AI Paper Atlas

Research map / 3D vision / 3D generation

Revisiting 2D Foundation Models for Scalable 3D Medical Image Classification

Han Liu, Bogdan Georgescu, Yanbo Zhang, Youngjin Yoo, Michael Baumgartner, Riqiang Gao, Jianing Wang, Gengyan Zhao, Eli Gibson, Dorin Comaniciu, Sasa Grbic

CVPR 2026 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 5 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 linear probing with AnyMC3D adaptation (ablation)MII · 10-task averageaverage AUC: 0.785 -> 0.894Improved
replace linear probing with AnyMC3D adaptation (ablation)MedGemma · 10-task averageaverage AUC: 0.690 -> 0.866Improved
use DINOv3 backbone instead of MedGemma under AnyMC3DAnyMC3D · 10-task averageaverage AUC: 0.866 -> 0.894Improved
use DINOv3 instead of medical MII under AnyMC3DAnyMC3D · 10-task averageaverage AUC: 0.894 -> 0.894No clear effect
use DINOv3 instead of DINOv2 (ablation)AnyMC3D · 3D medical classificationAUCNo clear effect
add auxiliary pixel-level supervision (ablation)AnyMC3D (DINOv3) · PDAC early detection T5AUC: 0.962 -> 0.973Improved
use AnyMC3D (DINOv3) instead of PanDxPDAC detection · T5AUC: 0.949 -> 0.962Improved
use full finetuning instead of linear probing (ablation)MedicalNet · T4AUC: 0.654 -> 0.899Improved
use full finetuning instead of linear probing (ablation)VoCo · T4AUC: 0.702 -> 0.919Improved
use LoRA instead of linear probing (ablation)MedicalNet · T4AUC: 0.654 -> 0.889Improved
use LoRA instead of linear probing (ablation)VoCo · T4AUC: 0.702 -> 0.838Improved
use AnyMC3D with 20% training data instead of 3D DenseNetT3 low-data · T3 (20% data)AUC: 0.741 -> 0.924Improved

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