xraydar-cv

X-Raydar CV — Chest X-Ray Image Classifier

Pre-trained model weights for the computer vision component of X-Raydar, from "Development and validation of open-source deep neural networks for comprehensive chest x-ray reading" (Cid, Macpherson et al., The Lancet Digital Health, 2024).

Trained on over 2.5 million chest X-ray studies from six NHS hospitals across the UK.

Website: x-raydar.info Code: github.com/gmontana/xraydar-cv NLP model: dnamodel/xraydar-nlp

Model Description

XNet38MS is a multi-scale Inception v3 ensemble that takes a chest X-ray image and predicts probabilities for 37 radiological findings. Three models trained at different resolutions (299, 512, 1024 pixels) are averaged at inference time.

Architecture

• Backbone: Modified Inception v3 (single-channel input) with 38-class output
• Multi-scale: Three models at 299px, 512px, and 1024px, ensembled by averaging sigmoid probabilities
• Input: Grayscale chest X-ray image (any resolution, resized and padded internally)

Files

Usage

Download weights

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="dnamodel/xraydar-cv",
    local_dir="./xraydar-cv-weights"
)

Place weights for the code repository

from huggingface_hub import hf_hub_download
import shutil, os

for size in [299, 512, 1024]:
    dest = f"src/model_20210820_XNet38MS/model_weights/direct_multi93_is{size}_Rv10_pre00_imagenet"
    os.makedirs(dest, exist_ok=True)
    for f in ["model_best.pth.tar", "model_TranslatorCVLogitsToUrgency_fcs.pth.tar"]:
        path = hf_hub_download("dnamodel/xraydar-cv", f"cv/is{size}/{f}")
        shutil.copy(path, os.path.join(dest, f))

See the code repository for full inference instructions.

Radiological Findings (37 classes + 1 meta-class)

Citation

@article{cid2024development,
  title={Development and validation of open-source deep neural networks for comprehensive chest x-ray reading: a retrospective, multicentre study},
  author={Cid, Yan Digilov and Macpherson, Matt and others},
  journal={The Lancet Digital Health},
  volume={6},
  number={1},
  pages={e44--e57},
  year={2024},
  publisher={Elsevier},
  doi={10.1016/S2589-7500(23)00218-2}
}

License

For academic research and non-commercial evaluation only. See x-raydar.info for terms and conditions.

Contact

• Questions or collaborations: Giovanni Montana — [email protected]
• Commercial licensing: Warwick Ventures — [email protected]