various types of thrombi and hematomas depending on human sites. For example, for the head, there are subarachnoid hemorrhage, acute cerebral infarction, and cerebral sinus thrombosis; In , there are superior mesenteric artery occlusion/dissection, non-obstructive intestinal ischemia, and in the spine, vertebral epidural hematoma.

Although thrombosis and hematoma have been described as examples of pathological conditions of interest, the pathological conditions of interest are not limited to thrombus and hematoma, and may be other endogenous pathologies. Additionally, the condition of interest may be an extrinsic condition, such as tissue injury, contusion, or bleeding.

Further, in the above series of explanations, a case has been described in which predetermined color information such as red, yellow, etc. is given to pixels having CT values within a predetermined range in the region of interest E, but the present invention is not limited to this, and a corresponding pixel can be emphasized in a manner other than color information. For example, a pixel value of a pixel having a CT value within a predetermined range in the region of interest E can be set to a pixel value distinguishable from pixel values of pixels in other regions. A region can also be highlighted by associating a specific figure with it.

It should be noted that each configuration shown in the above examples, modifications, and applications is merely functionally schematic, and does not necessarily need to be physically configured as shown. That is, the form of distribution/integration of each device is not limited to the illustrated one, and all or part of them can be functionally or physically distributed/integrated in arbitrary units according to various loads and usage conditions. Can be configured.

INDUSTRIAL APPLICABILITY The medical image diagnosis support device, the medical image capturing device, the image management server, and the medical image diagnosis support method of the present invention are useful for quickly determining the presence of a disease condition of interest in captured medical images.

1 modality 2 image management server 3 input unit 4 display unit 5 communication unit 6 storage unit 7 control unit 8 information processing control unit 10 medical image diagnosis support device 11, 41 region of interest setting unit 12, 42 color information addition unit 13 terminal device 15 Control unit 22 Local server 30 Cloud 32 Image management server 43 Information providing unit 101 Spinal column 102 Downward aorta 102a, 104a Hematoma 103 Downward vena cava 104 Superior mesenteric artery 105 Superior mesenteric vein 106 Liver 111 Ribs A1, A2 Annotation C center line D, D1 medical image D10 medical information E, E102-E105 region of interest P center R radius θ angle

Claims (18)

A medical image diagnosis support device that assists in determining the presence of a pathological condition of interest from a medical image captured by a medical imaging device,
a region-of-interest setting unit that sets a region of interest including a tissue in which the pathological condition of interest may occur on the medical image;
an information adding unit that adds display information in a manner distinguishable from other regions to a region having a pixel value indicating the possibility of existence of the disease state of interest within the region of interest ;
The region-of-interest setting unit sets the region of interest based on a position of an anatomical structure including bones and organs.
A medical image diagnosis support device characterized by : The region-of-interest setting unit learns anatomical structure positions including bones and organs by machine learning, and uses the anatomical structure positions obtained by the machine learning as a reference to determine the region of interest in the captured medical image. 2. The medical image diagnosis support apparatus according to claim 1, wherein is set. 2. The medical image diagnosis support according to claim 1, wherein the information adding unit adds predetermined color information to a region having a pixel value indicating the possibility of existence of the disease state of interest within the region of interest. Device. The information providing unit learns the possibility of the presence of the target pathology by machine learning based on a normal image in which the target pathology does not exist and an abnormal image in which the target pathology exists in the region of interest, and performs imaging. 4. The method according to claim 3 , wherein when the region of interest of the medical image includes a region in which the pathological condition of interest is highly likely to exist, the color information is added to the region in which the pathological condition of interest is highly likely to exist. Medical image diagnosis support equipment. 5. The medical image diagnosis support apparatus according to claim 4 , further comprising an information addition unit that adds an annotation to the medical image when there is a region in which the pathological condition of interest is highly likely to exist. The medical image diagnosis support apparatus according to any one of claims 1 to 5 , wherein the pixel values are pixel values within a predetermined range. The medical image diagnosis support apparatus according to any one of claims 1 to 6 , wherein the medical image is a simple examination image that does not use a contrast medium. The medical image diagnosis support apparatus according to any one of claims 1 to 7 , wherein said medical images include X-ray CT images, MRI images and ultrasound images. 9. The medical image diagnosis support apparatus according to claim 1, wherein said medical image is an X-ray CT image, and said pixel values are values obtained by converting CT values. 10. The medical image diagnosis support apparatus according to any one of claims 1 to 9 , wherein the pathology of interest is thrombus and hematoma. A medical image capturing apparatus comprising the medical image diagnosis support apparatus according to any one of claims 1 to 10 . An image management server that receives and manages the medical image captured by the medical image capturing device, and at least supports interpretation of the medical image,
An image management server comprising the medical image diagnosis support device according to any one of claims 1 to 10 . An image management server on the cloud that receives and manages the medical images captured by the medical imaging device, and supports at least interpretation of the medical images,
An image management server comprising the medical image diagnosis support device according to any one of claims 1 to 10 . A medical image diagnosis support method for a medical image diagnosis support device that supports determination of the presence of a pathological condition of interest from a medical image captured by a medical image capturing device, comprising:
a region of interest setting step of setting a region of interest including a tissue in which the pathological condition of interest may occur on the medical image;
an information addition step of adding display information in a manner distinguishable from other regions to the region having pixel values indicating the possibility of existence of the disease state of interest within the region of interest ;
The region-of-interest setting step sets the region-of-interest based on a position of an anatomical structure including bones and organs.
A medical image diagnosis support method characterized by : In the region-of-interest setting step, the position of an anatomical structure including bones and organs is learned by machine learning, and the region of interest in the captured medical image is based on the position of the anatomical structure obtained by the machine learning. 15. The medical image diagnosis support method according to claim 14 , wherein the setting is . 15. The medical image diagnosis support according to claim 14 , wherein said information adding step adds predetermined color information to a region having a pixel value indicating the possibility of existence of said pathological condition of interest within said region of interest. Method. In the information providing step, the possibility of the presence of the target pathology is learned by machine learning based on a normal image in which the target pathology does not exist and an abnormal image in which the target pathology exists in the region of interest, and the image is captured. 17. The method according to claim 16 , wherein when the region of interest of the medical image includes a region in which the disease condition of interest is highly likely to exist, the color information is added to the region in which the disease condition of interest is highly likely to exist. Medical image diagnosis support method. 18. The medical image diagnosis support method according to claim 17 , further comprising an information adding step of adding an annotation to that effect to the medical image when there is a region in which the pathological condition of interest is highly likely to exist.

Images