Papers for

connectomics software engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

ContactCut improves 3D error correction in brain connectivity maps

ContactCut: A Partition-Aware Contact Selection Framework for False-Merge Correction in Connectomics

Abstract: Localized false-merge correction in connectomics requires converting an identified error into an executable native 3D partition. Still, neither intermediate correction predictions nor seeded graph solvers alone determine which native source-sink constraints should define that partition. We formulate this problem as a 3D-native partition-aware contact selection problem: selecting candidate contacts based on the complete partitions they induce. Our solution comprises two components: ContactCut (CC)-Auto, which uses learned single-contact selection, and ContactCut (CC)-Search, which enables bounded paired-contact search, generates compact alternatives, and applies learned panel ranking. On historical two-way false-merge corrections from MICrONS and FlyWire, CC-Auto improves failure-aware 3D partition (FA-3D Part.) mIoU by 5.9 and 3.4 points over the strongest graph-based controls and by 12.5 and 10.0 points over the best learned baselines. A MICrONS-trained ranker transfers to FlyWire with negligible degradation. CC-Search expands oracle reachability and prioritizes near-oracle alternatives. The code is available at https://github.com/bentake/ContactCut.

Sun 1 NovComputer Vision and Pattern Recognition
The gist
Mapping brain connections accurately is hard because sometimes different neurons get mistakenly merged together. The authors address this problem by focusing on how to select tiny contact points that define where these incorrect merges happen. They created ContactCut, a method that uses learned models to pick these points and identify better partitions in 3D brain maps. Their method works better than previous ones on data from real brain mapping projects and even transfers well between different datasets.
Open → 2611.01457v1