Dual Uncertainty-Guided Mixing Consistency for Semi-Supervised 3D Medical Image Segmentation

3D semi-supervised medical image segmentation is extremely essential in computer-aided diagnosis, which can reduce the time-consuming task of performing annotation. The challenges with current 3D semi-supervised segmentation algorithms includes the methods, limited attention to volume-wise context information, their inability to generate accurate pseudo labels and a failure to capture important details during data augmentation. This article proposes a dual uncertainty-guided mixing consistency network for accurate 3D semi-supervised segmentation, which can solve the above challenges. The proposed network consists of a Contrastive Training Module which improves the quality of augmented images by retaining the invariance of data augmentation between original data and their augmentations. The Dual Uncertainty Strategy calculates dual uncertainty between two different models to select a more confident area for subsequent segmentation. The Mixing Volume Consistency Module that guides the consistency between mixing before and after segmentation for final segmentation, uses dual uncertainty and can fully learn volume-wise context information. Results from evaluative experiments on brain tumor and left atrial segmentation shows that the proposed method outperforms state-of-the-art 3D semi-supervised methods as confirmed by quantitative and qualitative analysis on datasets. This effectively demonstrates that this study has the potential to become a medical tool for accurate segmentation. Code is available at: https://github.com/yang6277/DUMC.

I. Introduction

3D semi-supervised medical image segmentation in medical image analysis has been a subject of continuous interest to numerous researchers. This interest has been earned by 3D segmentation abilities in facilitating the planning and preparation of treatment for physicians by providing quantitative analysis of tissue volume, localization of pathologically modified tissues and visualization of anatomical structures amongst many other tasks. Applying 3D semi-supervised segmentation to the large amount of unlabeled data available in the medical field would reduce the time-consuming and laborious work of manually delineate the target area of medical images in clinical practice. Superior to 2D segmentation, 3D methods [1] provide rich details of organs, tissues and lesions, thereby revealing more disease characteristics which enhances the effectiveness of diagnosis.