AI Paper Atlas

Research map / Detection and segmentation / CNN features

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

Yannick Kirchhoff, Maximilian R Rokuss, Saikat Roy, Balint Kovacs, Constantin Ulrich, Tassilo Wald, Maximilian Zenk, Philipp Vollmuth, Jens Kleesiek, Fabian Isensee, Klaus H. Maier-Hein

ECCV 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 73 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Skeleton Recall Loss to nnUNetnnUNet · ToothFairyclDice: 89.16 -> 92.05Improved
add Skeleton Recall Loss to nnUNetnnUNet · DRIVE (5-fold CV)beta0 error: 57.00 -> 38.75Improved
add Skeleton Recall Loss to nnUNetnnUNet · TopCoW multi-classDice: 85.36 -> 86.59Improved
add Skeleton Recall Loss to nnUNetnnUNet · TopCoW multi-classbeta0 error: 0.137 -> 0.151Hurt
add Skeleton Recall Loss to nnUNetnnUNet · Cracks (5-fold CV)beta0 error: 0.147 -> 0.148No clear effect
add Skeleton Recall Loss to HRNetHRNet · DRIVE (HRNet)Dice: 80.34 -> 76.08Hurt
add Skeleton Recall Loss to HRNetHRNet · DRIVE (HRNet)clDice: 77.83 -> 84.20Improved
replace clDice loss soft skeleton with Skeleton Recall Loss tubed skeletonnnUNet training · Training costadditional training time: 88% -> 8%Improved
replace clDice loss with Skeleton Recall LossnnUNet training · Training costadditional VRAM: 52% -> 2%Improved
replace clDice Loss with Skeleton Recall Loss on 13-class datannUNet · TopCoW multi-classfeasibilityImproved
use Topo-clDice Loss instead of clDice LossnnUNet · Roadsbeta0 error: 6.539 -> 11.00Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy