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

Medical image segmentation is an important step in medical image analysis. With the rapid development of 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, etc... (read more)

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Lung Nodule Segmentation on LUNA (Accuracy metric)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Retinal Vessel Segmentation DRIVE CE-Net AUC 0.9779 # 9
Accuracy 0.9545 # 4
Medical Image Segmentation ISBI 2012 EM Segmentation CE-Net VInfo 0.9878 # 1
VRand 0.9743 # 1
Lung Nodule Segmentation LUNA CE-Net Accuracy 0.99 # 1
Optic Disc Segmentation Messidor CE-Net Error rate 0.051 # 1
Optic Disc Segmentation ORIGA CE-Net Error rate 0.058 # 1
Optic Disc Segmentation RIM-ONE-R1 CE-Net Error rate 0.087 # 1
Retinal OCT Layer Segmentation Topcon CE-Net w/ Dice MAE 1.68 # 1

Methods used in the Paper


METHOD TYPE
Concatenated Skip Connection
Skip Connections
U-Net
Semantic Segmentation Models
Average Pooling
Pooling Operations
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Residual Connection
Skip Connections
Convolution
Convolutions
ResNet
Convolutional Neural Networks