# Machine Learning Segmentation **Entity class:** Concept or analytic term **Collection:** [[collections/Neurotech|Neurotech]] **Type:** Computational imaging method **Primary sources:** [[articles/2026 Annual Report on Brain-Computer Interfaces|2026 Annual Report on Brain-Computer Interfaces]]; [[articles/The Organic-Synthetic Brain Atlas|The Organic-Synthetic Brain Atlas]] ## Definition **Machine-learning segmentation** uses trained models to identify and separate structures in image data. Connectomics applies it to dense microscopy volumes where manual tracing alone would be prohibitive. ## Relationships - Flood-filling networks and PATHFINDER are routed through [[wiki/Connectome Reconstruction Infrastructure|Connectome Reconstruction Infrastructure]]. - [[wiki/FlyWire Consortium|FlyWire]] combined automated segmentation with 33 reported person-years of proofreading. - [[wiki/PRISM (E11 Bio)|PRISM]] combines morphology with molecular barcode evidence; its preprint reports eightfold greater tracing accuracy in its pilot comparison, not elimination of proofreading across connectomics. - Model output remains a provisional reconstruction until error detection, review, and provenance controls are applied. <!-- BEGIN HUMANIZED RELATIONSHIPS 2026-09-11 --> This entry's documented connections are expressed in its definition and related-work routes, with provenance retained in the source-linked material. <!-- END HUMANIZED RELATIONSHIPS 2026-09-11 --> ## Related Work in the Corpus <!-- BEGIN HUMANIZED CORPUS ROUTES 2026-09-11 --> - In [[articles/2026 Annual Report on Brain-Computer Interfaces|2026 Annual Report on Brain-Computer Interfaces]], **FlyWire: Whole-Brain Completeness at Insect Scale** provides the narrative context for **Machine Learning Segmentation**: The companion annotation paper, led by the Cambridge Drosophila Connectomics Group under Gregory Jefferis (MRC Laboratory of Molecular Biology and University of Cambridge), provided systematic hierarchical annotation of neuronal… - In [[articles/2026 Annual Report on Brain-Computer Interfaces|2026 Annual Report on Brain-Computer Interfaces]], **MICrONS: Function-Structure Registration at Mammalian Scale** provides the narrative context for **Machine Learning Segmentation**: The consortium of 150+ scientists across 22 institutions was led by the Allen Institute for Brain Science (Senior Investigator Dr. <!-- END HUMANIZED CORPUS ROUTES 2026-09-11 -->