Researching | Improved Res-UNet-based vascular segmentation of retinal images

Optical Instruments, Volume. 45, Issue 4, 24(2023)

Improved Res-UNet-based vascular segmentation of retinal images

Han YANG... Baicheng LI* and Lingling CHEN* |Show fewer author(s)

Author Affiliations

School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093

show less

Abstract Get PDF(in Chinese)

Figures&Tables (7)

References (26)

Paper Information

Figures & Tables(7)

Fig. 1. Schematic diagram of the residual module

Download full size

View in Article

Fig. 2. Schematic diagram of the nonlocal attention mechanism

Download full size

View in Article

Fig. 3. Improved residual U-net

Download full size

View in Article

Fig. 4. Comparison of segmentation results

Download full size

View in Article

Fig. 5. Segmentation of partial vascular area

Download full size

View in Article

Table 1. Comparison of results from different structural segmentation methods based on U-Net
View table
View in Article
Table 1. Comparison of results from different structural segmentation methods based on U-Net
Algorithm Acc Se Sp Dice系数
A1 0.9528 0.7656 0.9804 0.8170
A2 0.9562 0.8015 0.9832 0.8197
A3 0.9586 0.8196 0.9861 0.8249
A4 0.9679 0.8245 0.9896 0.8281

Table 2. Comparison of results from different algorithms on DRIVE dataset

View in Article

Table 2. Comparison of results from different algorithms on DRIVE dataset

Algorithm	Acc	Se	Sp	Dice系数
method in Ref. [20]	0.9531	0.7642	0.9757	0.8142
method in Ref. [21]	0.9533	0.7995	0.9533	0.8208
method in Ref. [22]	0.9620	0.7763	0.9768	0.8172
method in Ref. [23]	0.9546	0.7420	0.9820	0.8237
method in Ref. [24]	0.9443	0.8053	0.9705	0.8155
method in Ref. [25]	0.9767	0.8173	0.9733	0.8269
method in Ref. [26]	0.9614	0.8095	0.9769	0.8117
method in Ref. [27]	0.9638	0.8126	0.9814	0.8202
Our method	0.9679	0.8245	0.9896	0.8281

Tools

Get Citation

Copy Citation Text

Han YANG, Baicheng LI, Lingling CHEN. Improved Res-UNet-based vascular segmentation of retinal images[J]. Optical Instruments, 2023, 45(4): 24

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: APPLICATION TECHNOLOGY

Received: Dec. 4, 2022

Accepted: --

Published Online: Sep. 26, 2023

The Author Email: LI Baicheng (baichengli2012@163.com), CHEN Lingling (baichengli2012@163.com)

DOI:10.3969/j.issn.1005-5630.2023.004.004

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology