Related Experiment Video
Updated: Oct 10, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
A coarse-refine segmentation network for COVID-19 CT images
Ziwang Huang1, Liang Li2, Xiang Zhang3
1School of Data and Computer Science Sun Yat-Sen University Guangzhou China.
Insights
A new coarse-refine segmentation network accurately segments COVID-19 lung CT scans. This AI model improves boundary detection and multi-scale analysis for better infection assessment and treatment planning.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pulmonology
Background:
- Accurate segmentation of COVID-19 infected regions in CT scans is crucial for effective patient treatment.
- Challenges include multi-scale infected areas and unclear boundaries due to low contrast in CT images.
Purpose of the Study:
- To develop an advanced segmentation network for precise COVID-19 CT image analysis.
- To address limitations of existing models in segmenting complex infected lung regions.
Main Methods:
- Proposed a novel coarse-refine segmentation network incorporating an atrous spatial pyramid pooling module.
- Utilized a hybrid loss function to enhance boundary definition and capture delicate structures.
- Implemented a coarse-refine architecture to improve segmentation accuracy.
Main Results:
- The proposed network demonstrated superior performance in segmenting COVID-19 CT images compared to established medical segmentation models.
- The model effectively handled multi-scale infected regions and improved boundary delineation.
- Achieved more accurate estimates of infection progression.
Conclusions:
- The developed coarse-refine segmentation network offers a significant advancement for COVID-19 diagnosis and treatment planning.
- Enhanced segmentation accuracy facilitates better clinical decision-making for COVID-19 patients.
- This AI-driven approach aids in providing more reasonable and effective treatment options.
Abstract:
The rapid spread of the novel coronavirus disease 2019 (COVID-19) causes a significant impact on public health. It is critical to diagnose COVID-19 patients so that they can receive reasonable treatments quickly. The doctors can obtain a precise estimate of the infection's progression and decide more effective treatment options by segmenting the CT images of COVID-19 patients. However, it is challenging to segment infected regions in CT slices because the infected regions are multi-scale, and the boundary is not clear due to the low contrast between the infected area and the normal area. In this paper, a coarse-refine segmentation network is proposed to address these challenges. The coarse-refine architecture and hybrid loss is used to guide the model to predict the delicate structures with clear boundaries to address the problem of unclear boundaries. The atrous spatial pyramid pooling module in the network is added to improve the performance in detecting infected regions with different scales. Experimental results show that the model in the segmentation of COVID-19 CT images outperforms other familiar medical segmentation models, enabling the doctor to get a more accurate estimate on the progression of the infection and thus can provide more reasonable treatment options.
