KibromBerihu/ai4elife

This data-centric AI repository implements a robust deep learning method (LFBNet) for fully automated tumor segmentation in whole-body [18]F-FDG PET/CT images.

46
/ 100
Emerging

This project offers a fully automated way to identify and measure tumor lesions in whole-body 18F-FDG PET/CT images, specifically for Diffuse Large B-cell lymphoma (DLBCL) patients. It takes 3D PET scans and automatically segments tumor regions, then calculates key clinical endpoints like surrogate Total Metabolic Active Tumor Volume (sTMTV) and surrogate maximum tumor dissemination (sDmax). This tool is designed for oncologists, radiologists, and clinical researchers who need to quickly and consistently evaluate tumor burden and spread.

Use this if you need an automated, consistent, and fast method to quantify tumor burden and dissemination from PET images in DLBCL patients, without relying on manual delineation.

Not ideal if your imaging data is not 18F-FDG PET/CT or if you need to segment tumors for cancer types other than DLBCL.

oncology radiology medical-imaging tumor-segmentation biomarker-quantification
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

40

Forks

10

Language

Python

License

MIT

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KibromBerihu/ai4elife"

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