Journal Article

AI-driven quantification of ground glass opacities in lungs of COVID-19 patients using 3D computed tomography imaging

Kumar, T. K. Satish, Amin, Sagar B., Kalia, Rajiv K., Saha, Monjoy, Sharma, Ashish

2022

Overview

Ground-glass opacity (GGO)-a hazy, gray appearing density on computed tomography (CT) of lungs-is one of the hallmark features of SARS-CoV-2 in COVID-19 patients. This AI-driven study is focused on segmentation, morphology, and distribution patterns of GGOs. We use an AI-driven unsupervised machine learning approach called PointNet++ to detect and quantify GGOs in CT scans of COVID-19 patients and to assess the severity of the disease. We have conducted our study on the \"MosMedData\", which contains CT lung scans of 1110 patients with or without COVID-19 infections. We quantify the morphologies of GGOs using Minkowski tensors and compute the abnormality score of individual regions of segmented lung and GGOs. PointNet++ detects GGOs with the highest evaluation accuracy (98%), average class accuracy (95%), and intersection over union (92%) using only a fraction of 3D data. On average, the shapes of GGOs in the COVID-19 datasets deviate from sphericity by 15% and anisotropies in GGOs are dominated by dipole and hexapole components. These anisotropies may help to quantitatively delineate GGOs of COVID-19 from other lung diseases. The PointNet++ and the Minkowski tensor based morphological approach together with abnormality analysis will provide radiologists and clinicians with a valuable set of tools when interpreting CT lung scans of COVID-19 patients. Implementation would be particularly useful in countries severely devastated by COVID-19 such as India, where the number of cases has outstripped available resources creating delays or even breakdowns in patient care. This AI-driven approach synthesizes both the unique GGO distribution pattern and severity of the disease to allow for more efficient diagnosis, triaging and conservation of limited resources.

• Publisher: Public Library of Science,Public Library of Science (PLoS)
• Subject: Anisotropy / Artificial Intelligence / Asymptomatic / Biology and Life Sciences / Computed tomography / Computer science / Conservation / Coronaviruses / COVID-19 / COVID-19 - diagnostic imaging / COVID-19 - pathology / CT imaging / Deep learning / Dipoles / Disease transmission / Female / Funding / Health aspects / Humans / Image segmentation / India / Informatics / Lung - diagnostic imaging / Lung - pathology / Lung diseases / Lungs / Machine learning / Male / Mathematical analysis / Medical imaging / Medicine and Health Sciences / Methods / Morphology / Opacity / Pandemics / Patient Acuity / Patients / Physical Sciences / Radiographic Image Interpretation, Computer-Assisted - methods / Research and Analysis Methods / Retrospective Studies / Segmentation / Severe acute respiratory syndrome coronavirus 2 / Tensors / Tomography / Tomography, X-Ray Computed - methods / Unsupervised Machine Learning