Identification and Severity Assessment of COVID-19 Using Lung CT Scans
Open Access
- 6 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 124542-124555
Abstract
The COVID-19 pandemic, caused by the SARS-CoV-2 virus, continues to have a significant impact on the global population. To effectively triage patients and understand the progression of the disease, a metric-based analysis of diagnostic techniques is necessary. The objective of the present study is to identify COVID-19 from chest CT scans and determine the extent of severity, defined by a severity score that indicates the volume of infection. An unsupervised preprocessing pipeline is proposed to extract relevant clinical features and utilize this information to employ a pretrained ImageNet EfficientNetB5 model to extract discriminative features. Subsequently, a shallow feed-forward neural network is trained to classify the CT scans into three classes, namely COVID-19, Community-Acquired Pneumonia, and Normal. Through various ablation studies, we find that a domain-specific preprocessing pipeline has a significant positive impact on classification accuracy. The infection segmentation mask generated from the preprocessed pipeline performs better than state-of-the-art supervised semantic segmentation models. Further, the estimated infection severity score is observed to be well correlated with radiologists’ assessments. The results confirm the importance of domain-specific preprocessing for training machine learning algorithms.Keywords
All Related Versions
This publication has 64 references indexed in Scilit:
- Automatic Segmentation of Ground-Glass Opacities in Lung CT Images by Using Markov Random Field-Based AlgorithmsJournal of Digital Imaging, 2011
- Automatic lung segmentation for accurate quantitation of volumetric X-ray CT imagesIEEE Transactions on Medical Imaging, 2001
- Regions adjacency graph applied to color image segmentationIEEE Transactions on Image Processing, 2000
- Partitioning 3D surface meshes using watershed segmentationIEEE Transactions on Visualization and Computer Graphics, 1999
- Snakes, shapes, and gradient vector flowIEEE Transactions on Image Processing, 1998
- Method for segmenting chest CT image data using an anatomical model: preliminary resultsIEEE Transactions on Medical Imaging, 1997
- Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Image thresholding by minimizing the measures of fuzzinessPattern Recognition, 1995
- Seeded region growingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- A new method for gray-level picture thresholding using the entropy of the histogramComputer Vision, Graphics, and Image Processing, 1985