{"count":5,"items":[{"article":null,"cancer_slugs":["pan-cancer"],"category":"multimodal","confidence":"high","developer":"Microsoft Research","hf":{"downloads":249031,"fetched_at":"2026-09-09T21:33:08Z","gated":false,"last_modified":"2025-01-14","library":"open_clip","license":"mit","likes":424,"pipeline_tag":"zero-shot-image-classification"},"kind":"foundation","license":"MIT","links":{"demo":null,"docs":null,"doi":null,"github":"https://github.com/microsoft/BiomedCLIP_data_pipeline","huggingface":"https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224","paper":"https://ai.nejm.org/doi/full/10.1056/AIoa2400640","pmid":null},"modalities":["multimodal","histopathology","radiology-xray","radiology-ct","literature"],"name":"BiomedCLIP","openness":"open-weights","regulatory_status":"research-only","release_date":"2023-03-02","settings":["basic-research","education"],"slug":"biomedclip","summary":"CLIP-style vision-language model pretrained on PMC-15M \u2014 15 million figure\u2013caption pairs from biomedical papers \u2014 with a PubMedBERT text tower and a ViT-B image tower; supports zero-shot classification and retrieval across pathology, radiology and more.","tasks":["image-text-retrieval","classification","feature-extraction","question-answering"],"url":"/ai-oncology/models/biomedclip","verified_at":"2026-09-05T22:26:00.027245","version":null},{"article":null,"cancer_slugs":["pan-cancer"],"category":"radiology","confidence":"high","developer":"Bo Wang Lab, University of Toronto / University Health Network","hf":{"downloads":3637,"fetched_at":"2026-09-09T21:33:09Z","gated":false,"last_modified":"2023-05-03","library":"transformers","license":"apache-2.0","likes":24,"pipeline_tag":"mask-generation"},"kind":"foundation","license":"apache-2.0","links":{"demo":null,"docs":null,"doi":"10.1038/s41467-024-44824-z","github":"https://github.com/bowang-lab/MedSAM","huggingface":"https://huggingface.co/wanglab/medsam-vit-base","paper":"https://www.nature.com/articles/s41467-024-44824-z","pmid":null},"modalities":["radiology-ct","radiology-mri","ultrasound","endoscopy","histopathology","radiology-xray","multimodal"],"name":"MedSAM","openness":"open-weights","regulatory_status":"research-only","release_date":"2024-01-22","settings":["basic-research","treatment-planning"],"slug":"medsam","summary":"Segment Anything adapted to medical images: a promptable segmentation model fine-tuned on over 1.5 million image\u2013mask pairs across 10 imaging modalities and more than 30 cancer types.","tasks":["segmentation"],"url":"/ai-oncology/models/medsam","verified_at":"2026-09-05T22:26:01.532196","version":null},{"article":null,"cancer_slugs":["pan-cancer"],"category":"radiology","confidence":"high","developer":"German Cancer Research Center (DKFZ), Division of Medical Image Computing","hf":null,"kind":"framework","license":"apache-2.0","links":{"demo":null,"docs":null,"doi":"10.1038/s41592-020-01008-z","github":"https://github.com/MIC-DKFZ/nnUNet","huggingface":null,"paper":"https://www.nature.com/articles/s41592-020-01008-z","pmid":null},"modalities":["radiology-ct","radiology-mri","pet"],"name":"nnU-Net","openness":"open-weights","regulatory_status":"not-applicable","release_date":"2020-12-07","settings":["treatment-planning","basic-research"],"slug":"nnunet","summary":"Self-configuring segmentation framework: given a labelled dataset it chooses preprocessing, network topology and training schedule automatically, and it remains the baseline to beat on most medical segmentation challenges, including tumour tasks.","tasks":["segmentation"],"url":"/ai-oncology/models/nnunet","verified_at":"2026-09-05T22:26:01.557400","version":"v2"},{"article":null,"cancer_slugs":["pan-cancer"],"category":"radiology","confidence":"high","developer":"University Hospital Basel","hf":null,"kind":"tool","license":"apache-2.0","links":{"demo":null,"docs":null,"doi":"10.1148/ryai.230024","github":"https://github.com/wasserth/TotalSegmentator","huggingface":null,"paper":"https://pubs.rsna.org/doi/10.1148/ryai.230024","pmid":null},"modalities":["radiology-ct","radiology-mri"],"name":"TotalSegmentator","openness":"open-weights","regulatory_status":"research-only","release_date":"2023-07-05","settings":["treatment-planning","basic-research"],"slug":"totalsegmentator","summary":"Command-line tool that segments 117 anatomical structures (v2) in any CT scan with nnU-Net models trained on more than 1,200 clinical CTs \u2014 the standard way to get organ masks for radiomics, dose planning and tumour-context features.","tasks":["segmentation"],"url":"/ai-oncology/models/totalsegmentator","verified_at":"2026-09-05T22:26:01.552100","version":"v2"},{"article":null,"cancer_slugs":["lung-bronchus"],"category":"radiology","confidence":"high","developer":"MIT Jameel Clinic / Massachusetts General Hospital","hf":null,"kind":"task-model","license":"MIT","links":{"demo":null,"docs":null,"doi":"10.1200/JCO.22.01345","github":"https://github.com/reginabarzilaygroup/Sybil","huggingface":null,"paper":"https://ascopubs.org/doi/10.1200/JCO.22.01345","pmid":"36634294"},"modalities":["radiology-ct"],"name":"Sybil","openness":"open-weights","regulatory_status":"research-only","release_date":"2023-01-12","settings":["screening"],"slug":"sybil","summary":"Deep-learning model that predicts an individual's risk of lung cancer over the next one to six years from a single low-dose chest CT, without radiologist annotations or clinical variables.","tasks":["risk-prediction","screening"],"url":"/ai-oncology/models/sybil","verified_at":"2026-09-05T22:26:01.509204","version":null}],"standard":"https://cancer3.ai/docs/ai-model-card","vocab":{"confidence":["high","medium","low"],"dataset_access":["open","registration","dua","controlled","commercial"],"dataset_kinds":["dataset","registry","benchmark","biobank","corpus"],"formats":["SVS","TIFF","NDPI","DICOM","NIfTI","PNG","JPEG","CSV","TSV","JSON","Parquet","FASTQ","BAM","VCF","MAF","h5ad","PDB","mmCIF","text","other"],"kinds":["foundation","task-model","tool","framework","product"],"link_roles":["pretraining","training","finetuning","evaluation","benchmark"],"modalities":["histopathology","radiology-ct","radiology-mri","radiology-xray","mammography","pet","ultrasound","dermoscopy","endoscopy","genomics","transcriptomics","single-cell","proteomics","protein-sequence","molecules","clinical-text","literature","ehr","multimodal","immunopeptidomics"],"need_status":["open","in-progress","solved"],"openness":["open-weights","gated-weights","api-only","closed"],"regulatory":["research-only","fda-cleared","fda-de-novo","fda-pma","ce-marked","ce-ivdr","not-applicable"],"settings":["basic-research","screening","diagnosis","prognosis","treatment-planning","treatment-response","drug-discovery","clinical-trials","education","vaccine-design","immunotherapy"],"tasks":["feature-extraction","classification","segmentation","detection","screening","risk-prediction","prognosis","treatment-response","survival-analysis","image-text-retrieval","report-generation","question-answering","information-extraction","clinical-trial-matching","protein-structure","variant-effect","gene-expression","single-cell","drug-discovery","drug-repurposing","peptide-mhc-binding","antigen-presentation","neoantigen-prioritisation"]}}