Image processing pipeline for the detection of blood flow through retinal vessels with subpixel accuracy in fundus images

• Published in: Computer methods and programs in biomedicine 2021-09, Vol.208, p.106240-106240, Article 106240
• Main Authors: Czepita, Maciej, Fabijańska, Anna
• Format: Article
• Language: English
• Subjects: Blood flow; Fundus image; Retinal vessel; Subpixel analysis; U-Net; Vessel diameter
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2021.106240

•Blood flow detection through the retinal vessels manifests itself as changes in vessel diameter in consecutive phases of blood flow.•This paper proposes an automated pipeline to analyze the blood flow through retinal vessels by means of convolutional neural networks used for optic nerve disc and vessel detection and full width at half maximum analysis used for vessel width assessment at the subpixel level.•Measurements of the diameter were performed at a particular distance derived from the optic nerve disc size. Blood flow was detected with high accuracy.•In contrast to previous studies, special attention was placed on the limiting resolution of the fundus camera employed and the images were taken during the different phases of the cardiac cycle.•The proposed method can have a wide range of clinical applications. Blood flow detection through the retinal vessels is an essential step in diagnosing several eye diseases. It manifests itself as changes in vessel diameter in consecutive phases of blood flow. Previous studies focused mainly on determining retinal vessel diameter by the manual demarcation of vessel edges, which is time-consuming. As a result, only a few selected vessels were considered, which is not reliable. Such measurements are also prone to human errors and operator subjectivity, which additionally decreases their reliability. For these reasons, this paper proposes an automated pipeline to analyze the blood flow through retinal vessels. Convolutional neural networks were used for optic disc and vessel detection and full width at half maximum analysis used for vessel width assessment at the subpixel level. Measurements of the diameter were performed for five phases of the blood flow to all vessels at a particular distance derived from the optic disc size. We tested the approach on fundus images of five patients, with both eyes examined in each participant. The threshold for the detections of blood flow was when the retinal diameter vessel measurements were above the camera's resolution as compared among all 5 phases of blood flow. A total of 205 large caliber blood vessels were analyzed with blood flow detected in 18 retinal blood vessels. Conclusions Average vessel diameters derived from manual and automatic measurements differed on average by 4.96%. Average relative errors for single vessel measurements along the vessels range from 4.21 to 11.85%, with a global average at the level of 8%. Therefore, the measurements can be considered as acc