bupt-ai-cz/HSA-NRL
Hard Sample Aware Noise Robust Learning forHistopathology Image Classification
This project helps pathologists and medical researchers improve the accuracy of classifying histopathology images, specifically for colorectal cancer. It takes microscope images of tissue samples as input and outputs a more reliably classified diagnosis (e.g., normal, serrated, adenocarcinoma, adenoma), even when the initial image labels might be noisy or incorrect. This is designed for professionals in medical imaging, diagnostics, and pathology research.
No commits in the last 6 months.
Use this if you need to classify histopathology images with high accuracy, especially when dealing with large datasets where manual labeling errors or 'noisy' labels are a concern.
Not ideal if your image classification task is outside of histopathology or if you cannot use the project for non-commercial purposes.
Stars
37
Forks
10
Language
Python
License
—
Category
Last pushed
Oct 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bupt-ai-cz/HSA-NRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nilearn/nilearn
Machine learning for NeuroImaging in Python
aramis-lab/clinica
Software platform for clinical neuroimaging studies
TissueImageAnalytics/tiatoolbox
Computational Pathology Toolbox developed by TIA Centre, University of Warwick.
nipreps/mriqc
Automated Quality Control and visual reports for Quality Assessment of structural (T1w, T2w) and...
nadeemlab/DeepLIIF
Deep Learning Inferred Multiplex ImmunoFluorescence for IHC Image Quantification...