# US 12,183,449 B2 · Diagnosis support program, diagnosis support system, and diagnosis support method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,449 B2 - Document ID: US12183449B2 - Status: Granted - Kind: B2 - Application number: 17/433,566 - Filed: 2019-12-25 - Published: 2022-05-12 - Granted: 2024-12-31 - Earliest claimed: 2019-02-28 - Assignees: Sony Corporation - Applicants: Sony Group Corporation - Inventors: Kazuki Aisaka; Takeshi Kunihiro; Kenji Yamane; Shinji Watanabe - Web page: https://patentgrep.com/patent/US12183449B2 ## CPC - G16H 30/40: for processing medical images, e.g. editing - G16H 50/30: for calculating health indices; for individual health risk assessment - G02B 21/368: {details of associated display arrangements, e.g. mounting of LCD monitor} - G06T 7/0012: {Biomedical image inspection} - G06T 7/11: Region-based segmentation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06T 2207/10056: Microscopic image - G06T 2207/20081: Training; Learning - G06T 2207/30024: Cell structures in vitro; Tissue sections in vitro - G06T 2207/30096: Tumor; Lesion - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A diagnosis support program causes a computer to execute a derivation procedure of deriving, on the basis of a first pathological image corresponding to a first affected tissue, history information regarding a history of viewing the first pathological image, and diagnostic information for the first affected tissue corresponding to the first pathological image, diagnosis support information for supporting diagnosis of a second pathological image corresponding to a second affected tissue to be diagnosed. ## Claims ### Claim 1 A non-transitory computer readable medium storing a program which, when executed, causes a computer to perform processing comprising: a derivation procedure of deriving, on a basis of a first pathological image corresponding to a first affected tissue wherein the first pathological image comprises a plurality of pixels, history information regarding a history of viewing the first pathological image comprising a number of times the first pathological image was viewed and a length of time over which the first pathological image has been viewed and a position of a portion of the first pathological image that was enlarged and displayed, and diagnostic information for the first affected tissue corresponding to the first pathological image, diagnosis support information for supporting diagnosis of a second pathological image corresponding to a second affected tissue to be diagnosed; and a learning procedure comprising assigning at least one of the plurality of pixels an attention value based on a magnification ratio of the at least one pixel, a viewing time of the at least one pixel, a number of times the at least one pixel was viewed, generating a map image comprising the attention values corresponding to the plurality of pixels, and determining the diagnostic information for the first affected tissue corresponding to the first pathological image by identifying a first portion of the first pathological image having a positive result and a second portion of the first pathological image having a negative result. ### Claim 2 (depends on 1) The diagnosis support program according to claim 1, wherein the derivation procedure derives information regarding viewing as the diagnosis support information. ### Claim 3 (depends on 1) The diagnosis support program according to claim 1, wherein the first pathological image is an entire image obtained by imaging the entire first affected tissue, and the history information is position information indicating a position where the first pathological image has been viewed. ### Claim 4 (depends on 3) The diagnosis support program according to claim 3, wherein the history information is position information indicating a position where the first pathological image has been viewed, and information indicating a time or the number of times the first pathological image has been viewed. ### Claim 5 (depends on 1) The diagnosis support program according to claim 1, wherein the first pathological image is an image constituted by a partial image corresponding to each region of the first affected tissue, and the history information is partial image information indicating a viewed partial image among the partial images corresponding to the regions. ### Claim 6 (depends on 1) The diagnosis support program according to claim 1, wherein the derivation procedure derives the diagnosis support information on a basis of an attention region of the second pathological image estimated from the history information. ### Claim 7 (depends on 6) The diagnosis support program according to claim 6, wherein the derivation procedure derives the diagnosis support information on a basis of the history information, assuming that a region with a larger display magnification is an attention region with a higher degree of attention, a region with a longer viewing time is an attention region with a higher degree of attention, or a region with a larger number of times of viewing is an attention region with a higher degree of attention. ### Claim 8 (depends on 1) The diagnosis support program according to claim 1, wherein the diagnostic information is information regarding whether a lesion site has been found, a type of the lesion site, or a degree of progression of the lesion site. ### Claim 9 (depends on 1) The diagnosis support program according to claim 1, wherein the learning procedure learning an association among the first pathological image, the history information, and the diagnostic information, and wherein the derivation procedure derives the diagnosis support information by using a result of learning by the learning procedure. ### Claim 10 (depends on 9) The diagnosis support program according to claim 9, wherein the learning procedure learns, in association with each other, the diagnostic information that indicates a positive diagnosis result and the history information corresponding to the diagnostic information. ### Claim 11 (depends on 9) The diagnosis support program according to claim 9, wherein the learning procedure learns, in association with each other, the diagnostic information that indicates a negative diagnosis result and the history information corresponding to the diagnostic information. ### Claim 12 (depends on 11) The diagnosis support program according to claim 11, wherein the learning procedure learns regions other than an attention region in the second pathological image as the diagnostic information that indicates a negative diagnosis result. ### Claim 13 (depends on 1) The diagnosis support program according to claim 1, wherein the derivation procedure derives the diagnosis support information on a basis of history information regarding a viewing history corresponding to the first pathological image having a similarity to the second pathological image higher than a threshold value, or the first pathological image having a degree of correlation with the second pathological image higher than a threshold value. ### Claim 14 A diagnosis support system comprising: a microscope; and a derivation device that derives diagnosis support information, which is information for supporting diagnosis, wherein the derivation device derives, on a basis of a first pathological image corresponding to a first affected tissue, history information regarding a history of viewing the first pathological image comprising a number of times the first pathological image was viewed and a length of time over which the first pathological image has been viewed and a position of a portion of the first pathological image that was enlarged and displayed, and diagnostic information for the first affected tissue, diagnosis support information for supporting diagnosis of a second pathological image corresponding to a second affected tissue to be diagnosed that has been imaged by the microscope; and a learning procedure, wherein the learning procedures assigns at least one of the plurality of pixels an attention value based on a magnification ratio of the at least one pixel, a viewing time of the at least one pixel, a number of times the at least one pixel was viewed, generates a map image comprising the attention values corresponding to the plurality of pixels, and determines the diagnostic information for the first affected tissue corresponding to the first pathological image by identifying a first portion of the first pathological image having a positive result and a second portion of the first pathological image having a negative result. ### Claim 15 (depends on 14) The diagnosis support system according to claim 14, wherein the diagnosis support system further includes a display control device, and the display control device controls, on a basis of the diagnosis support information, an attention region, which is a region estimated to influence a diagnosis, to be visibly superimposed and displayed on the second pathological image. ### Claim 16 (depends on 15) The diagnosis support system according to claim 15, wherein the display control device changes a display mode of the attention region in accordance with a degree of influence on the diagnosis or a degree of reliability of the diagnosis support information on a basis of the diagnosis support information. ### Claim 17 (depends on 15) The diagnosis support system according to claim 15, wherein the display control device performs a control to display a part of an image of the second affected tissue corresponding to the attention region. ### Claim 18 (depends on 14) The diagnosis support system according to claim 14, wherein the diagnosis support information is a diagnosis result for the first affected tissue and a predicted diagnosis prediction result. ### Claim 19 (depends on 18) The diagnosis support system according to claim 18, wherein the diagnosis prediction result is whether a lesion site has been found, a type of the lesion site, a degree of progression of the lesion site, or a probability of being the lesion site. ### Claim 20 A diagnosis support method comprising: deriving, by a computer, on a basis of a first pathological image corresponding to a first affected tissue, history information regarding a history of viewing the first pathological image comprising a number of times the first pathological image was viewed and a length of time over which the first pathological image has been viewed and a position of a portion of the first pathological image that was enlarged and displayed, and diagnostic information for the first affected tissue corresponding to the first pathological image, diagnosis support information for supporting diagnosis of a second pathological image corresponding to a second affected tissue to be diagnosed; assigning, by the computer, at least one of the plurality of pixels an attention value based on a magnification ratio of the at least one pixel, a viewing time of the at least one pixel, a number of times the at least one pixel was viewed, generating, by the computer, a map image comprising the attention values corresponding to the plurality of pixels, and determining, by the computer, the diagnostic information for the first affected tissue corresponding to the first pathological image by identifying a first portion of the first pathological image having a positive result and a second portion of the first pathological image having a negative result. ### Claim 21 A diagnosis support system comprising: a microscope; and software used for processing of a pathological image corresponding to an object to be imaged by the microscope, wherein the software causes an information processing device to execute, on a basis of a first pathological image corresponding to a first affected tissue, history information regarding a history of viewing the first pathological image comprising a number of times the first pathological image was viewed and a length of time over which the first pathological image has been viewed and a position of a portion of the first pathological image that was enlarged and displayed, and diagnostic information for the first affected tissue, processing of deriving diagnosis support information for supporting diagnosis of a second pathological image corresponding to a second affected tissue to be diagnosed that has been imaged by the microscope; and wherein the software further causes the information processing device to execute a learning procedure comprising assigning at least one of the plurality of pixels an attention value based on a magnification ratio of the at least one pixel, a viewing time of the at least one pixel, a number of times the at least one pixel was viewed, generating a map image comprising the attention values corresponding to the plurality of pixels, determining the diagnostic information for the first affected tissue corresponding to the first pathological image by identifying a first portion of the first pathological image having a positive result and a second portion of the first pathological image having a negative result.