A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images
By Guotai Wang, Xinglong Liu, Chaoping Li, Zhiyong Xu, Jiugen Ruan, Haifeng Zhu, T. Meng, Kang Li, Ning Huang, Shaoting Zhang. IEEE Transactions on Medical Imaging, 2020
418 citations recorded by the source corpus.
Segmentation of pneumonia lesions from CT scans of COVID-19 patients is important for accurate diagnosis and follow-up. Deep learning has a potential to automate this task but requires a large set of high-quality annotations that are difficult to collect. Learning from noisy training labels that are easier to obtain has a potential to alleviate this problem. To this end, we propose a novel noise-robust framework to learn from noisy labels for the segmentation task. We first introduce a noise-robust Dice loss that is a generalization of Dice loss for segmentation and Mean Absolute Error (MAE) loss for robustness against noise, then propose a novel COVID-19 Pneumonia Lesion segmentation network (COPLE-Net) to better deal with the lesions with various scales and appearances. The noise-robust Dice loss and COPLE-Net are combined with an adaptive self-ensembling framework for training, where an Exponential Moving Average (EMA) of a student model is used as a teacher model that is adaptively updated by suppressing the contribution of the student to EMA when the student has a large training loss. The student model is also adaptive by learning from the teacher only when the teacher outperforms the student. Experimental results showed that: (1) our noise-robust Dice loss outperforms existing noise-robust loss functions, (2) the proposed COPLE-Net achieves higher performance than state-of-the-art image segmentation networks, and (3) our framework with adaptive self-ensembling significantly outperforms a standard training process and surpasses other noise-robust training approaches in the scenario of learning from noisy labels for COVID-19 pneumonia lesion segmentation.
Subfields: Health Informatics, Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/664c5bef7e60cc11e75132ecd3566db166d3607e
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Radiology, Nuclear Medicine and Imaging
Citations in the corpus
- Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, methodology): “[34] 2D CT UESTC-COVID-19 Dataset [35], COVID-19-CT-Seg dataset [26] Self-ensembling strategy to build the up-to-date predictions via exponential moving average online”
- Medical Image Segmentation Review: The Success of U-Net (2022, methodology): “make use of ASPP in the bottleneck as well in their COPLE-Net for the segmentation of pneumonia lesions from CT scans of COVID-19 patients [82].”
- Recent advances and clinical applications of deep learning in medical image analysis (2021, methodology): “…semi-supervised adversarial approach, consistency-based semi-supervised methods such as Π - Model (Laine and Aila, 2017) and Mean Teacher (Tarvainen and Valpola, 2017b) have also been used to leverage unlabeled medical image data for better classification (Shang et al., 2019; Liu et al., 2020a).”
- Blockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging (2020, background): “To improve the detection accuracy, a significant series of deep learning models are proposed which detect different types of infection by analyzing the CT and X-ray images [1]–[6].”