Weighted Res-UNet for High-Quality Retina Vessel Segmentation

By Xiao-nan Xiao, Sheng Lian, Zhiming Luo, Shaozi Li. International Conference on Information Technology in Medicine and Education, 2018

978 citations recorded by the source corpus.

Retinal vessel segmentation is a key step towards the accurate visualization, diagnosis, early treatment and surgery planning of ocular diseases. Recently, deep learning based retinal vessel segmentation methods have reached the state-of-the-art performance. Due to the extreme variations in the morphology of the vessels against the noisy background, these methods still have issues of dealing with small thin vessels, low discriminative ability at the optic disk area, etc. In this paper, we proposed a U-Net-like model with the weighted attention mechanism and the skip connection scheme for addressing these issues. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed methods.

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

View Paper: https://www.semanticscholar.org/paper/ff8b823d6f04a78bdb568a09139ef6d02111764e

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

In Ophthalmology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Customized Segment Anything Model for Medical Image Segmentation (2023, methodology): “Following U-Net, researchers de-sign multiple variants to increase the performance of medical image segmentation, including Res-UNet [35], Dense-UNet [21], U-Net++ [37], 3D-Unet [5], etc. Recently, the application of Transformer [33] in nature image also sparks the research in medical image segmenta”
SegDiff: Image Segmentation with Diffusion Probabilistic Models (2021, methodology): “Method Dice mIoU FCN [3] 28.84 28.71 U-Net [38] 79.43 65.99 U-Net++ [53] 79.49 66.04 Res-UNet [48] 79.49 66.07 A.A U-Net [46] 76.83 62.49 MedT [45] 79.55 66.17 Ours 81.59 69.00 The performance of the mIoU segmentation metric as a function of the number of iterations is presented for the three…”
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation (2021, methodology): “Following this technical route, many algorithms such as 3D U-Net [6], Res-UNet [7], U-Net++ [8] and UNet3+ [9] have been developed for image and volumetric segmentation of various medical imaging modalities.”
DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation (2021, methodology): “Convolutional neural networks (CNNs), especially encoder-decoder based U-Net [1] and its variants have demonstrated superb performance in medical image segmentation, e.g., UNet++ [2] designs a series of nested and dense skip pathways to reduce the semantic gap, Attention U-Net [4] proposes a novel a”
IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks (2019, background): “The emergence of UNet [1] leads to a new era of image segmentation in the medical domain, and has revolutionized most image segmentation tasks in relevant domain [15, 16, 17, 18, 19].”
R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network (2021, methodology): “Inspired by the residual network, Res-UNet [43] substitutes a module with residual connections for each sub-module of U-Net.”
A Review of Deep-Learning-Based Medical Image Segmentation Methods (2021, methodology): “Other U-Net Structures Res-UNet (Weighted Res-UNet) [46] and H-DenseUNet (hybrid densely connected UNet) [47] are inspired by residual connections and dense connections, respectively.”
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation (2021, methodology): “For convolutional baselines, we compare with fully convolutional network (FCN) [1], U-Net [17], U-Net++ [31] and Res-Unet [27].”