YalaLab/pillar-pretrain

This repository contains the pretraining code for the Pillar-0 model.

35
/ 100
Emerging

This is a specialized toolkit for researchers and developers working with large-scale medical imaging data, specifically CT scans of the abdomen, and associated radiology reports. It processes raw imaging data and text reports into a structured format, then trains advanced AI models. The output is a highly capable AI model that can understand and analyze complex medical images and text, useful for radiology research and clinical support.

Use this if you are a researcher or AI developer working on developing or evaluating foundation models for medical imaging, particularly in radiology, and need to pretrain a model using large datasets of CT scans and their corresponding text reports.

Not ideal if you are looking for a plug-and-play solution for clinical use or a tool for general image analysis outside of radiology, or if you don't have access to large medical imaging datasets.

medical-imaging radiology-AI CT-scans medical-research AI-model-training
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 9 / 25

How are scores calculated?

Stars

28

Forks

3

Language

Python

License

Last pushed

Jan 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YalaLab/pillar-pretrain"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.