Related Experiment Video
Updated: Nov 30, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
AI aiding in diagnosing, tracking recovery of COVID-19 using deep learning on Chest CT scans
Maheshwar Kuchana1, Amritesh Srivastava2, Ronald Das3
1BML Munjal University, Kapriwas, India.
Insights
A novel U-Net deep learning model improves COVID-19 detection in CT scans by segmenting lung spaces and anomalies. This AI approach achieves high accuracy, aiding in pandemic control efforts.
Area of Science:
- Artificial Intelligence in Medical Imaging
- Deep Learning for Disease Detection
- Radiology and Diagnostic Imaging
Background:
- Coronavirus disease (COVID-19) pandemic declared by WHO due to rapid spread and high mortality.
- Diagnostic challenges: COVID-19 incubation period varies (5-27 days), and CT scan sensitivity may exceed RT-PCR.
- Key CT scan indicators for COVID-19 include ground-glass opacity (GGO), consolidation, and pleural effusion.
Purpose of the Study:
- To develop and evaluate a deep learning model for segmenting lung spaces and identifying COVID-19 anomalies in chest CT scans.
- To enhance diagnostic accuracy and potentially aid in controlling the spread of COVID-19 through improved medical imaging analysis.
Main Methods:
- A 2D deep learning architecture utilizing U-Net as its backbone was proposed for dual segmentation tasks.
- Hyperparameter optimization included adjusting filters, incorporating attention gates, spatial pyramid pooling, and maintaining filter homogeneity.
- Model performance was assessed using public datasets (GitHub, Kaggle) and evaluated with F1-Score and Mean Intersection over Union (Mean IoU).
Main Results:
- The proposed U-Net based model achieved a high F1-Score of 97.31% and a Mean IoU of 84.6%.
- Experimental results demonstrated superior performance compared to standard U-Net and attention U-Net architectures.
- Optimized hyperparameters significantly contributed to the model's enhanced segmentation and detection capabilities.
Conclusions:
- The modified U-Net architecture with hyperparameter tuning offers a robust and accurate method for COVID-19 detection in CT scans.
- This AI-driven approach shows promise for integration into healthcare workflows to assist in pandemic management.
- The study highlights the potential of deep learning in improving the sensitivity and efficiency of radiological diagnostics for infectious diseases.
Abstract:
Coronavirus (COVID-19) has spread throughout the world, causing mayhem from January 2020 to this day. Owing to its rapidly spreading existence and high death count, the WHO has classified it as a pandemic. Biomedical engineers, virologists, epidemiologists, and people from other medical fields are working to help contain this epidemic as soon as possible. The virus incubates for five days in the human body and then begins displaying symptoms, in some cases, as late as 27 days. In some instances, CT scan based diagnosis has been found to have better sensitivity than RT-PCR, which is currently the gold standard for COVID-19 diagnosis. Lung conditions relevant to COVID-19 in CT scans are ground-glass opacity (GGO), consolidation, and pleural effusion. In this paper, two segmentation tasks are performed to predict lung spaces (segregated from ribcage and flesh in Chest CT) and COVID-19 anomalies from chest CT scans. A 2D deep learning architecture with U-Net as its backbone is proposed to solve both the segmentation tasks. It is observed that change in hyperparameters such as number of filters in down and up sampling layers, addition of attention gates, addition of spatial pyramid pooling as basic block and maintaining the homogeneity of 32 filters after each down-sampling block resulted in a good performance. The proposed approach is assessed using publically available datasets from GitHub and Kaggle. Model performance is evaluated in terms of F1-Score, Mean intersection over union (Mean IoU). It is noted that the proposed approach results in 97.31% of F1-Score and 84.6% of Mean IoU. The experimental results illustrate that the proposed approach using U-Net architecture as backbone with the changes in hyperparameters shows better results in comparison to existing U-Net architecture and attention U-net architecture. The study also recommends how this methodology can be integrated into the workflow of healthcare systems to help control the spread of 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...