# US 2025/0095155 A1 · Multiscale subnetwork fusion with adaptive data sampling for brain lesion detection and segmentation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0095155 A1 - Document ID: US20250095155A1 - Status: Published application - Kind: A1 - Application number: 18/469,760 - Filed: 2023-09-19 - Published: 2025-03-20 - Earliest claimed: 2023-09-19 - Assignees: Siemens Medical Solutions USA, Inc.; The Regents of the University of Michigan - Applicants: Siemens Medical Solutions USA, Inc.; The Regents of The University of Michigan - Inventors: Youngjin Yoo; Eli Gibson; Yue Cao; James Michael Balter - Web page: https://patentgrep.com/patent/US20250095155A1 ## CPC - G06T 7/11: Region-based segmentation - G06T 7/0012: {Biomedical image inspection} - G06T 2207/10081: Computed x-ray tomography [CT] - G06T 2207/10088: Magnetic resonance imaging [MRI] - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30016: Brain - G06T 2207/30096: Tumor; Lesion - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Systems and methods for segmenting one or more lesions from medical image patches are provided. An input medical image patch depicting one or more lesions is received. The one or more lesions are segmented from the input medical image patch using a plurality of machine learning based segmentation networks to respectively generate a plurality of initial segmentation masks. Each of the plurality of machine learning based segmentation networks is trained to segment lesions from patches with a different field of view size. A final segmentation mask of the one or more lesions is generated based on the plurality of initial segmentation masks. The final segmentation mask of the one or more lesions is output. ## Claims ### Claim 1 A computer-implemented method comprising: receiving an input medical image patch depicting one or more lesions; segmenting the one or more lesions from the input medical image patch using a plurality of machine learning based segmentation networks to respectively generate a plurality of initial segmentation masks, each of the plurality of machine learning based segmentation networks trained to segment lesions from patches with a different field of view size; generating a final segmentation mask of the one or more lesions based on the plurality of initial segmentation masks; and outputting the final segmentation mask of the one or more lesions. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein generating a final segmentation mask of the one or more lesions based on the plurality of initial segmentation masks comprises: combining the plurality of initial segmentation masks; and generating the final segmentation mask based on the combined initial segmentation masks. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein combining the plurality of initial segmentation masks comprises: combining intensity values of corresponding voxels in the plurality of initial segmentation masks into respective scores. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein generating the final segmentation mask based on the combined initial segmentation masks comprises: generating the final segmentation mask based on the scores using a machine learning based fusion network. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the plurality of machine learning based segmentation networks are trained by extracting training patches from training medical images depicting at least one lesion, the training patches extracted from the training medical images based on a size of the at least one lesion. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein at least some of the plurality of machine learning based segmentation networks are trained with different loss functions. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein at least some of the plurality of machine learning based segmentation networks are implemented with different network architectures. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein at least some of the plurality of machine learning based segmentation networks are implemented with different hyperparameters. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein the one or more lesions comprise one or more brain lesions located on a brain of a patient. ### Claim 10 An apparatus comprising: means for receiving an input medical image patch depicting one or more lesions; means for segmenting the one or more lesions from the input medical image patch using a plurality of machine learning based segmentation networks to respectively generate a plurality of initial segmentation masks, each of the plurality of machine learning based segmentation networks trained to segment lesions from patches with a different field of view size; means for generating a final segmentation mask of the one or more lesions based on the plurality of initial segmentation masks; and means for outputting the final segmentation mask of the one or more lesions. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein the means for generating a final segmentation mask of the one or more lesions based on the plurality of initial segmentation masks comprises: means for combining the plurality of initial segmentation masks; and means for generating the final segmentation mask based on the combined initial segmentation masks. ### Claim 12 (depends on 11) The apparatus of claim 11, wherein the means for combining the plurality of initial segmentation masks comprises: means for combining intensity values of corresponding voxels in the plurality of initial segmentation masks into respective scores. ### Claim 13 (depends on 12) The apparatus of claim 12, wherein the means for generating the final segmentation mask based on the combined initial segmentation masks comprises: means for generating the final segmentation mask based on the scores using a machine learning based fusion network. ### Claim 14 (depends on 10) The apparatus of claim 10, wherein the plurality of machine learning based segmentation networks are trained by extracting training patches from training medical images depicting at least one lesion, the training patches extracted from the training medical images based on a size of the at least one lesion. ### Claim 15 A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising: receiving an input medical image patch depicting one or more lesions; segmenting the one or more lesions from the input medical image patch using a plurality of machine learning based segmentation networks to respectively generate a plurality of initial segmentation masks, each of the plurality of machine learning based segmentation networks trained to segment lesions from patches with a different field of view size; generating a final segmentation mask of the one or more lesions based on the plurality of initial segmentation masks; and outputting the final segmentation mask of the one or more lesions. ### Claim 16 (depends on 15) The non-transitory computer readable medium of claim 15, wherein generating a final segmentation mask of the one or more lesions based on the plurality of initial segmentation masks comprises: combining the plurality of initial segmentation masks; and generating the final segmentation mask based on the combined initial segmentation masks. ### Claim 17 (depends on 15) The non-transitory computer readable medium of claim 15, wherein at least some of the plurality of machine learning based segmentation networks are trained with different loss functions. ### Claim 18 (depends on 15) The non-transitory computer readable medium of claim 15, wherein at least some of the plurality of machine learning based segmentation networks are implemented with different network architectures. ### Claim 19 (depends on 15) The non-transitory computer readable medium of claim 15, wherein at least some of the plurality of machine learning based segmentation networks are implemented with different hyperparameters. ### Claim 20 (depends on 15) The non-transitory computer readable medium of claim 15, wherein the one or more lesions comprise one or more brain lesions located on a brain of a patient.