VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation

Abstract

Recently deep residual learning with residual units for training very deep neural networks advanced the state-of-the-art performance on 2D image recognition tasks, e.g., object detection and segmentation. However, how to fully leverage contextual representations for recognition tasks from volumetric data has not been well studied, especially in the field of medical image computing, where a majority of image modalities are in volumetric format. In this paper we explore the deep residual learning on the task of volumetric brain segmentation. There are at least two main contributions in our work. First, we propose a deep voxelwise residual network, referred as VoxResNet, which borrows the spirit of deep residual learning in 2D image recognition tasks, and is extended into a 3D variant for handling volumetric data. Second, an auto-context version of VoxResNet is proposed by seamlessly integrating the low-level image appearance features, implicit shape information and high-level context together for further improving the volumetric segmentation performance. Extensive experiments on the challenging benchmark of brain segmentation from magnetic resonance (MR) images corroborated the efficacy of our proposed method in dealing with volumetric data. We believe this work unravels the potential of 3D deep learning to advance the recognition performance on volumetric image segmentation.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Wide Residual Networks
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• Identity Mappings in Deep Residual Networks
• Instance-aware Semantic Segmentation via Multi-task Network Cascades
• Deep End2End Voxel2Voxel Prediction

Cited by in corpus (32)

• A Survey on Deep Learning in Medical Image Analysis
• Medical Image Segmentation Using Deep Learning: A Survey
• Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networks
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• An application of cascaded 3D fully convolutional networks for medical image segmentation
• Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks
• CNN-based Segmentation of Medical Imaging Data
• Hierarchical 3D fully convolutional networks for multi-organ segmentation
• Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge
• Quantitative analysis of patch-based fully convolutional neural networks for tissue segmentation on brain magnetic resonance imaging
• Tangent Convolutions for Dense Prediction in 3D
• Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities
• Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
• DARTS: DenseUnet-based Automatic Rapid Tool for brain Segmentation
• Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification
• Cardiac Segmentation on CT Images through Shape-Aware Contour Attentions
• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
• Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach
• Spatial Aggregation of Holistically-Nested Convolutional Neural Networks for Automated Pancreas Localization and Segmentation
• U-Net Based Architecture for an Improved Multiresolution Segmentation in Medical Images
• A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans
• Deep Learning Based Instance Segmentation in 3D Biomedical Images Using Weak Annotation
• Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
• Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation
• False Positive Reduction in Lung Computed Tomography Images using Convolutional Neural Networks
• Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation
• The Method of Multimodal MRI Brain Image Segmentation Based on Differential Geometric Features
• Selective Information Passing for MR/CT Image Segmentation
• A Survey On 3D Inner Structure Prediction from its Outer Shape
• A Study on Trees's Knots Prediction from their Bark Outer-Shape
• Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans
• Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation