Deep-learning characterization and quantification of COVID-19 pneumonia lesions from chest CT images

A relevant percentage of COVID-19 patients present bilateral pneumonia. Disease progression and healing is characterized by the presence of different parenchymal lesion patterns. Artificial intelligence algorithms have been developed to identify and assess the related lesions and properly segment affected lungs, however very little attention has been paid to automatic lesion subtyping. In this work we present artificial intelligence algorithms based on CNN to automatically identify and quantify COVID-19 pneumonia patterns. A Dense-efficient CNN architecture is presented to automatically segment the different lesion subtypes. The proposed technique has been independently tested in a multicentric cohort of 100 patients, showing Dice coefficients of 0.988 +/- 0.01 for ground glass opacities, 0.948 +/- 0.05 for consolidations, and 0.999 +/- 0.0003 for healthy tissue with respect to radiologist's reference segmentations, and high correlations with respect to radiologist severity visual scores.

Automated summary

This work presents artificial intelligence algorithms based on CNN to automatically identify and quantify COVID-19 pneumonia patterns, as well as to automatically segment different lesion subtypes.