This is part of my internship at Endimension Technology, IIT Bombay.
PyTorch implementation of CheXNet: Radiologist level pneumonia detection using deep learning based on this implementation.
You can run the complete notebook on Kaggle -> CheXNet-PyTorch
| Batch size | Learning Rate | Epochs | Time |
|---|---|---|---|
| 64 | 0.01 | 20 | 2 hrs |
| Pathology | AUROC |
|---|---|
| Atelectasis | 0.735 |
| Cardiomegaly | 0.882 |
| Effusion | 0.82 |
| Infiltration | 0.673 |
| Mass | 0.788 |
| Nodule | 0.728 |
| Pneumonia | 0.647 |
| Pneumothorax | 0.799 |
| Consolidation | 0.689 |
| Edema | 0.832 |
| Emphysema | 0.858 |
| Fibrosis | 0.77 |
| Pleural_Thickening | 0.719 |
| Hernia | 0.846 |
