Gated Skip-Connection Network with Adaptive Upsampling for Retinal Vessel Segmentation
| Autor: | Huixia Yao, Shengxin Tao, Yun Jiang, Jing Liang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Fundus Oculi
Computer science Connection (vector bundle) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Bilinear interpolation TP1-1185 Biochemistry Article Analytical Chemistry Upsampling deep convolutional neural work retinal vessel segmentation adaptive upsampling Image Processing Computer-Assisted Segmentation Computer vision Electrical and Electronic Engineering Instrumentation skip-connection business.industry Chemical technology Retinal Vessels Atomic and Molecular Physics and Optics Feature (computer vision) Path (graph theory) gating mechanism Neural Networks Computer Artificial intelligence business Encoder Algorithms Decoding methods |
| Zdroj: | Sensors, Vol 21, Iss 6177, p 6177 (2021) Sensors (Basel, Switzerland) Sensors Volume 21 Issue 18 |
| ISSN: | 1424-8220 |
| Popis: | Segmentation of retinal vessels is a critical step for the diagnosis of some fundus diseases. Methods: To further enhance the performance of vessel segmentation, we propose a method based on a gated skip-connection network with adaptive upsampling (GSAU-Net). In GSAU-Net, a novel skip-connection with gating is first utilized in the extension path, which facilitates the flow of information from the encoder to the decoder. Specifically, we used the gated skip-connection between the encoder and decoder to gate the lower-level information from the encoder. In the decoding phase, we used an adaptive upsampling to replace the bilinear interpolation, which recovers feature maps from the decoder to obtain the pixelwise prediction. Finally, we validated our method on the DRIVE, CHASE, and STARE datasets. Results: The experimental results showed that our proposed method outperformed some existing methods, such as DeepVessel, AG-Net, and IterNet, in terms of accuracy, F-measure, and AUCROC. The proposed method achieved a vessel segmentation F-measure of 83.13%, 81.40%, and 84.84% on the DRIVE, CHASE, and STARE datasets, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|