Fast and efficient retinal blood vessel segmentation method based on deep learning network

• Published in: Computerized medical imaging and graphics Vol. 90; p. 101902
• Main Authors: Boudegga, Henda, Elloumi, Yaroub, Akil, Mohamed, Hedi Bedoui, Mohamed, Kachouri, Rostom, Abdallah, Asma Ben
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2021; Elsevier Science Ltd; Elsevier
• Subjects: Automation; Blood vessels; Complexity; Computer applications; Computer Science; Convolution; Deep learning; Image Processing; Image segmentation; Medical Imaging; Neural and Evolutionary Computing; Retina; Retinal images; Retinal vessel tree; Segmentation; Deep learning; Retinal vessel tree; Segmentation
• ISSN: 0895-6111; 1879-0771
• DOI: 10.1016/j.compmedimag.2021.101902

•Propose a novel deep learning architecture for retinal blood vessel segmentation based on well-known Deep learning networks.•Based on lightweight convolution modules, in order to achieve higher segmentation performance with reduced computation requirements.•Evaluated through 4-fold cross-validation approach using both DRIVE and STARE databases.•A higher trade-off between detection rate and computation time is propounded with respect to the state-of-the-art methods. The segmentation of the retinal vascular tree presents a major step for detecting ocular pathologies. The clinical context expects higher segmentation performance with a reduced processing time. For higher accurate segmentation, several automated methods have been based on Deep Learning (DL) networks. However, the used convolutional layers bring to a higher computational complexity and so for execution times. For such need, this work presents a new DL based method for retinal vessel tree segmentation. Our main contribution consists in suggesting a new U-form DL architecture using lightweight convolution blocks in order to preserve a higher segmentation performance while reducing the computational complexity. As a second main contribution, preprocessing and data augmentation steps are proposed with respect to the retinal image and blood vessel characteristics. The proposed method is tested on DRIVE and STARE databases, which can achieve a better trade-off between the retinal blood vessel detection rate and the detection time with average accuracy of 0.978 and 0.98 in 0.59 s and 0.48 s per fundus image on GPU NVIDIA GTX 980 platforms, respectively for DRIVE and STARE database fundus images.