Abstract
The coronavirus disease 2019 (COVID-19) epidemic has spread worldwide and the healthcare system is in crisis. Accurate, automated and rapid segmentation of COVID-19 lesion in computed tomography (CT) images can help doctors diagnose and provide prognostic information. However, the variety of lesions and small regions of early lesion complicate their segmentation. To solve these problems, we propose a new SAUNet++ model with squeeze excitation residual (SER) module and atrous spatial pyramid pooling (ASPP) module. The SER module can assign more weights to more important channels and mitigate the problem of gradient disappearance; the ASPP module can obtain context information by atrous convolution using various sampling rates. In addition, the generalized dice loss (GDL) can reduce the correlation between lesion size and dice loss, and is introduced to solve the problem of small regions segmentation of COVID-19 lesion. We collected multinational CT scan data from China, Italy and Russia and conducted extensive comparative and ablation studies. The experimental results demonstrated that our method outperforms state-of-the-art models and can effectively improve the accuracy of COVID-19 lesion segmentation on the dice similarity coefficient (our: 87.38 $$\%$$ vs. U-Net++: 84.25 $$\%$$ ), sensitivity (our: 93.28 $$\%$$ vs. U-Net++: 89.85 $$\%$$ ) and Hausdorff distance (our: 19.99 mm vs. U-Net++: 26.79 mm), respectively.
Highlights
COVID-19 caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was highly contagious, and world health organization (WHO) announced that the COVID-19 outbreak had entered a “global pandemic.” Up to October 20, 2021, there have been 241,411,380 confirmed cases of COVID-19, including 4,912,112 deaths, have been reported to the WHO [1]
1 γ pic gic where pic and picare probabilities that pixel i is of the lesion class c and non-lesion class c, respectively. gic and gicare probabilities for another class
By analyzing the segmentation results, the excellent performance of SAUNet++ is mainly attributed to the improvement on the segmentation of: (1) ground-glass opacity (GGO) with high transparency; (2) lesions located near blood vessels and trachea; (3) lesions located on the chest wall
Summary
COVID-19 caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was highly contagious, and world health organization (WHO) announced that the COVID-19 outbreak had entered a “global pandemic.” Up to October 20, 2021, there have been 241,411,380 confirmed cases of COVID-19, including 4,912,112 deaths, have been reported to the WHO [1]. It is found that the detection of nucleic acid by swabbing the pharynx is easy to lead to false negatives because of the quality of samples and the low viral load of the pharynx [2]. An important addition to RT-PCR, CT offers the advantages of noninvasiveness, high resolution and low noise [3]. After the development of the disease, GGO appeared in many lung lobes, which at the same time caused the thickening of interlobular septum and the appearance of “crazy-paving sign.”. After the development of the disease, GGO appeared in many lung lobes, which at the same time caused the thickening of interlobular septum and the appearance of “crazy-paving sign.” After entering the severe stage, both lungs showed
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
