All Competitors

Every biological foundation model, evaluated and ranked by the bio.rodeo team

Showing 121141 of 141 filtered models

  • Virchow

    4623311K
    Paige AISeptember 14, 2023digital_pathologyfoundation_modelhistology+3

    Histopathology foundation models: self-supervised vision transformers pretrained on millions of whole-slide images for tile-level feature extraction.

    Pathology
    42Openness
  • RETFound

    660938105
    University College London +1 otherSeptember 13, 2023disease_detectionfoundation_modelimage_classification+7

    Self-supervised foundation model for retinal imaging, pretrained on 1.6 million unlabelled fundus and OCT scans to detect ocular and systemic disease.

    ImagingPathology
    30Openness
  • SAM-Med2D

    1.1K258
    Shanghai AI LaboratoryAugust 30, 2023foundation_modelhistologyradiology+4

    Medical imaging adaptation of the Segment Anything Model, fine-tuned on 4.6M images and 19.7M masks for promptable segmentation across 10 modalities.

    Imaging
    82Openness
  • RadFM

    561263
    Shanghai Jiao Tong University +1 otherAugust 4, 2023disease_diagnosisfoundation_modelgenerative+7

    Radiology foundation model that reads interleaved 2D and 3D scans with text for diagnosis, visual question answering, and report generation.

    ImagingLanguage model
    84Openness
  • Med-Flamingo

    452618
    Stanford University +2 othersJuly 27, 2023few_shotin_context_learningmedical_imaging+6

    Multimodal medical vision-language model for few-shot visual question answering, learning new imaging tasks from in-context examples at inference.

    PathologyLanguage model
    18Openness
  • Med-PaLM M

    552
    Google Research +1 otherJuly 26, 2023generativegenomicshistology+9

    Google's generalist multimodal biomedical AI that encodes clinical text, medical images, and genomics with a single set of weights across 14 tasks.

    ImagingLanguage model
    25Openness
  • Phikon

    17211421.7K
    OwkinJuly 21, 2023biomarker_predictionfoundation_modelhistology+3

    Self-supervised histopathology foundation models for H&E whole-slide images. Phikon-v2 is a ViT-L/16 DINOv2 encoder used for biomarker prediction.

    Pathology
    35Openness
  • MIS-FM

    25050
    University of Electronic Science and Technology of China +3 othersJune 29, 2023cnnctfoundation_model+3

    Self-supervised foundation model for 3D medical image segmentation, pretrained on roughly 110,000 unannotated CT volumes via Volume Fusion.

    Imaging
    73Openness
  • MedLSAM

    52282
    Shanghai AI Laboratory +3 othersJune 26, 2023cnnctfew_shot+6

    3D CT localization foundation model that pairs MedLAM with SAM to segment any anatomical structure at a fixed, dataset-independent annotation cost.

    Imaging
    76Openness
  • LVM-Med

    217100
    University of Stuttgart +6 othersJune 20, 2023classificationcontrastive_learningct+11

    Self-supervised vision foundation model pretrained on 1.3M medical images via second-order graph matching, for segmentation and classification.

    Imaging
    28Openness
  • HeartBEiT

    25118
    Icahn School of Medicine at Mount SinaiJune 6, 2023cardiologydisease_diagnosisecg_classification+4

    Vision transformer for electrocardiograms that reads the printed 12-lead ECG as an image, enabling data-efficient diagnosis from few labeled examples.

    Biosignals
    30Openness
  • LLaVA-Med

    2.2K1.9K12.3K
    Microsoft ResearchJune 1, 2023histologyimage_captioninginstruction_tuning+7

    Biomedical vision-language assistant for question answering on radiology and pathology images, adapted from LLaVA on PubMed Central captions.

    PathologyLanguage model
    28Openness
  • PathAsst

    136104
    Westlake University +3 othersMay 24, 2023cytologyfoundation_modelhistology+7

    Multimodal pathology assistant that answers questions about histology and cytology images, pairing the PathCLIP vision encoder with a Vicuna-13B LLM.

    PathologyLanguage model
    17Openness
  • MedVInT

    236367
    Shanghai Jiao Tong University +1 otherMay 17, 2023generativehistologymedical_image_understanding+6

    Generative medical visual question answering model that pairs a vision encoder with a language model, trained on the 227k-pair PMC-VQA dataset.

    PathologyLanguage model
    83Openness
  • BiomedCLIP

    128665878.5K
    Microsoft ResearchMarch 1, 2023contrastive_learningfoundation_modelimage_analysis+4

    Biomedical vision-language model trained contrastively on 15M PubMed Central figure-caption pairs for zero-shot classification, retrieval, and VQA.

    Imaging
    61Openness
  • PTUnifier

    7853
    Chinese University of Hong Kong, Shenzhen +2 othersFebruary 17, 2023chest_x_rayfoundation_modelimage_text_retrieval+8

    Medical vision-language pretraining unifying fusion-encoder and dual-encoder designs, handling image-only, text-only, and paired inputs in one model.

    PathologyLanguage model
    56Openness
  • RoentGen

    88146
    Stanford UniversityNovember 23, 2022chest_radiographydata_augmentationfoundation_model+5

    Text-conditioned latent diffusion model that generates synthetic chest X-rays from free-form radiology prompts by adapting Stable Diffusion.

    ImagingLanguage model
    20Openness
  • CheXzero

    234527
    Stanford UniversitySeptember 15, 2022chest_radiographycontrastive_learningimage_classification+7

    Self-supervised vision-language model for zero-shot detection of chest X-ray pathologies, trained on image-report pairs without explicit labels.

    ImagingPathology
    70Openness
  • Shenzhen Research Institute of Big Data +2 othersSeptember 15, 2022chest_x_rayfoundation_modelimage_text_retrieval+7

    Medical vision-language pretraining framework that injects structured medical knowledge into radiology image-text learning for VQA and retrieval.

    ImagingLanguage model
    29Openness
  • M3AE

    134192
    Shenzhen Research Institute of Big Data +2 othersSeptember 15, 2022autoencoderimage_text_retrievalmultimodal+5

    Self-supervised medical vision-and-language pretraining via multi-modal masked autoencoders that reconstruct masked image patches and text tokens.

    PathologyLanguage model
    29Openness
  • PubMedCLIP

    1833116.7K
    Hasso Plattner InstituteDecember 27, 2021cnncontrastive_learninghistology+8

    Medical-domain CLIP fine-tuned on radiology image-caption pairs from ROCO, serving as a drop-in visual encoder for medical visual question answering.

    PathologyLanguage model
    75Openness