Enzo Tartaglione¹, Carlo Alberto Barbano¹, Claudio Berzovini², Marco Calandri³, Marco Grangetto¹ | [pdf]

1_{University of Turin, Computer Science dept.}
2_{Azienda Ospedaliera Città della Salute e della Scienza, Turin, Italy}
3_{University of Turin, Oncology dept., AOU San Luigi Gonzaga, Orbassano, Italy}

The possibility to use widespread and simple chest X-ray (CXR) imaging for early screening of COVID-19 patients is attracting much interest from both the clinical and the AI community. In this study we provide insights and also raise warnings on what is reasonable to expect by applying deep learning to COVID classification of CXR images. We provide a methodological guide and critical reading of an extensive set of statistical results that can be obtained using currently available datasets. In particular, we take the challenge posed by current small size COVID data and show how significant can be the bias introduced by transfer-learning using larger public non-COVID CXR datasets. We also contribute by providing results on a medium size COVID CXR dataset, just collected by one of the major emergency hospitals in Northern Italy during the peak of the COVID pandemic. These novel data allow us to contribute to validate the generalization capacity of preliminary results circulating in the scientific community. Our conclusions shed some light into the possibility to effectively discriminate COVID using CXR.

For citing our work, please use the following bibtex entry:

@article{tartaglione2020unveiling,
  title={Unveiling covid-19 from chest x-ray with deep learning: a hurdles race with small data},
  author={Tartaglione, Enzo and Barbano, Carlo Alberto and Berzovini, Claudio and Calandri, Marco and Grangetto, Marco},
  journal={International Journal of Environmental Research and Public Health},
  volume={17},
  number={18},
  pages={6933},
  year={2020},
  publisher={Multidisciplinary Digital Publishing Institute}
}