Li Zhongliang, Li Xuechen, Jin Zhihao, Shen Linlin
AI Research Center for Medical Image Analysis and Diagnosis, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060 Guangdong China.
National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060 Guangdong China.
Neural Comput Appl. 2023;35(15):10717-10731. doi: 10.1007/s00521-023-08259-9. Epub 2023 Mar 24.
The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019, and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by ground glass opacity, a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo-lesion generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo-COVID-19 images. The pairs of normal and pseudo-COVID-19 images were then used to train an encoder-decoder architecture-based U-Net for image restoration, which does not require any labeled data. The pretrained encoder was then fine-tuned using labeled data for COVID-19 diagnosis task. Two public COVID-19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis, and the accuracy of the proposed method outperformed the supervised model pretrained on large-scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively.
自2019年12月首次报告以来，2019冠状病毒病（COVID-19）已在全球迅速传播，胸部计算机断层扫描（CT）已成为其诊断的主要工具之一。近年来，基于深度学习的方法在众多图像识别任务中表现出令人印象深刻的性能。然而，它们通常需要大量带注释的数据进行训练。受COVID-19患者CT扫描中常见的磨玻璃影的启发，我们在本文中提出了一种基于伪病变生成和恢复的新型自监督预训练方法用于COVID-19诊断。我们使用基于梯度噪声的数学模型柏林噪声来生成类似病变的图案，然后将其随机粘贴到正常CT图像的肺部区域以生成伪COVID-19图像。然后使用正常图像和伪COVID-19图像对来训练基于编码器-解码器架构的U-Net进行图像恢复，该方法不需要任何标记数据。然后使用COVID-19诊断任务的标记数据对预训练的编码器进行微调。使用两个由CT图像组成的公开COVID-19诊断数据集进行评估。综合实验结果表明，所提出的自监督学习方法可以为COVID-19诊断提取更好的特征表示，并且该方法在SARS-CoV-2数据集和济南COVID-19数据集上的准确率分别比在大规模图像上预训练的监督模型高出6.57%和3.03%。
