A two-stage 3D Unet framework for multi-class segmentation on full resolution image

Abstract

Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances. However, a common problem when dealing with large, high resolution 3D data is that the volumes input into the deep CNNs has to be either cropped or downsampled due to limited memory capacity of computing devices. These operations lead to loss of resolution and increment of class imbalance in the input data batches, which can downgrade the performances of segmentation algorithms. Inspired by the architecture of image super-resolution CNN (SRCNN) and self-normalization network (SNN), we developed a two-stage modified Unet framework that simultaneously learns to detect a ROI within the full volume and to classify voxels without losing the original resolution. Experiments on a variety of multi-modal volumes demonstrated that, when trained with a simply weighted dice coefficients and our customized learning procedure, this framework shows better segmentation performances than state-of-the-art Deep CNNs with advanced similarity metrics.

References in corpus (6)

• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalities
• Hierarchical 3D fully convolutional networks for multi-organ segmentation
• Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
• Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets
• Multi-Planar Deep Segmentation Networks for Cardiac Substructures from MRI and CT

Cited by in corpus (9)

• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation
• FU-net: Multi-class Image Segmentation Using Feedback Weighted U-net
• Organ at Risk Segmentation in Head and Neck CT Images by Using a Two-Stage Segmentation Framework Based on 3D U-Net
• Simultaneous Left Atrium Anatomy and Scar Segmentations via Deep Learning in Multiview Information with Attention
• Multi-channel MRI Embedding: An EffectiveStrategy for Enhancement of Human Brain WholeTumor Segmentation
• ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease
• Tissue characterization based on the analysis on i3DUS data for diagnosis support in neurosurgery
• Accurate Congenital Heart Disease Model Generation for 3D Printing