# US 12,009,104 B2 · Medical image processing apparatus, medical image processing method, machine learning system, and program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,009,104 B2 - Document ID: US12009104B2 - Status: Granted - Kind: B2 - Application number: 17/117,408 - Filed: 2020-12-10 - Published: 2021-04-29 - Granted: 2024-06-11 - Earliest claimed: 2018-06-28 - Assignees: FUJIFILM Corporation - Applicants: FUJIFILM Corporation - Inventors: Misaki Kawahara; Goro Miura; Satoshi Naito; Shumpei Kamon; Masaaki Oosake - Web page: https://patentgrep.com/patent/US12009104B2 ## CPC - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - A61B 1/000096: {using artificial intelligence} - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 3/098: Distributed learning, e.g. federated learning - G06N 20/00: Machine learning - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/776: Validation; Performance evaluation - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - A61B 6/03: Computed tomography [CT] - G06N 3/045: Combinations of networks - G06V 2201/03: Recognition of patterns in medical or anatomical images - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract There are provided a medical image processing apparatus, a medical image processing method, a machine learning system, and a program that can reduce the volume of communication and can reduce the processing load of retraining or additional training that is performed by a machine learning apparatus. A medical image processing apparatus (13) includes: a trainer (26) that performs additional training for a first computer-aided diagnosis device on the basis of an input medical image; an evaluation unit that compares a second computer-aided diagnosis device obtained by the additional training with the first computer-aided diagnosis device and evaluates whether learning difference information about the additional training contributes to improvement of performance of the first computer-aided diagnosis device; a communication determination unit that determines, on the basis of a result of evaluation, whether the learning difference information is to be communicated; and a communication unit (34) that outputs the learning difference information in accordance with a result of determination by the communication determination unit. ## Claims ### Claim 1 A medical image processing apparatus comprising one or more first processors configured to: perform additional training for a first computer-aided diagnosis device on a basis of an input medical image; compare a second computer-aided diagnosis device obtained by the additional training with the first computer-aided diagnosis device and evaluate whether learning difference information about the additional training contributes to improvement of performance of the first computer-aided diagnosis device; determine, on a basis of a result of the evaluation, whether the learning difference information is to be communicated; and perform communication to output the learning difference information in accordance with a result of the determination. ### Claim 2 (depends on 1) The medical image processing apparatus according to claim 1, wherein the one or more first processors are further configured to: extract feature value information about the medical image; perform a recognition process on a basis of the feature value information, wherein information; and perform the additional training on a basis of the feature value information and a result of the recognition process. ### Claim 3 (depends on 1) The medical image processing apparatus according to claim 1, further comprising a first memory configured to store parameter information about the first computer-aided diagnosis device. ### Claim 4 (depends on 1) The medical image processing apparatus according to claim 1, wherein the learning difference information includes parameter difference information that indicates a difference between parameter information about the first computer-aided diagnosis device and parameter information about the second computer-aided diagnosis device. ### Claim 5 (depends on 1) The medical image processing apparatus according to claim 1, wherein the learning difference information includes parameter information about the second computer-aided diagnosis device. ### Claim 6 (depends on 2) The medical image processing apparatus according to claim 2, wherein the learning difference information includes the feature value information. ### Claim 7 (depends on 1) The medical image processing apparatus according to claim 1, wherein the learning difference information includes the medical image provided for the additional training. ### Claim 8 (depends on 1) The medical image processing apparatus according to claim 1, wherein the first computer-aided diagnosis device is a first recognizer that is created in advance by performing machine learning using a first learning dataset, and the second computer-aided diagnosis device is a second recognizer for which a parameter of the first recognizer is changed. ### Claim 9 (depends on 1) A machine learning system comprising: the medical image processing apparatus according to claim 1; and an information processing apparatus including one or more second processors configured to receive the learning difference information output from the medical image processing apparatus to collect learning data including the learning difference information. ### Claim 10 (depends on 9) The machine learning system according to claim 9, wherein the one or more second processors are configured to use the received learning difference information to perform a training process for the first computer-aided diagnosis device. ### Claim 11 (depends on 9) The machine learning system according to claim 9, wherein the information processing apparatus further includes a second memory configured to store the received learning difference information. ### Claim 12 A medical image processing method to be performed by a medical image processing apparatus, the medical image processing method comprising: a step of obtaining a medical image; a step of performing additional training for a first computer-aided diagnosis device by using a trainer on a basis of the obtained medical image; a step of comparing a second computer-aided diagnosis device obtained by the additional training using the trainer with the first computer-aided diagnosis device and evaluating whether learning difference information about the additional training contributes to improvement of performance of the first computer-aided diagnosis device; a step of determining, on a basis of a result of evaluation obtained in the evaluating, whether the learning difference information is to be communicated; and a step of outputting, from a communication unit, the learning difference information in accordance with a result of determination obtained in the determining. ### Claim 13 A storage medium that is a non-transitory computer-readable storage medium and that, in a case where a command stored in the storage medium is read by a computer, causes the computer to execute: a function of a trainer performing additional training for a first computer-aided diagnosis device on a basis of an input medical image; a function of comparing a second computer-aided diagnosis device obtained by the additional training using the trainer with the first computer-aided diagnosis device and evaluating whether learning difference information about the additional training contributes to improvement of performance of the first computer-aided diagnosis device; a function of determining, on a basis of a result of evaluation obtained in the evaluating, whether the learning difference information is to be communicated; and a function of outputting, from a communication unit, the learning difference information in accordance with a result of determination obtained in the determining.