H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

Abstract

Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2D and 3D FCNs, serve as the back-bone in many volumetric image segmentation. However, 2D convolutions can not fully leverage the spatial information along the third dimension while 3D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2D DenseUNet for efficiently extracting intra-slice features and a 3D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion (HFF) layer. We extensively evaluated our method on the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge and 3DIRCADb Dataset. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.

Accept for publication at IEEE Transactions on Medical Imaging

Cited by in corpus (15)

• U-Net and its variants for medical image segmentation: theory and applications
• Medical Image Segmentation Using Deep Learning: A Survey
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
• Reinventing 2D Convolutions for 3D Images
• 3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
• Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet
• A Comprehensive Review of Modern Object Segmentation Approaches
• Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
• Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
• Hybrid Cascaded Neural Network for Liver Lesion Segmentation
• Conquering Data Variations in Resolution: A Slice-Aware Multi-Branch Decoder Network
• Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images
• E${}^2$Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans