FengheTan9/LLM4Seg

[MICCAI 2025] Official code for "Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster"

36
/ 100
Emerging

This project helps medical professionals, researchers, and developers in medical imaging improve the accuracy and generalizability of their image segmentation models. It takes various medical image scans (ultrasound, CT, dermoscopy, polypscopy) as input and uses a pre-trained Large Language Model (LLM) to produce more precise segmentations of anatomical structures or anomalies. The primary users are researchers and practitioners working with medical image analysis who want to enhance their segmentation results.

No commits in the last 6 months.

Use this if you need to perform highly accurate and robust segmentation on diverse medical images, especially when your existing models struggle with generalization across different imaging modalities or datasets.

Not ideal if you are looking for a plug-and-play solution without any programming or deep learning knowledge, as this project requires familiarity with Python and PyTorch.

medical-imaging image-segmentation biomedical-engineering diagnostic-imaging radiology-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

51

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Oct 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/FengheTan9/LLM4Seg"

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