# US 12,762,821 B2 · Medical image processing device, method of operating medical image processing device, non-transitory computer readable medium, and endoscope system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,762,821 B2 - Document ID: US12762821B2 - Status: Granted - Kind: B2 - Application number: 18/664,261 - Filed: 2024-05-14 - Published: 2024-11-21 - Granted: 2026-10-13 - Earliest claimed: 2023-05-16 - Assignees: FUJIFILM Corporation - Applicants: FUJIFILM Corporation - Inventors: Shumpei Kamon - Web page: https://patentgrep.com/patent/US12762821B2 ## CPC - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - A61B 1/000096: {using artificial intelligence} - G06T 7/0012: {Biomedical image inspection} - G06V 10/764: using classification, e.g. of video objects - G06T 2207/10068: Endoscopic image - G06T 2207/20081: Training; Learning - G06T 2207/30096: Tumor; Lesion - G06V 2201/031: of internal organs - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A medical image processing device includes a medical image acquisition unit that acquires a medical image, a region classification unit that classifies a region of a subject into a first region or a second region, and a region-of-interest detection unit that detects a region of interest from the medical image. The region-of-interest detection unit detects the region of interest using a first trained model obtained from machine learning with a first data set including data of the first region and data of the second region or a second trained model obtained from machine learning with a second data set including the data of the second region. ## Claims ### Claim 1 A medical image processing device comprising: one or more processors configured to: acquire a medical image in which a subject is imaged; classify a region of the subject in the medical image into a first region or a second region; detect a region of interest from the medical image using a first trained model obtained from machine learning with a first data set including data of the first region and data of the second region, with regard to the medical image of which the region of the subject is classified into the first region; and detect a region of interest from the medical image using a second trained model obtained from machine learning with a second data set including data of the second region, with regard to the medical image of which the region of the subject is classified into the second region, and the first data set includes relatively more data of the first region compared to data of the second region. ### Claim 2 (depends on 1) The medical image processing device according to claim 1, wherein the first trained model has a higher detection accuracy for the region of interest in the first region than for the region of interest in the second region, and the second trained model has a higher detection accuracy for the region of interest in the second region than for the region of interest in the first region. ### Claim 3 (depends on 1) The medical image processing device according to claim 1, wherein the first data set is composed of data of the first region which includes images containing the region of interest and images not containing the region of interest, and data of the second region which includes images not containing the region of interest. ### Claim 4 (depends on 1) The medical image processing device according to claim 1, wherein either the first trained model or the second trained model is the trained model trained with either the first data set or the second data set, which differ in data and/or combinations of data. ### Claim 5 (depends on 1) The medical image processing device according to claim 1, wherein the one or more processors configured to analyze the medical image to acquire a classification result indicating the region of the subject in the medical image, and select the first trained model or the second trained model according to the classification result. ### Claim 6 (depends on 1) The medical image processing device according to claim 1, wherein the one or more processors configured to acquire a classification result indicating the region of the subject in the medical image on the basis of a user's input, and select the first trained model or the second trained model according to the classification result. ### Claim 7 (depends on 1) The medical image processing device according to claim 1, wherein the one or more processors configured to perform a control of notifying a user of a detection result obtained from the first trained model or the second trained model. ### Claim 8 (depends on 7) The medical image processing device according to claim 7, wherein the one or more processors configured to perform a display control to display the acquired time-series medical images on a medical image display, and superimpose the detection results onto the medical images in which the region of interest is detected and display the superimposed images on the medical image display, for the notification. ### Claim 9 (depends on 7) The medical image processing device according to claim 7, wherein the one or more processors configured to notify a user of not only the detection result but also a selection state of the first trained model or the second trained model. ### Claim 10 (depends on 1) The medical image processing device according to claim 1, wherein the machine learning is deep learning. ### Claim 11 (depends on 1) An endoscope system comprising: an endoscope that captures the medical image; and the medical image processing device according to claim 1. ### Claim 12 A method of operating a medical image processing device, comprising: a step of acquiring a medical image in which a subject is imaged; a step of classifying a region of the subject in the medical image into a first region or a second region; a step of detecting a region of interest from the medical image using a first trained model obtained from machine learning with a first data set including data of the first region and data of the second region, with regard to the medical image of which the region of the subject is classified into the first region; and a step of detecting a region of interest from the medical image using a second trained model obtained from machine learning with a second data set including the data of the second region, with regard to the medical image of which the region of the subject is classified into the second region, wherein the first data set includes relatively more data of the first region compared to data of the second region. ### Claim 13 A non-transitory computer readable medium for storing a computer-executable program, the computer-executable program causing a computer to execute: processing for acquiring a medical image in which a subject is imaged; processing for classifying a region of the subject in the medical image into a first region or a second region; processing for detecting a region of interest from the medical image using a first trained model obtained from machine learning with a first data set including data of the first region and data of the second region, with regard to the medical image of which the region of the subject is classified into the first region; and processing for detecting a region of interest from the medical image using a second trained model obtained from machine learning with a second data set including the data of the second region, with regard to the medical image of which the region of the subject is classified into the second region, wherein the first data set includes relatively more data of the first region compared to data of the second region.