AI Paper Atlas

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

Beyond Isolated Scans: Cross-Phase Alignment of Structure and Topology for 3D Medical Pretraining

Wenzhuo xu, YANJIE ZHOU, Yujian Hu, Hongkun Zhang, Minfeng Xu

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 0 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 spectral consistency (Lspec) to reconstruction baseline (ablation)CAST · Parse22Dice: 0.7972 -> 0.8423; +4.51%Improved
add geometry-aware topological consistency (Lgeo) to reconstruction baseline (ablation)CAST · Parse22Dice: 0.7972 -> 0.8365; +3.93%Improved
combine Lspec and Lgeo (ablation)CAST · Parse22Dice: 0.8423 -> 0.8463Improved
add Lspec to reconstruction baseline (ablation)CAST · COVID19-20Dice: 0.6271 -> 0.6935Improved
add Lgeo and Lspec together (ablation)CAST · COVID19-20Dice: 0.6975 -> 0.7075Improved
use Diff+TopHat keypoint sampling instead of Random sampling (ablation)CAST · Parse22Dice: 0.8268 -> 0.8463Improved
use Diff+TopHat sampling instead of Diff only (ablation)CAST · Parse22Dice: 0.8021 -> 0.8463Improved
use 1024 keypoints instead of 512 (ablation)CAST · Parse22Dice: 0.8174 -> 0.8463Improved
use 1024 keypoints instead of 2048 (ablation)CAST · Parse22Dice: 0.8132 -> 0.8463Improved
use true paired NCCT-CECT pretraining instead of shuffled pairs (ablation)CAST · COVID19-20Dice: 0.6364 -> 0.7075Improved
use paired cross-phase pretraining instead of NCCT-only CAST (ablation)CAST · COVID19-20 (10% labels)Dice: 2.15% gain at 10% labels (0.6514)Improved
use 10% paired pretraining data versus full NCCT-only data (ablation)CAST · COVID19-20Dice: +0.0094 Dice; full 13,850 pairs reach 0.7075Improved

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