Improved 3D U-Net for COVID-19 Chest CT Image Segmentation

Abstract

Coronavirus disease 2019 (COVID-19) has spread rapidly worldwide. The rapid and accurate automatic segmentation of COVID-19 infected areas using chest computed tomography (CT) scans is critical for assessing disease progression. However, infected areas have irregular sizes and shapes. Furthermore, there are large differences between image features. We propose a convolutional neural network, named 3D CU-Net, to automatically identify COVID-19 infected areas from 3D chest CT images by extracting rich features and fusing multiscale global information. 3D CU-Net is based on the architecture of 3D U-Net. We propose an attention mechanism for 3D CU-Net to achieve local cross-channel information interaction in an encoder to enhance different levels of the feature representation. At the end of the encoder, we design a pyramid fusion module with expanded convolutions to fuse multiscale context information from high-level features. The Tversky loss is used to resolve the problems of the irregular size and uneven distribution of lesions. Experimental results show that 3D CU-Net achieves excellent segmentation performance, with Dice similarity coefficients of 96.3% and 77.8% in the lung and COVID-19 infected areas, respectively. 3D CU-Net has high potential to be used for diagnosing COVID-19.

A visual review of artificial intelligence and Industry 4.0 in healthcare

“…This cluster includes the following prominent research topics: infected area, real-world scenario, and Bi-LSTM (Bidirectional Long Short Term Memory) network in the “3D CU-NET” research area. 3D CU-NET is a conventional neural network architecture that is used to diagnose and identify COVID-19 infected areas [25] .…”

A modified DeepLabV3+ based semantic segmentation of chest computed tomography images for COVID‐19 lung infections

“…They obtained the best segmentation performance with 256 × 256 and 512 × 512 image resolutions. Zheng et al 36 proposed a variant of U‐Net model named 3D CU‐Net for automatic segmentation of COVID 19 lesions from 3D chest CT scans. They developed an attention mechanism to reach local cross‐channel information interaction in an encoder.…”

DMDF-Net: Dual multiscale dilated fusion network for accurate segmentation of lesions related to COVID-19 in lung radiographic scans

“…Comparative results indicate the following distinctive aspects of FCNs over U-Nets: 1) achieve accurate segmentation despite the class imbalance on the dataset; 2) perform well even in case of annotation errors on the boundaries of symptom manifestation areas. ( Zheng et al, 2021 ) performed the volumetric segmentation of the whole 3D chest CT-scan using an enhanced version of U-Net named 3D CU-Net. An attention mechanism was mainly included in the encoder part of the proposed 3D CU-Net to obtain different levels of the feature representation.…”