Skip to content

Latest commit

 

History

7 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

weak-labels-cxr

Exploring how to handle uncertain labels in medical imaging — experiments on CheXpert for robust chest X-ray classification

Data Setup

This project uses the CheXpert-v1.0-small dataset.

Download Instructions

  1. Go to Kaggle CheXpert Dataset
  2. Download archive.zip (~11GB)
  3. Place it in this data/ folder
  4. Unzip it:
   cd data/
   unzip archive.zip
  1. Run preprocessing:
   python scripts/prepare_data.py

Expected Structure After Setup

data/
├── archive/
│   ├── train/
│   ├── valid/
│   ├── train.csv
│   └── valid.csv
└── processed/
    ├── train_labels.csv
    └── valid_labels.csv
README.md

About

Exploring how to handle uncertain labels in medical imaging — experiments on CheXpert for robust chest X-ray classification

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages