Research map / Label-efficient and robust learning / Self-supervised and contrastive
Anatomical Invariance Modeling and Semantic Alignment for Self-supervised Learning in 3D Medical Image Analysis
Yankai Jiang, Mingze Sun, Heng Guo, Xiaoyu Bai, Ke Yan, Le Lu, Minfeng Xu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add inter-volume anatomical invariance contrastive loss (cross-volume views) (ablation) | IBOT · FLARE 2022 | DSC: 84.04 -> 85.41 | Improved |
| add inter-volume anatomical invariance contrastive loss (cross-volume views) (ablation) | Alice · FLARE 2022 | DSC: 85.63 -> 86.87 | Improved |
| add CASA module (ablation) | Alice · FLARE 2022 | DSC: 85.66 -> 86.87 | Improved |
| add CASA module (ablation) | IBOT · FLARE 2022 | DSC: 84.04 -> 85.34 | Improved |
| add CASA module (ablation) | SIM · FLARE 2022 | DSC: 83.96 -> 85.21 | Improved |
| use BYOL-style cosine loss instead of InfoNCE (no negatives) (ablation) | Alice · FLARE 2022 | DSC: 86.83 -> 86.87 | No clear effect |
| SSL pre-training with Alice vs random initialization | UNETR · FLARE 2022 | DSC: 80.95 -> 85.81 | Improved |
| Alice pre-training vs strongest hybrid SSL baseline CMAE | nnFormer · FLARE 2022 | DSC: 84.47 -> 86.87 | Improved |
| Alice pre-training vs ViT SSL baselines on COVID-19 transfer | ViT-B · MosMedData COVID-19 | AUC: 87.73 -> 90.88 | Improved |
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.
- UniMiSS — UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Barrier (ECCV 2022) · better on 2 of 2 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
- Structure-aware Semantic Discrepancy and Consistency for 3D Medical Image Self-supervised Learning (ICCV 2025 · similarity 0.90)
- Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self Supervision (CVPR 2024 · similarity 0.88)
- VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis (CVPR 2024 · similarity 0.88)
- Autoregressive Sequence Modeling for 3D Medical Image Representation (AAAI 2025 · similarity 0.87)
- AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images (AAAI 2025 · similarity 0.86)
- Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration (CVPR 2024 · similarity 0.85)
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.
