YalaLab/pillar-pretrain
This repository contains the pretraining code for the Pillar-0 model.
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.
Stars
28
Forks
3
Language
Python
License
—
Category
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.
Higher-rated alternatives
limix-ldm-ai/LimiX
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence...
tatsu-lab/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
google-research/plur
PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets...
YalaLab/pillar-finetune
Finetuning framework for Pillar medical imaging models.
thuml/LogME
Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML...