Abstract

Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment. The remaining challenges are the obvious scale difference between different types of COVID-19 lesions and the similarity between the lesions and normal tissues. This work aims to segment lesions of different scales and lesion boundaries correctly by utilizing multiscale and multilevel features. A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features for better segmentation of lesions at different scales. Furthermore, a multilevel feature aggregate (MLFA) module is proposed to reduce the information loss in the downsampling process. Experiments on the publicly available COVID-19 CT Segmentation dataset demonstrate that the proposed MSDC-Net is superior to other existing methods in segmenting lesion boundaries and large, medium, and small lesions, and achieves the best results in Dice similarity coefficient, sensitivity and mean intersection-over-union (mIoU) scores of 82.4%, 81.1% and 78.2%, respectively. Compared with other methods, the proposed model has an average improvement of 10.6% and 11.8% on Dice and mIoU. Compared with the existing methods, our network achieves more accurate segmentation of lesions at various scales and lesion boundaries, which will facilitate further clinical analysis. In the future, we consider integrating the automatic detection and segmentation of COVID-19, and conduct research on the automatic diagnosis system of COVID-19.

Highlights

  • Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment

  • Hassantabar et al.[12] proposed a deep neural network and a convolutional neural network to diagnose COVID-19 patients, a segmentation method is designed for the location of COVID-19 infected tissues in lung X-ray images

  • Where k represents the number of pixel categories, pii represents the number of pixels whose actual category is i and the predicted category is i, pij represents the number of pixels whose actual category is i but predicted category is j, and pji represents the number of pixels whose actual category is j but predicted category is i

Read more

Summary

Introduction

Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment. A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. Hassantabar et al.[12] proposed a deep neural network and a convolutional neural network to diagnose COVID-19 patients, a segmentation method is designed for the location of COVID-19 infected tissues in lung X-ray images. The network needs to acquire the image features of lesions at different ­scales[21,22], which have a great influence on the segmentation ­accuracy[23] These multiscale features will determine the accuracy of pixel classification during the lesion segmentation. The above methods do not fully consider the multiscale feature information of infected lesions

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

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 call