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

By Zaiwang Gu, Jun Cheng, Huan Fu, Kang Zhou, Huaying Hao, Yitian Zhao, Tianyang Zhang, Shenghua Gao, Jiang Liu. IEEE Transactions on Medical Imaging, 2019

2,080 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/a07aa5b834e5083624189a929be07c7ae2389229

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications (2020, background): “As with MRI, cancer diagnosis is a major that involves the application of CT imaging; including liver cancer [22], [23], [57], [71], [73], [85], [94], [109], [194]–[196], lung cancer [24], [34], [45], [48], [70], [73], [197]–[201], bone cancer [60], and cervical cancer [202].”
Deep semantic segmentation of natural and medical images: a review (2019, methodology): “ pushing the images to the main segmentation network. They showed improved results on electron microscopy segmentation, liver segmentation from CT, and prostate segmentation from MRI scans. Gu et al. [40] proposed using a dilated convolution block close to the network’s bottleneck to preserve contex”
PraNet: Parallel Reverse Attention Network for Polyp Segmentation (2020, background): “s issue, we propose a principle strategy to progressively mine discriminative polyp regions through an erasing foreground object manner [27,4]. Instead of aggregating features from all levels like in [4,13,36,33], we propose to adaptively learn the reverse attention in three parallel high-level feat”
CPFNet: Context Pyramid Fusion Network for Medical Image Segmentation (2020, methodology): “U-Net [7], Attention U-Net [21], FastFCN [17], CE-Net [26], GCN [20], DFN [19] and MultiResUNet (result as reported in [2]).”
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation (2021, background): “Some studies have tried to address this problem by using atrous convolutional layers [10,11], self-attention mechanisms [12,13], and image pyramids [14].”
Medical Image Segmentation via Cascaded Attention Decoding (2023, methodology): “The pyramid pooling and dilated convolution [5] are also used for lesion and organ segmentation [12, 11].”
MA-Net: A Multi-Scale Attention Network for Liver and Tumor Segmentation (2020, methodology): “…skip connections to fuse different-level semantic features, other state-of-the-art methods based on FCNs architecture have been proposed to capture Multi-scale context feature information of image via using dilated convolutions with different sampling rate [8]–[10] and pooling operations [11]–[14].”
MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing (2021, neutral): “CE-Net [36] mainly consists of three parts: a ResNet encoder, a context extractor and a decoder module.”
MISSFormer: An Effective Medical Image Segmentation Transformer (2021, background): “Gu et al. 2019; Feng et al. 2020).”
Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey (2020, positive): “The output of medical image segmentation is a collection of medical segments covering the whole medical image (Gu et al., 2019).”
Medical Image Segmentation Using Deep Learning: A Survey (2020, methodology): “Inspired by the SPP, a multiscale information extraction block is designed and named residual multi-kernel pooling (RMP) [75] that uses four”
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model (2022, methodology): “In the table, ResUnet [11] and BEAL [18] are proposed for optic disc/cup segmentation, TransBTS [3] and EnsemDiff [19] are proposed for the brain tumor segmentation, MTSeg [20] and UltraUNet [21] are proposed for the Thyroid Nodule segmentation, CENet [22], MRNet [1], SegNet [23], nnUNet [24] and Tr”
MISSFormer: An Effective Transformer for 2D Medical Image Segmentation (2022, methodology): “To overcome the limitation, a type of method uses dilated convolution [9], [10] and pyramid pooling [11] to enlarge the receptive ﬁeld as much as possible, and another type [12], [13] tries to employ few self-attention layers in high-level semantic feature maps, due to the quadratic relationship…”
U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation (2024, background): “The CE-Net [20] further integrates a contextual information encoding module, enhancing the model’s receptive field and semantic representation capabilities.”
Multistage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images (2020, neutral): “223 CE-Net [9] ResNet34 92.”
UNETR: Transformers for 3D Medical Image Segmentation (2021, methodology): “Several efforts have used atrous convolutional layers [9, 27, 18] to enlarge the”