Our work on COVID-19 CT image segmentation accepted by IEEE TMI

Recntly, our work on COVID-19 CT image segmentation has been accepted by IEEE TMI. The paper is entitled "A Noise-robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions from CT Images".

Abstract: 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 COPLENet 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.

The above figure shows an example of the pneumonia lesion segmentation. (a) one slice of a CT volume. (b) segmentation by COPLE-Net (green) compared with the ground truth (orange). (c) 3D visualization.

The full version of the paper is avaiable at: https://ieeexplore.ieee.org/document/9109297

Based on this project, we have also released a dataset, called "UESTC-COVID-19" , which contains 120 annotated CT volumes of COVID-19 patients. More details can be found here: http://faculty.uestc.edu.cn/HiLab/en/article/379152/list/index.htm 

The proposed COPLE-Net and a pretrained model is also avaible on github: https://github.com/HiLab-git/COPLE-Net