Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays

I am pleased to announce that our newest research article on COVID-19, Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays, has been published.

We developed an Interpretable Deep Learning model for COVID-19 screening. Its performance surpasses the state-of-the-art at predicting COVID-19 against common pneumonia cases, while at the same time it provides meaningful and interpretable insight for the clinicians (Figure 1).

If you find it interesting, please cite it:

Tsiknakis, N., Trivizakis, E., Vassalou, E. E., Papadakis, G. Z., Spandidos, D. A., Tsatsakis, A., Sánchez‑García, J., López‑González, R., Papanikolaou, N., Karantanas, A. H., Marias, K.”Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays”. Experimental and Therapeutic Medicine. https://doi.org/10.3892/etm.2020.8797

Download PDF

Attention Map COVID-19 CNN
Figure 1: Attention map of patient 23 - Binary classification - True positive COVID-19 with a certainty of 100% - Evaluated as grade 2 and 3 (left and right lungs, respectively) by the experts.