---
tags:
- chest-xray
- radiology
- contrastive-learning
- mimic-cxr
- vision-encoder
license: apache-2.0
---

# LAPVQA — Pretrain (Contrastive)

Part of the [LAPVQA collection](https://huggingface.co/collections/dmusingu/lapvqa).

## Description

A **ViT-L/14** vision encoder trained from scratch on [MIMIC-CXR](https://physionet.org/content/mimic-cxr) chest X-ray / report pairs
using **InfoNCE contrastive learning** (image encoder vs. 6-layer bidirectional text encoder).
The encoder is intended to be used as a frozen feature extractor for downstream CXR tasks.

## Architecture

| Component | Detail |
|---|---|
| Vision backbone | ViT-L/14, 24-layer, 1024-dim, 16-head, patch 14, 384 px |
| Text encoder | 6-layer, 512-dim bidirectional transformer, GPT-2 vocab (50 257) |
| Projection | Linear → 512-dim shared embedding space |
| Loss | InfoNCE (symmetric softmax cross-entropy) |
| Training data | MIMIC-CXR (physionet.org/content/mimic-cxr) |
| Epochs | 50 |

## Downstream Evaluation (frozen encoder + linear probe)

| Dataset | Mean AUC |
|---|---|
| NIH CXR-14 (14-class) | 0.653 |
| CheXpert-5 (5-class) | 0.759 |

## Files

| File | Description |
|---|---|
| `encoder_final.pt` | Vision encoder weights at the end of training |
| `model_best.pt` | Full model (encoder + text encoder) at best val loss |

## Usage

```python
import torch
from lapvqa.pretrain.model import ContrastiveModel

ckpt = torch.load("encoder_final.pt", map_location="cpu")
model = ContrastiveModel()
model.vision_encoder.load_state_dict(ckpt)
model.eval()
```

## Citation

If you use these weights please cite MIMIC-CXR:

```bibtex
@article{johnson2019mimic,
  title   = {MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports},
  author  = {Johnson, Alistair EW and others},
  journal = {Scientific data},
  volume  = {6}, pages = {317}, year = {2019}
}
```