Differentiating COVID-19 Cases from Others by an Anatomy Similarity-Inspired Sensitive Merit from CT Images

Computed tomography (CT) of COVID-19 manifests a relatively global effect through the whole lungs, like peripheral ground glass, consolidation, reticular pattern, nodules etc. This characteristic effect renders the difficulties in differentiating COVID-19 from the normal body or other lung diseases by CT. This work presents a novel method to relieve the difficulties by reducing the global effect through the 3D whole lung volume into 2D-like domain. The hypothesis is that the lung tissue shares the similar anatomic structure within a small lung sub-volume for normal subjects. Therefore, the anatomic land-markers along the z-axis, denoted as Lung Marks are used to eliminate axial variable. Our experiments indicated that 30 Lung Marks are sufficient to eliminate the axial variable. The method computes texture measures from each 2D-like volumetric data and maps the measures on to the corresponding Lung Mark, resulting in a profile along the z-axis. The difference of the profiles between two different abnormalities is the proposed sensitive merit to differentiate COVID-19 cases from others in CT images. 48 COVID-19 cases and 48 normal screening cases were used to test the effectiveness of the proposed sensitive merit. Intensity and gradient based texture descriptors were computed from each axial cross image at the corresponding Lung Mark along the z-axis. Euclidean, Jaccard and Dice distances are calculated to generate the profiles of the proposed sensitive merit. Consistent results are observed across texture descriptor types and distance types in the texture measure between the normal and COVID-19 subjects. Uneven Profiles demonstrate the variation along the z-axis. With Lung Mark, the variation of texture descriptor has been reduced prominently. The Gradient based descriptor is more sensitive. Individual Haralick features analysis shows the 2^nd and 10^th dimensions are most distinguishable.