AI Paper Atlas

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

AbdCTBench: Learning Clinical Biomarker Representations from Abdominal Surface Geometry

Muhammad Ahmed Chaudhry, Suhana Bedi, Pola Lydia Lagari, Brian T Layden, William Galanter, Ayis Pyrros, Sanmi Koyejo

ICLR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations

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
train a shared-backbone multi-task model on all 10 biomarkers instead of single-task (ablation)ResNet-18 · Age predictionMAE: 6.472 -> 14.529Hurt
train multi-task instead of single-task (ablation)ResNet-18 · MortalityAUROC: 0.839 -> 0.615Hurt
train multi-task instead of single-task (ablation)ResNet-18 · HCC-18AUROC: 0.799 -> 0.590Hurt
train multi-task instead of single-task (ablation)ResNet-34 · Age predictionMAE: 6.486 -> 21.834Hurt
use medical-domain RadImageNet pretraining (ResNet-50) vs ImageNet ResNetsResNet-50 · MortalityAUROC: 0.810 vs 0.839 (ResNet-18)No clear effect
use DINOv2 self-supervised pretraining (ViT-Small) vs ImageNet CNNsViT-Small · MortalityAUROC: 0.811 vs 0.839 (ResNet-18)No clear effect
use larger architecture (Swin Transformer-Base) vs small CNNSwin Transformer-Base · Age predictionMAE: 6.540 vs 6.223 (EfficientNet-B0)No clear effect
stratify evaluation to male patientsEfficientNet-B0 · Age predictionMAE: 6.63 -> 5.76Improved
evaluate on male instead of female patientsResNet-18 · HCC-111 COPDAUROC: 0.740 -> 0.802Improved
evaluate on female instead of male patientsResNet-18 · HCC-18AUROC: 0.773 -> 0.824Improved
predict cancer comorbidity HCC-12 instead of cardio-metabolic targetsbest architectures · HCC-12AUROC: 0.591 vs 0.848 (Calcium Score)Hurt

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