A deep-learning-based framework for severity assessment of COVID-19 with CT images. (15th December 2021)

• Record Type: Journal Article
• Authors: Li, Zhidan; Zhao, Shixuan; Chen, Yang; Luo, Fuya; Kang, Zhiqing; Cai, Shengping; Zhao, Wei; Liu, Jun; Zhao, Di; Li, Yongjie
• Is Part Of: Expert systems with applications. Volume 185(2021)
• Publication Date: 2021-12-15
• Subjects: COVID-19 -- Deep learning -- Severity assessment -- Multi-view lesion -- Dual-Siamese channels -- Clinical metadata; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115616
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel prior-knowledge-based model for severity assessment of COVID-19. A new input strategy based on multi-view slices for 3D model of COVID-19. Sufficient CT images were collected for the fine-grained severity assessment. Potential values for accelerating triage, following up the treatment response, etc. Abstract: Millions of positive COVID-19 patients are suffering from the pandemic around the world, a critical step in the management and treatment is severity assessment, which is quite challenging with the limited medical resources. Currently, several artificial intelligence systems have been developed for the severity assessment. However, imprecise severity assessment and insufficient data are still obstacles. To address these issues, we proposed a novel deep-learning-based framework for the fine-grained severity assessment using 3D CT scans, by jointly performing lung segmentation and lesion segmentation. The main innovations in the proposed framework include: 1) decomposing 3D CT scan into multi-view slices for reducing the complexity of 3D model, 2) integrating prior knowledge (dual-Siamese channels and clinical metadata) into our model for improving the model performance. We evaluated the proposed method on 1301 CT scans of 449 COVID-19 cases collected by us, our method achieved an accuracy of 86.7% for four-way classification, with the sensitivities of 92%, 78%, 95%, 89% for four stages. Moreover, ablation study demonstrated the effectiveness of the major components in our model. This indicates that our method may contribute a potential solution to severity assessment of COVID-19 patients using CT images and clinical metadata.