Get Started
Home
Topics
Search
Library
Research questionHow can fiber-bundle segmentation in tracer histology preserve topology while exposing oversegmentation missed by detection metrics?Tracer histology contains branching axon bundles whose structure matters for anatomical interpretation, but pixel-overlap scores and any-overlap detection can hide excessive or spatially incorrect predictions. Segmentation quality therefore requires distinguishing bundle detection from accurate topology and spatial extent.
AI
Computer Vision
Evaluation & Benchmarks
Health
Image & Video Processing
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Topology-Aware Training and Spatial Diagnostics for Fiber Bundle Segmentation in Tracer HistologyThe evidence concerns fiber-bundle segmentation in macaque tracer histology using a frozen DINOv3 backbone. It compares BCE-Dice, clDice, Betti matching, and Topograph, and reports topology and spatial diagnostics including beta-zero error, false discovery rate, area ratio, and Excess32.research paper · Sep 3, 2026
Related questions
How can whole-slide image classifiers preserve irregular tissue regions while modeling relationships across spatially separated regions?How can tissue regions and patch coordinates be extracted from whole-slide images despite staining and artifact variation?How can brain MRI super-resolution preserve continuous tissue mixtures at partial-volume tissue transitions?How can retinal fundus models remain interpretable and accurate when pathology alters vessel appearance?