Guedri Hichem, Ben Abdallah Mariem, Echouchene Fraj, Belmabrouk Hafedh
Electronics and Microelectronics Laboratory, Physics Department, Faculty of Sciences, Monastir University, Monastir 5019, Tunisia.
Department of Physics, College of Science AlZulfi, Majmaah University, Majmaah 15341, Saudi Arabia.
Biomedicines. 2017 Mar 27;5(2):12. doi: 10.3390/biomedicines5020012.
Several clinical studies reveal the relationship between alterations in the topologies of the human retinal blood vessel, the outcrop and the disease evolution, such as diabetic retinopathy, hypertensive retinopathy, and macular degeneration. Indeed, the detection of these vascular changes always has gaps. In addition, the manual steps are slow, which may be subjected to a bias of the perceiver. However, we can overcome these troubles using computer algorithms that are quicker and more accurate. This paper presents and investigates a novel method for measuring the blood vessel diameter in the retinal image. The proposed method is based on a thresholding segmentation and thinning step, followed by the characteristic point determination step by the Douglas-Peucker algorithm. Thereafter, it uses the active contours to detect vessel contour. Finally, Heron's Formula is applied to assure the calculation of vessel diameter. The obtained results for six sample images showed that the proposed method generated less errors compared to other techniques, which confirms the high performance of the proposed method.
多项临床研究揭示了人类视网膜血管拓扑结构的改变、露头与疾病演变之间的关系，如糖尿病视网膜病变、高血压视网膜病变和黄斑变性。事实上，这些血管变化的检测总是存在差距。此外，人工步骤缓慢，可能会受到感知者偏差的影响。然而，我们可以使用更快、更准确的计算机算法来克服这些问题。本文提出并研究了一种测量视网膜图像中血管直径的新方法。所提出的方法基于阈值分割和细化步骤，随后通过道格拉斯 - 普克算法进行特征点确定步骤。此后，它使用活动轮廓来检测血管轮廓。最后，应用海伦公式来确保血管直径的计算。六个样本图像的所得结果表明，与其他技术相比，所提出的方法产生的误差更小，这证实了所提出方法的高性能。
