CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging

  title={CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging},
  author={Lei Mou and Yitian Zhao and H. Fu and Yonghuai Liu and Jun Cheng and Yalin Zheng and Pan Su and Jianlong Yang and L. Chen and Alejandro F Frangi and Masahiro Akiba and Jiang Liu},
  journal={Medical image analysis},

MDANet: Multi-Direction Attention Network for Curvilinear Structure Segmentation of Biomedical Images

A Multi-Direction Attention (MDA) mechanism to learn adequate multi-direction spatial attention and channel attention information and a novel deep model, MDANet, for curvilinear structure segmentation is designed.

Curvilinear object segmentation in medical images based on ODoS filter and deep learning network

A new approach that incorporates the ODoS filter as part of a deep learning network is presented to improve the spatial attention of curvilinear objects and has yielded surprising results compared with some state-of-the-art methods.

DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation

DTU-Net is presented, a data-driven approach to topology-preserving curvilinear structure segmentation that outperforms existing approaches in both pixel-wise segmentation accuracy and topological continuity, with no need for prior topological knowledge.

IterMiUnet: A lightweight architecture for automatic blood vessel segmentation

This paper proposes IterMiUnet, a new lightweight convolution-based segmentation model that requires significantly fewer parameters and yet delivers performance similar to existing models, and has a lot of potential to be utilized as a tool for the early diagnosis of many diseases.

Local Intensity Order Transformation for Robust Curvilinear Object Segmentation

This paper aims to improve the generalizability of deep learning-based methods by introducing a novel local intensity order transformation (LIOT), which transfers a gray-scale image into a contrast-invariant four-channel image based on the intensity order between each pixel and its nearby pixels along with the four (horizontal and vertical) directions.

Multi-scale feature pyramid fusion network for medical image segmentation

Experimental results show that both the MSAM and SFPM techniques proposed in this paper can assist the network to improve the segmentation effect, so that the proposed MS-Net method achieves better results in the CHAOS, Lung and ISIC 2018 segmentation tasks.

A Multilevel Remote Relational Modeling Network for Accurate Segmentation of Fundus Blood Vessels

A novel multilevel remote relational modeling network (MRRM-Net) is proposed, which can balance global/local long-range contextual relations through building multidimensional and multileVEL attention and has more robust data adaptability than other state-of-the-art network structures in a small capacity.

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation

A novelAFN is presented which adopts a contrast-insensitive approach based on multiscale affinity to jointly model topology and pixel-wise segmentation features that outperforms the state-of-the-art methods in terms of both higher accuracy and topological metrics, and meanwhile is more robust to various contrast changes than existing methods.



CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation

This work proposes a general unifying curvilinear structure segmentation network that works on different medical imaging modalities: optical coherence tomography angiography, color fundus image, and corneal confocal microscopy, and instead of the U-Net based convolutional neural network, a novel network which includes a self-attention mechanism in the encoder and decoder.

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

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.

Multi-level deep supervised networks for retinal vessel segmentation

  • Juan MoLei Zhang
  • Medicine, Computer Science
    International Journal of Computer Assisted Radiology and Surgery
  • 2017
The proposed approach segments retinal vessels accurately with a much faster processing speed and can be easily applied to other biomedical segmentation tasks, making it suitable for real-world clinical applications.

DUNet: A deformable network for retinal vessel segmentation

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

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

Deep Vessel Segmentation By Learning Graphical Connectivity

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.

Cerebrovascular Network Segmentation of MRA Images With Deep Learning

This work presents a convolutional neural network approach for segmentation of the cerebrovascular structure from magnetic resonance angiography inspired by the U-net 3D and by the Inception modules, entitled Uception.

Attention U-Net: Learning Where to Look for the Pancreas

A novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes is proposed to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs).