# US 2023/0410482 A1 · Machine learning system, recognizer, learning method, and program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0410482 A1 - Document ID: US20230410482A1 - Status: Published application - Kind: A1 - Application number: 18/457,374 - Filed: 2023-08-29 - Published: 2023-12-21 - Earliest claimed: 2021-03-01 - Assignees: FUJIFILM Corporation - Applicants: FUJIFILM Corporation - Inventors: Masaaki OOSAKE; Toshihiro USUDA - Web page: https://patentgrep.com/patent/US20230410482A1 ## CPC - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - A61B 8/14: Echotomography - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/09: Supervised learning - G06T 1/00: General purpose image data processing - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 7/0012: {Biomedical image inspection} - G06V 10/945: {User interactive design; Environments; Toolboxes} - G16H 30/40: for processing medical images, e.g. editing - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/30: for calculating health indices; for individual health risk assessment - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G06T 2207/10132: Ultrasound image - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/20104: Interactive definition of region of interest [ROI] - G06T 2207/20212: Image combination - G06T 2207/30096: Tumor; Lesion - G06V 10/82: using neural networks - G06V 2201/03: Recognition of patterns in medical or anatomical images - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract There are provided a machine learning system, a learning method, and a program that can facilitate learning of a large number of combined medical images. A machine learning system (10) includes: an image database (14) that stores a plurality of medical images; a geometric-shape database (16) that stores geometric shapes to be superimposed on the medical images; a processor (22); and a learning model (30), in which the processor (22) is configured to perform a selection accepting process of accepting selection of a medical image from among the medical images stored in the image database (14) and selection of a geometric shape from among the geometric shapes stored in the geometric-shape database (16), a geometric-shape combining process of combining the selected medical image and the selected geometric shape and generating a composite image, and a training process of making the learning model perform learning by using the composite image. ## Claims ### Claim 1 A machine learning system comprising: an image database that stores a plurality of medical images; a geometric-shape database that stores geometric shapes to be superimposed on the medical images; a processor; and a learning model, wherein the processor is configured to perform a selection accepting process of accepting selection of a medical image from among the medical images stored in the image database and selection of a geometric shape from among the geometric shapes stored in the geometric-shape database, a geometric-shape combining process of combining the selected medical image and the selected geometric shape and generating a composite image, and a training process of making the learning model perform learning by using the composite image. ### Claim 2 (depends on 1) The machine learning system according to claim 1, wherein in the training process, the medical image accepted in the selection accepting process is used at least twice, and the learning model is made to perform learning by first using the medical image for which the geometric-shape combining process has not been performed and by next using the composite image for which the geometric-shape combining process has been performed. ### Claim 3 (depends on 1) The machine learning system according to claim 1, wherein the processor is configured to perform a size accepting process of accepting a size of the geometric shape that is combined in the geometric-shape combining process, and in the geometric-shape combining process, the geometric shape is combined with the medical image on the basis of the size accepted in the size accepting process. ### Claim 4 (depends on 1) The machine learning system according to claim 1, wherein the geometric-shape database stores in association with each geometric shape of the geometric shapes, at least one of information about a combination-allowed region in the medical images or maximum and minimum values of a size of the geometric shape. ### Claim 5 (depends on 1) The machine learning system according to claim 1, wherein the image database stores in association with each of the medical images, information about a region of interest, and in the geometric-shape combining process, the geometric shape is combined such that at least a portion of the geometric shape is superimposed on the region of interest, by using the information about the region of interest. ### Claim 6 (depends on 1) The machine learning system according to claim 1, wherein the image database stores in association with each of the medical images, information about a region of interest, and in the geometric-shape combining process, the geometric shape is combined in a region outside the region of interest, by using the information about the region of interest. ### Claim 7 (depends on 1) The machine learning system according to claim 1, wherein in the geometric-shape combining process, a plurality of composite images are generated by changing a position and a size of the selected geometric shape, and in the training process, the learning model is made to perform learning by using the plurality of composite images. ### Claim 8 (depends on 1) The machine learning system according to claim 1, wherein the medical images are images obtained from an ultrasound diagnostic apparatus. ### Claim 9 (depends on 1) A recognizer that is trained in the machine learning system according to claim 1 and that recognizes a region of interest from a medical image to which a geometric shape is added. ### Claim 10 A learning method using a machine learning system comprising: an image database that stores a plurality of medical images; a geometric-shape database that stores geometric shapes to be superimposed on the medical images; a processor; and a learning model, wherein the processor is configured to perform a selection accepting step of accepting selection of a medical image from among the medical images stored in the image database and selection of a geometric shape from among the geometric shapes stored in the geometric-shape database, a geometric-shape combining step of combining the selected medical image and the selected geometric shape and generating a composite image, and a training step of making the learning model perform learning by using the composite image. ### Claim 11 (depends on 10) A non-transitory, computer-readable tangible recording medium to which a program for causing, when read by a computer, the computer to execute the learning method according to claim 10 is recorded.