i6092467/semi-supervised-multiview-cbm
Concept bottleneck models for multiview data with incomplete concept sets
This project helps medical professionals, especially radiologists and pediatricians, interpret machine learning predictions for conditions like pediatric appendicitis. It takes medical images (like ultrasounds) and related patient data as input to predict a diagnosis, while also showing the underlying medical concepts (e.g., specific anatomical features) that influenced the decision. This makes the diagnostic process more transparent and trustworthy.
No commits in the last 6 months.
Use this if you need to build or evaluate machine learning models for medical diagnoses where understanding the 'why' behind the prediction, in terms of clinical concepts, is as crucial as the prediction itself.
Not ideal if your primary goal is only black-box prediction accuracy without needing human-interpretable intermediate concepts, or if you don't have well-defined clinical concepts to guide the model.
Stars
16
Forks
6
Language
Python
License
—
Last pushed
Nov 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/i6092467/semi-supervised-multiview-cbm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...