McGregorWwww/UCTransNet

Implementation of our AAAI'22 work: 'UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer'.

36
/ 100
Emerging

This project helps medical professionals and researchers automatically identify and outline specific structures within medical images, such as cancerous cells in histology slides or organs in CT/MRI scans. You input raw medical images, and it outputs segmented images highlighting the areas of interest, along with performance metrics like Dice and IoU scores. This is primarily for medical imaging specialists, histopathologists, and radiologists who work with large volumes of image data.

432 stars. No commits in the last 6 months.

Use this if you need a reliable method for segmenting structures in medical images, especially if you're working with datasets like GlaS, MoNuSeg, or Synapse, and want to evaluate its performance.

Not ideal if you are looking for a plug-and-play tool for general image segmentation outside of medical contexts, or if you need the absolute latest, most computationally efficient model (refer to UDTransNet for an improved version).

medical-image-segmentation histopathology radiology biomedical-imaging disease-detection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

432

Forks

54

Language

Python

License

Last pushed

May 19, 2024

Commits (30d)

0

Get this data via API

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

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