Weakly Supervised Segmentation of COVID19 Infection with Scribble Annotation on CT Images. (February 2022)

• Record Type: Journal Article
• Authors: Liu, Xiaoming; Yuan, Quan; Gao, Yaozong; He, Kelei; Wang, Shuo; Tang, Xiao; Tang, Jinshan; Shen, Dinggang
• Is Part Of: Pattern recognition. Volume 122(2022)
• Publication Date: 2022-02
• Subjects: COVID-19 -- infection segmentation -- weakly supervised learning -- transformation consistency -- uncertainty; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108341
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We propose a weakly supervised COVID-19 infection segmentation method with scribble supervision. To the best of our knowledge, it is the first work adopting scribble-level supervision in COVID-19 segmentation. An uncertainty-aware mean teacher framework is incorporated into the proposed method to guide the model training, encouraging the segmentation predictions to be consistent under different perturbations for an input image. With the pixel level uncertainty measure on the predictions of the teacher model, the student model is guided with reliable supervision. We further regularize the model with a transformation-consistent strategy, which is beneficial for the segmentation task and makes our approach easier to deal with the segmentation of irregular lesion areas. We evaluated the proposed method on three datasets and compared it with other advanced approaches. The results demonstrated the superiority of the proposed method. Abstract: Segmentation of infections from CT scans is important for accurate diagnosis and follow-up in tackling the COVID-19. Although the convolutional neural network has great potential to automate the segmentation task, most existing deep learning-based infection segmentation methods require fully annotated ground-truth labels for training, which is time-consuming and labor-intensive. This paper proposed a novel weakly supervised segmentation method for COVID-19 infections in CT slices, which only requires scribble supervision and is enhanced with the uncertainty-aware self-ensembling and transformation-consistent techniques. Specifically, to deal with the difficulty caused by the shortage of supervision, an uncertainty-aware mean teacher is incorporated into the scribble-based segmentation method, encouraging the segmentation predictions to be consistent under different perturbations for an input image. This mean teacher model can guide the student model to be trained using information in images without requiring manual annotations. On the other hand, considering the output of the mean teacher contains both correct and unreliable predictions, equally treating each prediction in the teacher model may degrade the performance of the student network. To alleviate this problem, the pixel level uncertainty measure on the predictions of the teacher model is calculated, and then the student model is only guided by reliable predictions from the teacher model. To further regularize the network, a transformation-consistent strategy is also incorporated, which requires the prediction to follow the same transformation if a transform is performed on an input image of the network. The proposed method has been evaluated on two public datasets and one local dataset. The experimental results demonstrate that the proposed method is more effective than other weakly supervised methods and achieves similar performance as those fully supervised.