One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation

Class imbalance has emerged as one of the major challenges for medical image segmentation. The model cascade (MC) strategy, a popular scheme, significantly alleviates the class imbalance issue via running a set of individual deep models for coarse-to-fine segmentation. Despite its outstanding performance, however, this method leads to undesired system complexity and also ignores the correlation among the models. To handle these flaws in the MC approach, we propose in this paper a light-weight deep model, i.e., the One-pass Multi-task Network (OM-Net) to solve class imbalance better than MC does, while requiring only one-pass computation for brain tumor segmentation. First, OM-Net integrates the separate segmentation tasks into one deep model, which consists of shared parameters to learn joint features, as well as task-specific parameters to learn discriminative features. Second, to more effectively optimize OM-Net, we take advantage of the correlation among tasks to design both an online training data transfer strategy and a curriculum learning-based training strategy. Third, we further propose sharing prediction results between tasks, which enables us to design a cross-task guided attention (CGA) module. By following the guidance of the prediction results provided by the previous task, CGA can adaptively recalibrate channel-wise feature responses based on the category-specific statistics. Finally, a simple yet effective post-processing method is introduced to refine the segmentation results of the proposed attention network. Extensive experiments are conducted to demonstrate the effectiveness of the proposed techniques. Most impressively, we achieve state-of-the-art performance on the BraTS 2015 testing set and BraTS 2017 online validation set. Using these proposed approaches, we also won joint third place in the BraTS 2018 challenge among 64 participating teams. The code is publicly available at https://github.com/chenhong-zhou/OM-Net.

I. Introduction

Brain tumors are one of the most deadly cancers worldwide. Among these tumors, glioma is the most common type [1]. The average survival time for glioblastoma patients is less than 14 months [2]. Timely diagnosis of brain tumors is thus vital to ensuring appropriate treatment planning, surgery, and follow-up visits [3]. As a popular non-invasive technique, Magnetic Resonance Imaging (MRI) produces markedly different types of tissue contrast and has thus been widely used by radiologists to diagnose brain tumors [4]. However, the manual segmentation of brain tumors from MRI images is both subjective and time-consuming [5]. Therefore, it is highly desirable to design automatic and robust brain tumor segmentation tools.