Segmentation of retinal blood vessels in fundus images is critical for early detection and treatment of diabetic retinopathy(DR). Due to the complex distribution of blood vessels, variations in noise, illumination, and vessel orientation in fundus images, the segmentation process becomes extremely challenging and time-consuming. In recent years, deep learning(DL)-based methods have been recognized as promising strategies for automatic retinal blood vessel segmentation that aids in early treatment, but most earlier DL algorithms prioritized accuracy over the complexity of the model for segmenting retinal vessels, making them challenging to adapt to medical devices. To the best of our knowledge, this is the first work to present a novel hybrid evolutionary weighted ensemble of three deep transfer learning(DTL) models: ResNet34, Inception V3, and VGG16 utilizing two public retinal fundus databases: DRIVE, and HRF for retinal blood vessel segmentation and latter detecting DR using Resnet34+Unet. Among comparing single models, Resnet34+-Net achieved impressive accuracy of 0.9575, F1 and IOU scores of 0.8421 and 0.8159, and AUC values of 0.9868 in the DRIVE dataset. In comparison to the state-of-the-art results for segmenting retinal blood vessels using DRIVE and HRF datasets, our proposed approach achieves 0.9853 and 0.9816 accuracy, 0.9881 and 0.9833 precision, 0.9853 and 0.9828 recall, 0.8791 and 0.8497 F1 scores, 0.8066 and 0.7754 IOU scores, and AUC of 0.9996 and 0.9928 respectively, with a rise of nearly 7–8 % and for classification, Resnet34+Unet achieves an accuracy= 0.996, precision= 0.993, recall= 1, and AUC= 0.999 respectively. Hence, the proposed model shows good potential for real-time diagnosis.

中文翻译：

---

用于视网膜血管分割和糖尿病视网膜病变检测的深度迁移学习模型的混合进化加权集成

眼底图像中视网膜血管的分割对于糖尿病视网膜病变（DR）的早期发现和治疗至关重要。由于眼底图像中血管的复杂分布、噪声、照明和血管方向的变化，分割过程变得极具挑战性和耗时。近年来，基于深度学习（DL）的方法被认为是有前途的自动视网膜血管分割策略，有助于早期治疗，但大多数早期的深度学习算法优先考虑视网膜血管分割模型的准确性，而不是复杂性，这使得它们适应医疗设备具有挑战性。据我们所知，这是第一篇利用两个公共视网膜眼底数据库：DRIVE 和 HRF 来提出一种新颖的混合进化加权集成的三个深度迁移学习（DTL）模型：ResNet34、Inception V3 和 VGG16血管分割，后期使用Resnet34+Unet检测DR。在比较单个模型时，Resnet34+-Net 在 DRIVE 数据集中取得了 0.9575 的准确率，F1 和 IOU 分数分别为 0.8421 和 0.8159，AUC 值为 0.9868。与使用 DRIVE 和 HRF 数据集分割视网膜血管的最先进结果相比，我们提出的方法实现了 0.9853 和 0.9816 准确度、0.9881 和 0.9833 精确度、0.9853 和 0.9828 召回率、0.8791 和 0.8497 F1 分数、0.8066 和IOU 得分为 0.7754，AUC 分别为 0.9996 和 0.9928，提升了近 7-8%，对于分类，Resnet34+Unet 分别实现了准确率 = 0.996、精度 = 0.993、召回率 = 1、AUC = 0.999。因此，所提出的模型显示出实时诊断的良好潜力。