ConQuer augments global CLIP alignment with independent per-concept contrastive losses on anatomical regions extracted from reports, producing Jolia which outperforms CLIP baselines on classification, report generation, and transfer.
Curia: A multi- modal foundation model for radiology.arXiv preprint arXiv:2509.06830, 2025
4 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
4
Pith papers citing it
2
external citations · external index
fields
cs.CV 4years
2026 4representative citing papers
Benchmark finds segmentation dominates volume and stage tasks while classifier choice dominates survival, histology, and age prediction, recommending Curia with tumor segmentation and CatBoost as a safe default.
FlexiCT provides CT foundation models via agglomerative pretraining on 266227 volumes from 56 datasets that match or exceed task-specific models on five task families while organizing embeddings along tumor-stage gradients.
Self-supervised pretraining on large unlabeled clinical brain MRI data improves generalization to out-of-domain clinical tasks over supervised in-domain training, with task-specific optimal objectives and limited benefits from model scaling.
citing papers explorer
-
Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning
ConQuer augments global CLIP alignment with independent per-concept contrastive losses on anatomical regions extracted from reports, producing Jolia which outperforms CLIP baselines on classification, report generation, and transfer.
-
Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
Benchmark finds segmentation dominates volume and stage tasks while classifier choice dominates survival, histology, and age prediction, recommending Curia with tumor segmentation and CatBoost as a safe default.
-
Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining
FlexiCT provides CT foundation models via agglomerative pretraining on 266227 volumes from 56 datasets that match or exceed task-specific models on five task families while organizing embeddings along tumor-stage gradients.
-
Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge
Self-supervised pretraining on large unlabeled clinical brain MRI data improves generalization to out-of-domain clinical tasks over supervised in-domain training, with task-specific optimal objectives and limited benefits from model scaling.