CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Published in

IEEE Transactions on Medical Imaging(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

Comprehensive results show that the proposed CE-Net method outperforms the original U- net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation , cell contour segmentation and retinal optical coherence tomography layer segmentation.

Abstract

Medical image segmentation is an important step in medical image analysis. With the rapid development of a convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, and so on. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations led to the loss of some spatial information. In this paper, we propose a context encoder network (CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor, and a feature decoder module. We use the pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution block and a residual multi-kernel pooling block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation, and retinal optical coherence tomography layer segmentation.

Authors

Jiang Liu

6 papers

Shenghua Gao

12 papers

Tianyang Zhang

3 papers

References82 items

Rethinking ImageNet Pre-Training

DeepDisc: Optic Disc Segmentation Based on Atrous Convolution and Spatial Pyramid Pooling

Unsupervised Medical Image Segmentation Based on the Local Center of Mass

Optic Disc and Cup Segmentation with Blood Vessel Removal from Fundus Images for Glaucoma Detection

Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Published in

IEEE Transactions on Medical Imaging(2019)

External Links:

Generate Graph DownloadPDF

TL;DR

Abstract

Authors

Jiang Liu

6 papers

Shenghua Gao

12 papers

Tianyang Zhang

3 papers

References82 items

Rethinking ImageNet Pre-Training

DeepDisc: Optic Disc Segmentation Based on Atrous Convolution and Spatial Pyramid Pooling

Unsupervised Medical Image Segmentation Based on the Local Center of Mass

Optic Disc and Cup Segmentation with Blood Vessel Removal from Fundus Images for Glaucoma Detection

Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading

Huaying Hao

2 papers

Yitian Zhao

5 papers

Sparse Range-Constrained Learning and Its Application for Medical Image Grading

Fully Convolutional Adaptation Networks for Semantic Segmentation

InfiNet: Fully convolutional networks for infant brain MRI segmentation

Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry.

Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks

Learning supervised descent directions for optic disc segmentation

Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation

Improving Generalization Performance by Switching from Adam to SGD

Learning Based Segmentation of CT Brain Images: Application to Postoperative Hydrocephalic Scans

Pathological OCT Retinal Layer Segmentation Using Branch Residual U-Shape Networks

Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation

Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection

The Marginal Value of Adaptive Gradient Methods in Machine Learning

ReLayNet: Retinal Layer and Fluid Segmentation of Macular Optical Coherence Tomography using Fully Convolutional Network

Dual-Channel Active Contour Model for Megakaryocytic Cell Segmentation in Bone Marrow Trephine Histology Images

Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network

Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network

Pyramid Scene Parsing Network

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

DeepVessel: Retinal Vessel Segmentation via Deep Learning and Conditional Random Field

Learning from Experts: Developing Transferable Deep Features for Patient-Level Lung Cancer Prediction

Densely Connected Convolutional Networks

VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation

3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Speckle Reduction in 3D Optical Coherence Tomography of Retina by A-Scan Reconstruction

Segmenting Retinal Blood Vessels With Deep Neural Networks

Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Superpixel-Based Segmentation for 3D Prostate MR Images

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Deep Residual Learning for Image Recognition

Liver segmentation using superpixel-based graph cuts and restricted regions of shape constrains

Crowdsourcing the creation of image segmentation algorithms for connectomics

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Discriminative dictionary learning for abdominal multi-organ segmentation

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Holistically-Nested Edge Detection

Automated Vessel Segmentation Using Infinite Perimeter Active Contour Model with Hybrid Region Information with Application to Retinal Images

Iterative Vessel Segmentation of Fundus Images

Trainable COSFIRE filters for vessel delineation with application to retinal images

Fully convolutional networks for semantic segmentation

FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Brain Tumor Segmentation Based on Local Independent Projection-Based Classification

Automatic Whole Brain MRI Segmentation of the Developing Neonatal Brain

Superpixel Classification Based Optic Disc and Optic Cup Segmentation for Glaucoma Screening

Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images

ImageNet classification with deep convolutional neural networks

A new deformable model-based segmentation approach for accurate extraction of the kidney from abdominal CT images

RIM-ONE: An open retinal image database for optic nerve evaluation

ORIGA-light: An online retinal fundus image database for glaucoma analysis and research

An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron Microscopy

Detecting the Optic Disc Boundary in Digital Fundus Images Using Morphological, Edge Detection, and Feature Extraction Techniques

Optic disc region of interest localization in fundus image for Glaucoma detection in ARGALI

Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images

Automated ventricular systems segmentation in brain CT images by combining low-level segmentation and high-level template matching

Detection of the optic disc in images of the retina using the Hough transform

Optic disk feature extraction via modified deformable model technique for glaucoma analysis

Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features.

Generalized Overlap Measures for Evaluation and Validation in Medical Image Analysis

Ridge-based vessel segmentation in color images of the retina

Optic nerve head segmentation

A shape-based approach to the segmentation of medical imagery using level sets

Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique

Image Segmentation Based on the Integration of Markov Random Fields and Deformable Models

Ridge Regression: Biased Estimation for Nonorthogonal Problems

Lung CT Image Segmentation Using Deep Neural Networks

Spleen segmentation in MRI sequence images using template matching and active contours

Lung Lesion Extraction Using a Toboggan Based Growing Automatic Segmentation Approach

Brain MR Image Segmentation Using Self Organizing Map

A Statistical Deformable Model for the Segmentation of Liver CT Volumes

We propose a DAC block and RMP block to capture more high-level features and preserve more spatial information

We integrate the proposed DAC block and RMP block with encoder-decoder structure for medical image segmentation

Field of Study

Computer ScienceMedicine

Journal Information

Name

Ieee Transactions on Medical Imaging

Page

1285 - 1298

Volume

Venue Information

Name

IEEE Transactions on Medical Imaging

Type

journal

URL

http://ieeexplore.ieee.org/servlet/opac?punumber=42

Alternate Names

IEEE Trans Med Imaging