# AI compute and model platforms for oncology

Source: https://onco.cc/technologies/ai-compute-platforms/  
OnCo record `ai-compute-platforms` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

AI compute platforms are the GPUs, model libraries, and cloud services that pathology, radiology, and drug-design AI run on.

## Summary

NVIDIA (Clara for imaging and pathology, BioNeMo for molecular models, MONAI open-source medical imaging framework), cloud providers (AWS HealthOmics, Google Cloud Healthcare and Med-PaLM/MedGemma, Microsoft Azure AI for Health and Prov-GigaPath), and open ecosystems (Hugging Face model hubs, OHIF viewer) provide the substrate for foundation models in oncology. Compute access, data governance, and validation frameworks decide who can build and deploy.

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-08
- Tags: supporting
- Principle: GPU clusters and managed services host training and inference; domain frameworks provide pretrained encoders, DICOM/WSI I/O, and deployment tooling.
- Strengths: Rapidly falling cost of large models; Open frameworks (MONAI)
- Limitations: Data access and privacy; Validation and regulatory clearance lag; Concentration in a few vendors

## Connected records

- technologies: [Agent-based and multicellular simulations](https://onco.cc/technologies/agent-based-tumour-models/), [AI auto-contouring and adaptive planning](https://onco.cc/technologies/auto-contouring-ai/), [AI in radiology](https://onco.cc/technologies/radiology-ai-screening/), [AI-assisted mammography screening](https://onco.cc/technologies/ai-mammography-screening/), [AI-driven drug & target discovery](https://onco.cc/technologies/ai-drug-design/), [Digital pathology & AI](https://onco.cc/technologies/digital-pathology-ai/), [Federated learning and privacy-preserving AI](https://onco.cc/technologies/federated-learning-medical-ai/), [Pathology & radiology foundation models](https://onco.cc/technologies/pathology-foundation-model/), [Tumour-immune dynamics models](https://onco.cc/technologies/immune-tumour-dynamics-models/)
- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/), [Drug Discovery Platforms](https://onco.cc/fronts/drug-discovery/)
- companies: [Google (Health, DeepMind, Verily)](https://onco.cc/companies/google-health/), [Microsoft (Health & Life Sciences)](https://onco.cc/companies/microsoft/), [NVIDIA](https://onco.cc/companies/nvidia/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/)
- terms: [Cancer AI vocabulary (CanSim terms map)](https://onco.cc/terms/cancer-ai-vocabulary/), [Foundation model](https://onco.cc/terms/foundation-model/), [GPU training and mixed precision](https://onco.cc/terms/mixed-precision-gpu/)

---
JSON: https://onco.cc/api/v1/entities/ai-compute-platforms.json