AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking

Yuheng Li, Tianyu Luan, Yizhou Wu, Shaoyan Pan, Yenho Chen, Xiaofeng Yang

ECCV 2024 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 8 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
replace random masking with reconstruction-guided AnatoMaskSTU-Net-B SSL pretraining · TotalSegmentatorDSC (%): 83.6 -> 84.3Improved
use hierarchical decoder instead of simple decoder (ablation)AnatoMask · TotalSegmentatorDSC (%): 83.4 -> 84.3Improved
AnatoMask masking on a simple decoder vs random masking (ablation)simple decoder MIM · TotalSegmentatorDSC (%): 82.9 -> 83.4Improved
add self-distillation (EMA teacher) (ablation)AnatoMask · TotalSegmentatorDSC (%): 83.7 -> 84.3Improved
mask high-loss regions instead of low-loss regions (ablation)AnatoMask · TotalSegmentatorDSC (%): 83.6 -> 84.3Improved
use easy-to-hard instead of hard-to-easy masking dynamics (ablation)AnatoMask · TotalSegmentatorDSC (%): 84.0 -> 84.3Improved
increase masking ratio from 0.6 to 0.8 or 0.9 (ablation)AnatoMask · TotalSegmentatorDSC (%): 84.3 -> 84.1 (0.8), 84.2 (0.9)Hurt
scale backbone from STU-Net-B to STU-Net-L and HAnatoMask · TotalSegmentatorDSC (%): 84.3 -> 87.8 -> 89.0Improved
transfer AnatoMask pretraining vs SparKSTU-Net-B · AMOS22 (transfer)DSC (%): 88.5 -> 89.1Improved
transfer AnatoMask pretraining vs SparKSTU-Net-B · FLARE22 (transfer)DSC (%): 93.8 -> 94.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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