Atlas-based lung segmentation combined with automatic densitometry characterization in COVID-19 patients: Training, validation and first application in a longitudinal study.

• Segmentation algorithms do not work well on unhealthy lungs as COVID-19 ones. • An Atlas for segmentation of COVID-19 lungs' patients was developed and validated. • Lung histograms parameters could impact the clinical management of COVID-19 patients. • Lung densitometry characterization method integrated to segmentation was implemented. To develop and validate an automated segmentation tool for COVID-19 lung CTs. To combine it with densitometry information in identifying Aerated, Intermediate and Consolidated Volumes in admission (CT1) and follow up CT (CT3). An Atlas was trained on manually segmented CT1 of 250 patients and validated on 10 CT1 of the training group, 10 new CT1 and 10 CT3, by comparing DICE index between automatic (AUTO), automatic-corrected (AUTOMAN) and manual (MAN) contours. A previously developed automatic method was applied on HU lung density histograms to quantify Aerated, Intermediate and Consolidated Volumes. Volumes of subregions in validation CT1 and CT3 were quantified for each method. In validation CT1/CT3, manual correction of automatic contours was not necessary in 40% of cases. Mean DICE values for both lungs were 0.94 for AUTO Vs MAN and 0.96 for AUTOMAN Vs MAN. Differences between Aerated and Intermediate Volumes quantified with AUTO Vs MAN contours were always < 6%. Consolidated Volumes showed larger differences (mean: −95 ± 72 cc). If considering AUTOMAN Vs MAN volumes, differences got further smaller for Aerated and Intermediate, and were drastically reduced for consolidated Volumes (mean: −36 ± 25 cc). The average time for manual correction of automatic lungs contours on CT1 was 5 ± 2 min. An Atlas for automatic segmentation of lungs in COVID-19 patients was developed and validated. Combined with a previously developed method for lung densitometry characterization, it provides a fast, operator-independent way to extract relevant quantitative parameters with minimal manual intervention. [ABSTRACT FROM AUTHOR]