Related Experiment Video
Updated: Sep 27, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model
Sania Shamim1, Mazhar Javed Awan1, Azlan Mohd Zain2
1Department of Software Engineering, University of Management and Technology, Lahore, Pakistan.
Insights
A novel segmentation method, convUnet, accurately identifies ground glass opacity in COVID-19 CT scans. This AI approach offers a faster, more reliable alternative to RT-PCR testing for diagnosing coronavirus disease 2019.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pulmonology
Background:
- The COVID-19 pandemic caused widespread health impacts globally.
- Computed Tomography (CT) scans offer a potential alternative to RT-PCR for COVID-19 diagnosis.
- Segmenting early-stage COVID-19 lung abnormalities like ground glass opacity (GGO) in CT scans is challenging due to their subtle appearance.
Purpose of the Study:
- To develop an automated segmentation approach for identifying ground glass opacity (GGO) in COVID-19 CT images.
- To improve the accuracy and efficiency of COVID-19 diagnosis using medical imaging analysis.
- To propose a modified Unet model, termed convUnet, for precise pixel-level classification of ROIs in lung CT scans.
Main Methods:
- A modified Unet deep learning model (convUnet) was developed, incorporating increased weights in its contracting and expanding paths.
- An improved convolutional module was integrated to enhance connectivity between the encoder and decoder pipelines.
- The convUnet model was trained and evaluated on the Medseg1 dataset for GGO segmentation.
Main Results:
- The convUnet model demonstrated superior performance in segmenting GGO in COVID-19 CT images compared to standard Unet and other state-of-the-art models.
- Quantitative metrics including accuracy (93.29%), recall (93.01%), precision (93.67%), Dice-coefficient (92.46%), F1-score (93.34%), and IOU (86.96%) were achieved.
- The enhanced model effectively addressed the challenge of segmenting subtle GGO in early-stage COVID-19 infections.
Conclusions:
- The proposed convUnet segmentation approach is accurate, fast, and reliable for diagnosing COVID-19 from CT scans.
- This AI-driven method can significantly aid clinicians in the rapid and efficient diagnosis of coronavirus disease 2019.
- The modifications to the Unet architecture enhance its capability for medical image segmentation tasks.
Abstract:
The coronavirus (COVID-19) pandemic has had a terrible impact on human lives globally, with far-reaching consequences for the health and well-being of many people around the world. Statistically, 305.9 million people worldwide tested positive for COVID-19, and 5.48 million people died due to COVID-19 up to 10 January 2022. CT scans can be used as an alternative to time-consuming RT-PCR testing for COVID-19. This research work proposes a segmentation approach to identifying ground glass opacity or ROI in CT images developed by coronavirus, with a modified structure of the Unet model having been used to classify the region of interest at the pixel level. The problem with segmentation is that the GGO often appears indistinguishable from a healthy lung in the initial stages of COVID-19, and so, to cope with this, the increased set of weights in contracting and expanding the Unet path and an improved convolutional module is added in order to establish the connection between the encoder and decoder pipeline. This has a major capacity to segment the GGO in the case of COVID-19, with the proposed model being referred to as "convUnet." The experiment was performed on the Medseg1 dataset, and the addition of a set of weights at each layer of the model and modification in the connected module in Unet led to an improvement in overall segmentation results. The quantitative results obtained using accuracy, recall, precision, dice-coefficient, F1score, and IOU were 93.29%, 93.01%, 93.67%, 92.46%, 93.34%, 86.96%, respectively, which is better than that obtained using Unet and other state-of-the-art models. Therefore, this segmentation approach proved to be more accurate, fast, and reliable in helping doctors to diagnose COVID-19 quickly and efficiently.
