wannature/BoostMIS
Pytorch implementation of BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
This project helps medical professionals, like radiologists or oncologists, classify medical images, specifically MRI scans of spinal cord compression, to optimize diagnosis and treatment referrals. You input a collection of labeled and unlabeled MRI images, and it outputs an AI model trained to accurately classify images into different severity grades, even with limited initial labeled data. This benefits medical specialists needing to quickly and reliably assess conditions.
No commits in the last 6 months.
Use this if you need to train a highly accurate model for classifying medical images, especially when you have a large amount of unlabeled data but limited expert-labeled examples.
Not ideal if your medical imaging task involves object detection, segmentation, or if you already have a fully labeled, extensive dataset for supervised training.
Stars
56
Forks
1
Language
Python
License
—
Category
Last pushed
Apr 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wannature/BoostMIS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dipy/dipy
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for...
Project-MONAI/MONAI
AI Toolkit for Healthcare Imaging
Project-MONAI/MONAILabel
MONAI Label is an intelligent open source image labeling and learning tool.
neuronets/nobrainer
A framework for developing neural network models for 3D image processing.
axondeepseg/axondeepseg
Axon/Myelin segmentation using Deep Learning