All Competitors
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 1–17 of 17 filtered models
Merlin
41912712.5KA 3D vision-language foundation model for abdominal CT that pretrains on paired scans, radiology reports, and structured EHR codes for zero-shot interpretation.
ImagingLanguage model54OpennessNeuroVFM
204—University of Michigan +1 otherNovember 23, 2025ctfoundation_modeljoint_embedding_predictive_architecture+8A generalist neuroimaging vision foundation model pretrained on 5.24M clinical MRI and CT volumes for radiologic diagnosis and report generation.
Imaging57OpennessM3FM
1936—Multimodal, multidomain, multilingual medical foundation model that performs zero-shot clinical diagnosis and report generation from chest X-ray and CT images across English and Chinese.
ImagingLanguage model60OpennessM3D
442159873A multimodal large language model for 3D medical imaging, handling retrieval, report generation, VQA, positioning, and segmentation on CT volumes.
ImagingLanguage model77OpennessuniGradICON
22566—A universal foundation model for medical image registration that generalizes across anatomies and modalities without per-pair optimization.
Imaging65OpennessVoCo
228109—Hong Kong University of Science and TechnologyFebruary 27, 2024contrastive_learningctfoundation_model+6A volume contrastive self-supervised framework that pretrains 3D medical image encoders by predicting the anatomical position of sub-volumes within CT scans.
Imaging69OpennessT3D
—13—Text-informed self-supervised vision-language pretraining for 3D CT volumes, enabling zero-shot classification, retrieval, report generation, and segmentation.
ImagingLanguage model12OpennessSegVol
383115278A promptable 3D foundation model for volumetric CT segmentation of 200+ anatomical categories using point, box, and text prompts.
Imaging100OpennessMIS-FM
24749—University of Electronic Science and Technology of China +3 othersJune 29, 2023cnnctfoundation_model+3A self-supervised foundation model for 3D medical image segmentation, pretrained on ~110k unannotated CT volumes via Volume Fusion.
Imaging73OpennessMedLSAM
52275—A 3D CT localization foundation model (MedLAM) paired with SAM to segment any anatomical structure with a fixed, dataset-independent annotation cost.
Imaging76OpennessLVM-Med
21796—Self-supervised vision foundation model pretrained on ~1.3M medical images via second-order graph matching, transferable across 15 medical imaging tasks.
Imaging28OpennessSTU-Net
370152—Scalable and transferable U-Net family (14M–1.4B parameters) for 3D medical image segmentation, supervised-pretrained on TotalSegmentator.
Imaging82OpennessSelf-supervised pre-training method for 3D medical images that embeds topological invariance into inter-image similarity to learn transferable representations.
Imaging17OpennessPCRLv2
10082—Self-supervised pre-training framework for medical image analysis that unifies pixel restoration with contrastive feature comparison across 2D and 3D modalities.
Imaging71OpennessModels Genesis
782398—Self-supervised 3D pretrained models that learn anatomical representations from unlabeled medical scans for transfer learning to segmentation and classification tasks.
Imaging20OpennessMed3D
2.2K653—Pretrained 3D-ResNet backbones trained on aggregated multi-domain medical segmentation data, released as transfer-learning weights for volumetric medical image analysis.
Imaging75Openness