Kako Najdavan A, Abdulazeez Adnan M, Abdulqader Diler N
Department of Information Technology, Technical College of Duhok, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq.
Department of Energy Engineering, Technical College of Engineering, Duhok Polytechnic University, Duhok, Kurdistan Region, Iraq.
Heliyon. 2024 Sep 1;10(18):e36996. doi: 10.1016/j.heliyon.2024.e36996. eCollection 2024 Sep 30.
Early diagnosis and continuous monitoring of patients with eye diseases are critical in computer-aided detection (CAD) techniques. Semantic segmentation, a key component in computer vision, enables pixel-level classification and provides detailed information about objects within images. In this study, we present three U-Net models designed for multi-class semantic segmentation, leveraging the U-Net architecture with transfer learning. To generate ground truth for the HRF dataset, we combine two U-Net models, namely MSU-Net and BU-Net, to predict probability maps for the optic disc and cup regions. Binary masks are then derived from these probability maps to extract the optic disc and cup regions from retinal images. The dataset used in this study includes pre-existing blood vessels and manually annotated peripapillary atrophy zones (alpha and beta) provided by expert ophthalmologists. This comprehensive dataset, integrating existing blood vessels and expert-marked peripapillary atrophy zones, fulfills the study's objectives. The effectiveness of the proposed approach is validated by training nine pre-trained models on the HRF dataset comprising 45 retinal images, successfully segmenting the optic disc, cup, blood vessels, and peripapillary atrophy zones (alpha and beta). The results demonstrate 87.7 % pixel accuracy, 87 % Intersection over Union (IoU), 86.9 % F1 Score, 85 % mean IoU (mIoU), and 15 % model loss, significantly contributing to the early diagnosis and monitoring of glaucoma and optic nerve disorders.
在计算机辅助检测（CAD）技术中，眼部疾病患者的早期诊断和持续监测至关重要。语义分割作为计算机视觉中的关键组成部分，能够实现像素级分类，并提供图像中物体的详细信息。在本研究中，我们提出了三种用于多类语义分割的U-Net模型，利用U-Net架构结合迁移学习。为了生成HRF数据集的真值，我们结合了两个U-Net模型，即MSU-Net和BU-Net，来预测视盘和视杯区域的概率图。然后从这些概率图中导出二值掩码，以从视网膜图像中提取视盘和视杯区域。本研究中使用的数据集包括预先存在的血管以及由眼科专家手动标注的视乳头周围萎缩区域（α和β）。这个综合了现有血管和专家标记的视乳头周围萎缩区域的数据集实现了本研究的目标。通过在包含45张视网膜图像的HRF数据集上训练九个预训练模型，成功分割视盘、视杯、血管和视乳头周围萎缩区域（α和β），验证了所提方法的有效性。结果显示像素准确率为87.7%、交并比（IoU）为87%、F1分数为86.9%、平均交并比（mIoU）为85%以及模型损失为15%，这对青光眼和视神经疾病的早期诊断和监测有显著贡献。
