One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation

Abstract

Class imbalance has emerged as one of the major challenges for medical image segmentation. The model cascade (MC) strategy 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, we propose 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. 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 and design a cross-task guided attention (CGA) module which 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. 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.

arXiv comment14 pages, 7 figures, To appear in IEEE Transactions on Image Processing

References in corpus (6)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
• Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions
• CompNet: Complementary Segmentation Network for Brain MRI Extraction

Cited by in corpus (7)

• Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalities
• Inter-slice Context Residual Learning for 3D Medical Image Segmentation
• Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review
• Feature-enhanced Generation and Multi-modality Fusion based Deep Neural Network for Brain Tumor Segmentation with Missing MR Modalities
• Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning
• Category Guided Attention Network for Brain Tumor Segmentation in MRI
• Federated Modality-specific Encoders and Partially Personalized Fusion Decoder for Multimodal Brain Tumor Segmentation