AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology

Saarthak Kapse, Pushpak Pati, Srikar Yellapragada, Srijan Das, Rajarsi R. Gupta, Joel Saltz, Dimitris Samaras, Prateek Prasanna

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 7 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
use self-interpretable linear concept aggregator instead of ABMIL in concept branch (ablation)GECKO ensemble · LUAD vs LUSC (k=10)AUC: 92.3 -> 95.3Improved
use self-interpretable linear concept aggregator instead of ABMIL in concept branch (ablation)GECKO ensemble · EBV+MSI vs Others (k=10)AUC: 75.1 -> 79.8Improved
use self-interpretable linear concept aggregator instead of ABMIL in concept branch (ablation)GECKO concept · LUAD vs LUSC (k=10)AUC: 88.2 -> 93.5Improved
add false negative elimination with keep ratio 0.7 (ablation)GECKO-Zero · five TCGA tasksAUCImproved
add concept prior alignment with WSI only vs Intra pretrainingGECKO ensemble · TCGA-STAD EBV+MSI vs Others (full supervision)AUC: 83.5 -> 86.4Improved
add gene modality to GECKO pretraining (ablation)GECKO ensemble · TCGA-STAD EBV+MSI vs Others (full supervision)AUC: 86.4 -> 87.1Improved
add gene modality to GECKO pretraining (ablation)GECKO ensemble · TCGA-BRCA HER2 (full supervision)AUC: 77.2 -> 78.4Improved
add gene modality to GECKO pretraining (ablation)GECKO ensemble · TCGA LUAD vs LUSC (full supervision)AUC: 97.6 -> 97.9No clear effect
ensemble deep and concept embeddings instead of deep only (ablation)GECKO (WSI only) · TCGA-STAD MSI vs Others (full supervision)AUC: 83.8 -> 86.5Improved
concept-based zero-shot with pretrained concept embeddings instead of MI-ZeroGECKO-Zero · TCGA-STAD MSI vs OthersAUC: 42.3 -> 77.1Improved
GECKO-Zero vs MI-Zero on lung subtypingGECKO-Zero · TCGA LUAD vs LUSCAUC: 96.6 -> 95.0No clear effect
GECKO ensemble vs TITAN in multimodal settingGECKO ensemble · TCGA-STAD EBV+MSI vs Others (k=10)AUC: 78.7 -> 84.4Improved

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