School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou 310053, China.
Comput Math Methods Med. 2022 Mar 26;2022:3117455. doi: 10.1155/2022/3117455. eCollection 2022.
Extracting retinal vessels accurately is very important for diagnosing some diseases such as diabetes retinopathy, hypertension, and cardiovascular. Clinically, experienced ophthalmologists diagnose these diseases through segmenting retinal vessels manually and analysing its structural feature, such as tortuosity and diameter. However, manual segmentation of retinal vessels is a time-consuming and laborious task with strong subjectivity. The automatic segmentation technology of retinal vessels can not only reduce the burden of ophthalmologists but also effectively solve the problem that is a lack of experienced ophthalmologists in remote areas. Therefore, the automatic segmentation technology of retinal vessels is of great significance for clinical auxiliary diagnosis and treatment of ophthalmic diseases. A method using SegNet is proposed in this paper to improve the accuracy of the retinal vessel segmentation. The performance of the retinal vessel segmentation model with SegNet is evaluated on the three public datasets (DRIVE, STARE, and HRF) and achieved accuracy of 0.9518, 0.9683, and 0.9653, sensitivity of 0.7580, 0.7747, and 0.7070, specificity of 0.9804, 0.9910, and 0.9885, score of 0.7992, 0.8369, and 0.7918, MCC of 0.7749, 0.8227, and 0.7643, and AUC of 0.9750, 0.9893, and 0.9740, respectively. The experimental results showed that the method proposed in this research presented better results than many classical methods studied and may be expected to have clinical application prospects.
准确提取视网膜血管对于诊断糖尿病视网膜病变、高血压和心血管等疾病非常重要。临床上，经验丰富的眼科医生通过手动分割视网膜血管并分析其结构特征（如迂曲度和直径）来诊断这些疾病。然而，视网膜血管的手动分割是一项耗时费力且主观性很强的任务。视网膜血管的自动分割技术不仅可以减轻眼科医生的负担，还可以有效解决偏远地区缺乏经验丰富的眼科医生的问题。因此，视网膜血管的自动分割技术对于眼科疾病的临床辅助诊断和治疗具有重要意义。本文提出了一种使用 SegNet 的方法来提高视网膜血管分割的准确性。在三个公共数据集（DRIVE、STARE 和 HRF）上评估了使用 SegNet 的视网膜血管分割模型的性能，达到了 0.9518、0.9683 和 0.9653 的准确率，0.7580、0.7747 和 0.7070 的敏感度，0.9804、0.9910 和 0.9885 的特异性，0.7992、0.8369 和 0.7918 的得分，0.7749、0.8227 和 0.7643 的 MCC，0.9750、0.9893 和 0.9740 的 AUC。实验结果表明，本研究提出的方法比许多经典方法的研究结果更好，有望具有临床应用前景。
