AI in Oncology · AI Models
A researcher-grade catalog of AI models, datasets and open data needs in oncology — every card structured, sourced and dated.
Filter by task, data type, cancer, availability and regulatory status. Each card follows one model-card standard and links to Hugging Face, code, papers and the datasets it was trained or tested on. { } export JSON
BiomedCLIP
CLIP-style vision-language model pretrained on PMC-15M — 15 million figure–caption pairs from biomedical papers — with a PubMedBERT text tower and a ViT-B image tower; supports zero-shot classification and retrieval across pathology, radiology and more.
MedSAM
Segment Anything adapted to medical images: a promptable segmentation model fine-tuned on over 1.5 million image–mask pairs across 10 imaging modalities and more than 30 cancer types.
nnU-Net v2
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.
TotalSegmentator v2
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 — the standard way to get organ masks for radiomics, dose planning and tumour-context features.
Sybil
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.
Cards follow the cancer3.ai model-card standard: AI_MODEL_CARD_STANDARD.md. Corrections and new entries: contact the editorial team; every fact needs a public source.
This page is educational — it is not medical advice and does not replace consultation with an oncologist. Diagnostic and treatment decisions are made solely by specialist physicians.