---
license: apache-2.0
library_name: timm
tags:
  - medical-imaging
  - chest-xray
  - pneumonia
  - dinov2
  - vit-small
base_model: facebook/dinov2-small
datasets:
  - rsna-pneumonia-detection-challenge
metrics:
  - roc-auc
  - pr-auc
  - ece
pipeline_tag: image-classification
---

# DINOv2-Small fine-tuned on RSNA Pneumonia

Binary chest X-ray pneumonia classifier. Backbone: [`vit_small_patch14_dinov2.lvd142m`](facebook/dinov2-small).
Two-phase fine-tune on [RSNA Pneumonia Detection Challenge](https://www.kaggle.com/competitions/rsna-pneumonia-detection-challenge/data)
(26685 patients total, ~22% prevalence).

This is the artifact published alongside the
[Clinical AI 2026 curriculum](https://github.com/timothy22000/clinical-ai-curriculum)
and the [GradCAM demo Space](https://huggingface.co/spaces/t22000t/clinical-ai-gradcam-demo).

## Headline metrics (validation set)

| Metric | Value |
|---|---:|
| ROC-AUC | 0.869 |
| PR-AUC | 0.669 |
| Accuracy at Youden op-point | 0.760 |
| Op-point threshold | 0.145 |
| ECE (raw) | 0.0344 |
| ECE (after temperature scaling) | 0.0297 |
| Positive prevalence | 0.225 |
| Validation set size | 5337 patients |

The Youden-J operating-point threshold is **0.145**,
not the default 0.5. The validation accuracy above is computed at this threshold.

## How to load

```python
import timm, torch
from safetensors.torch import load_file

model = timm.create_model(
    "vit_small_patch14_dinov2.lvd142m",
    pretrained=False,
    in_chans=1,
    num_classes=2,
    img_size=224,
)
model.load_state_dict(load_file("model.safetensors"))
model.eval()
```

## How to apply temperature scaling

```python
import json, torch.nn.functional as F

T = json.load(open("temperature_scaling.json"))["temperature"]  # 1.0571
logits = model(x)  # (B, 2)
calibrated_probs = F.softmax(logits / T, dim=-1)
positive_prob = calibrated_probs[:, 1]
prediction = (positive_prob > 0.145).long()
```

## Reproducibility

`val_indices.json` lists the **5337** patient IDs used as the held-out
validation set. Its sha256 is recorded in `evaluation_metrics.json` and
`training_config.json`. All metrics above are computed on exactly these
patients. We publish this list rather than relying on `random_state=42` because
sklearn's stratified split is not invariant across releases.

## DICOM preprocessing

The training pipeline applies the DICOM `WindowCenter` / `WindowWidth` if
present, inverts `MONOCHROME1` images so air is black, resamples to
224x224 with bilinear interpolation, and feeds a single grayscale
channel. See `training_config.json` for the full recipe.

## What this is and is not

This model is a **teaching artifact**. The recipe (linear probe -> partial
unfreeze of the last 2 blocks) is the canonical foundation-model adaptation
pattern, and the model card publishes the artifacts a clinical deployment
would need to audit it. State-of-the-art RSNA Pneumonia models reach
ROC-AUC ~0.93 with ensembles and aggressive augmentation; this single-model
recipe is several points below that ceiling by design.

This model is not clinically deployable. The RSNA dataset uses surrogate
labels ("Lung Opacity") with known label noise, and no real deployment ships
without prospective evaluation against an institutional standard.

## Failure analysis

`natural_failure_gallery.png` shows the highest-confidence false positives
and false negatives on the held-out validation set, with DINOv2 attention
rollout overlays. `augmentation_failure_gallery.png` shows
augmentation-induced flips: examples the model originally classified
correctly but flipped under one of 8 clinically-named perturbations. The
`lateral_flip` augmentation is the laterality-shortcut probe.

## Citation

If you use this model, please cite the underlying foundation model:

```
@misc{oquab2024dinov2,
  title  = {DINOv2: Learning Robust Visual Features without Supervision},
  author = {Oquab, Maxime and Darcet, Timothee and Moutakanni, Theo and
            Vo, Huy and Szafraniec, Marc and Khalidov, Vasil and
            Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and
            El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and
            Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and
            Rabbat, Mike and Assran, Mido and Ballas, Nicolas and
            Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and
            Mairal, Julien and Labatut, Patrick and Joulin, Armand and
            Bojanowski, Piotr},
  year   = {2024},
  eprint = {2304.07193},
  archivePrefix = {arXiv},
}
```

and the RSNA Pneumonia Detection Challenge.