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

By Huan Fu, Yanwu Xu, Stephen Lin, Damon Wing Kee Wong, Jiang Liu. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2016

462 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/94b43a5a4224c8c1d62f5fa3ac567de37f0c44aa

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Huan Fu
2. Changqing Zhang
3. Xiaochun Cao
4. Kwang-Ting Cheng
5. Zhiming Luo
6. Xin Yang
7. Zengqiang Yan
8. Shenghua Gao

In Ophthalmology

1. Huan Fu
2. Jiang Liu
3. Jun Cheng
4. Kwang-Ting Cheng
5. Xin Yang
6. Zengqiang Yan
7. Damon Wing Kee Wong
8. Yanwu Xu

In Radiology, Nuclear Medicine and Imaging

1. B. van Ginneken
2. Huan Fu
3. Jiang Liu
4. Jun Cheng
5. Francesco Ciompi
6. Kwang-Ting Cheng
7. Xin Yang
8. Zengqiang Yan

Citations in the corpus

• A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation (2019, background): “[32], [33] proposed to solve the vessel segmentation problem based on a fully convolutional neural network combined with a fully-connected Conditional Random Fields (CRFs).”
• Computer Methods and Programs in Biomedicine (unknown): “CNNs and Conditional Random Field (CRF) are combined into an integrated deep network called DeepVessel in [45] for retinal vessel segmentation.”
• Disc-Aware Ensemble Network for Glaucoma Screening From Fundus Image (2018, background): “For example, Convolutional Neural Networks (CNNs) learn hierarchical features from raw image data and are demonstrated to achieve a high performance on retinal vessel detection [23], [24].”
• A survey on deep learning in medical image analysis (2017, methodology): “…groups have tried to combine fCNNs with graphical models like MRFs (Shakeri et al., 2016; Song et al., 2015) and Conditional Random Fields (CRFs) (Alansary et al., 2016; Cai et al., 2016a; Christ et al., 2016; Dou et al., 2016c; Fu et al., 2016a; Gao et al., 2016c) to refine the segmentation output.”
• CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, methodology): “Sen Acc AUC Azzopardi [8] 0.7655 0.9442 0.9614 Roychowdhury [7] 0.7250 0.9520 0.9672 zhao [5] 0.7420 0.9540 0.8620 HED [74] 0.7364 0.9434 0.9723 U-Net [10] 0.7537 0.9531 0.9601 DeepVessel [4] 0.7603 0.9523 0.9752 Backbone 0.7781 0.9477 0.9705 CE-Net 0.8309 0.9545 0.9779 the official website 3 .”
• Weighted Res-UNet for High-Quality Retina Vessel Segmentation (2018, methodology): “[3] developed a multiscale and multi-level CNN model to do the segmentation and used a Conditional Random Field (CRF) to consider the long-range interactions between pixels.”