---
library_name: pytorch
tags:
- medical-imaging
- chest-x-ray
- multi-label-classification
- semi-supervised-learning
- chexpert
- resnet50
datasets:
- stanfordaimi/chexpert
metrics:
- auroc
license: mit
---

# loihuynh/semisub-cxr-uncertainty_filter-0.2

Semi-supervised multi-label chest X-ray classifier trained on the CheXpert dataset.

## Model Description

- **Architecture**: ResNet-50 backbone + Dropout + Linear head (6 classes)
- **Backbone**: `resnet50_imagenet` (ImageNet pretrained)
- **Training setting**: `uncertainty_filter`
- **Labeled data ratio**: 0.2 (20% of training set)
- **Seed**: 42
- **Best epoch**: 10

## Labels

This model predicts the following 6 chest X-ray findings:

`Cardiomegaly`, `Pleural Effusion`, `Pneumothorax`, `Consolidation`, `Atelectasis`, `Edema`

## Performance

**Macro AUROC**: 0.8519

| Class | AUROC |
|---|---|
| Cardiomegaly | 0.8127 |
| Pleural Effusion | 0.9301 |
| Pneumothorax | 0.8648 |
| Consolidation | 0.8715 |
| Atelectasis | 0.7181 |
| Edema | 0.9144 |


## Usage

```python
from src.utils.hub import load_from_hub

model = load_from_hub("loihuynh/semisub-cxr-uncertainty_filter-0.2")
model.eval()

# Run inference on a preprocessed image tensor (1, 3, 224, 224)
import torch
with torch.no_grad():
    logits = model(image_tensor)
    probabilities = torch.sigmoid(logits)
```

## Training Details

- **Dataset**: [CheXpert](https://stanfordmlgroup.github.io/competitions/chexpert/)
- **Method**: Pseudo-labeling with MC Dropout uncertainty filtering
- **Loss**: Binary Cross-Entropy (with masking for pseudo-labels)
- **Image size**: 224x224

## Citation

If you use this model, please cite the CheXpert dataset:

```bibtex
@inproceedings{irvin2019chexpert,
  title={CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison},
  author={Irvin, Jeremy and others},
  booktitle={AAAI},
  year={2019}
}
```