Improved fully convolutional neuron networks on small retinal vessel segmentation using local phase as attention

Xihe Kuang; Xiayu Xu; Leyuan Fang; Ehsan Kozegar; Huachao Chen; Yue Sun; Fan Huang; Tao Tan

doi:10.3389/fmed.2023.1038534

Improved fully convolutional neuron networks on small retinal vessel segmentation using local phase as attention

Front Med (Lausanne). 2023 Mar 1:10:1038534. doi: 10.3389/fmed.2023.1038534. eCollection 2023.

Authors

Xihe Kuang¹, Xiayu Xu², Leyuan Fang³, Ehsan Kozegar⁴, Huachao Chen⁵, Yue Sun⁶, Fan Huang¹, Tao Tan^{5

6}

Affiliations

¹ The University of Hong Kong, Pokfulam, Hong Kong SAR, China.
² The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi, China.
³ College of Electrical and Information Engineering, Hunan University, Changsha, Hunan, China.
⁴ Faculty of Technology and Engineering (East of Guilan), University of Guilan, Rudsar-Vajargah, Guilan, Iran.
⁵ Faculty of Applied Sciences, Macao Polytechnic University, Macau, Macao SAR, China.
⁶ Electrical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands.

Abstract

Retinal images have been proven significant in diagnosing multiple diseases such as diabetes, glaucoma, and hypertension. Retinal vessel segmentation is crucial for the quantitative analysis of retinal images. However, current methods mainly concentrate on the segmentation performance of overall retinal vessel structures. The small vessels do not receive enough attention due to their small percentage in the full retinal images. Small retinal vessels are much more sensitive to the blood circulation system and have great significance in the early diagnosis and warning of various diseases. This paper combined two unsupervised methods, local phase congruency (LPC) and orientation scores (OS), with a deep learning network based on the U-Net as attention. And we proposed the U-Net using local phase congruency and orientation scores (UN-LPCOS), which showed a remarkable ability to identify and segment small retinal vessels. A new metric called sensitivity on a small ship (Se_sv ) was also proposed to evaluate the methods' performance on the small vessel segmentation. Our strategy was validated on both the DRIVE dataset and the data from Maastricht Study and achieved outstanding segmentation performance on both the overall vessel structure and small vessels.

Keywords: local phase; orientation scores; retinal vessel; segmentation; unsupervised enhancement.