Related Experiment Video
Updated: Nov 7, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT
Shikha Chaganti1, Philippe Grenier1, Abishek Balachandran1
1Hôpital Foch, Suresnes, France (P.G., F.M.), Donald and Barbara Zucker School of Medicine, Feinstein Institutes for Medical Research, Northwell Health, Manhasset, NY, USA (S.C., P.S.), Siemens Healthinners, Bangalore, India (A.B.), Siemens Healthineers, Forchheim, Germany (T.F., V.Z.), Siemens Healthineers, Princeton, NJ, USA (S.C., B.G., S.G., S.L., T.R., Z.X., Y.Y., D.C.), Siemens Healthineers, Paris, France (G.C.), University Hospital Basel, Clinic of Radiology & Nuclear medicine, Basel, Switzerland (A.W.S.), Vancouver General Hospital, Vancouver, Canada (N.M., S.N., W.P.).
This study introduces an automated method to segment and quantify COVID-19 lung abnormalities on CT scans, providing rapid and accurate severity scores for ground glass opacities and consolidations.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Pulmonology
Background:
- Coronavirus disease 2019 (COVID-19) presents with characteristic lung abnormalities on CT scans, including ground glass opacities and consolidations.
- Accurate quantification of these abnormalities is crucial for assessing disease severity and patient outcomes.
- Manual segmentation and quantification of these patterns are time-consuming and subjective.
Purpose of the Study:
- To develop and validate an automated method for segmenting and quantifying COVID-19 related lung abnormalities on non-contrast chest CT scans.
- To provide objective, quantitative measures of disease severity, including global (extent and opacity) and lobe-specific involvement.
Main Methods:
- A deep learning and deep reinforcement learning-based method was developed to segment lesions, lungs, and lobes in 3D from non-contrast chest CT volumes.
- The method processes a dataset of 9749 chest CT volumes and outputs global (PO, PHO) and lobe-wise (LSS, LHOS) severity scores.
- Evaluation was performed on 200 participants (100 COVID-19 positive, 100 controls), with ground truth established by manual annotations.
Main Results:
- The automated method demonstrated high accuracy, with Pearson correlation coefficients ranging from 0.90 to 0.97 when compared to manual ground truth for COVID-19 cases.
- Healthy controls showed minimal predicted abnormality (PO < 1% in 98% of cases).
- Automated processing time was significantly reduced to 10 seconds per case, compared to 30 minutes for manual annotation.
Conclusions:
- A novel automated method effectively segments COVID-19 lung abnormalities and computes objective severity scores (PO, PHO, LSS, LHOS).
- This technique offers a rapid, accurate, and reproducible approach for quantifying COVID-19 lung involvement on CT.
- The automated system has the potential to aid in clinical assessment and research related to COVID-19.
More Related Videos
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
01:10Computed Tomography
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT