SakurajimaMaiii/ProtoKD

[ICASSP 2023] Prototype Knowledge Distillation for Medical Segmentation with Missing Modality

48
/ 100
Emerging

This project helps medical professionals and researchers accurately segment brain tumors in MRI scans, even when some imaging modalities (like T1, T2, T1ce, or FLAIR sequences) are unavailable. It takes pre-processed MRI images and a defined imaging modality as input and outputs a precise segmentation of the tumor, which can be visualized in standard medical image viewers. This is designed for medical imaging analysts and clinicians who need to segment tumors from potentially incomplete MRI datasets.

Use this if you need to perform brain tumor segmentation on MRI data where one or more imaging sequences might be missing, and you require highly accurate results.

Not ideal if you are working with non-medical image segmentation or if you consistently have complete multi-modal MRI data for all patients.

medical-imaging brain-tumor-segmentation radiology clinical-diagnosis missing-data-analysis
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

58

Forks

8

Language

Python

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

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

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