用于眼前节图像中翼状胬肉检测的卷积神经网络架构性能评估
A Performance Evaluation of Convolutional Neural Network Architectures for Pterygium Detection in Anterior Segment Eye Images.
作者信息
Moreno-Lozano Maria Isabel, Ticlavilca-Inche Edward Jordy, Castañeda Pedro, Wong-Durand Sandra, Mauricio David, Oñate-Andino Alejandra
机构信息
Information Systems Engineering Faculty, Universidad Peruana de Ciencias Aplicadas, Lima 15023, Peru.
Software Engineering Faculty, Universidad Peruana de Ciencias Aplicadas, Lima 15023, Peru.
出版信息
Diagnostics (Basel). 2024 Sep 13;14(18):2026. doi: 10.3390/diagnostics14182026.
In this article, various convolutional neural network (CNN) architectures for the detection of pterygium in the anterior segment of the eye are explored and compared. Five CNN architectures (ResNet101, ResNext101, Se-ResNext50, ResNext50, and MobileNet V2) are evaluated with the objective of identifying one that surpasses the precision and diagnostic efficacy of the current existing solutions. The results show that the Se-ResNext50 architecture offers the best overall performance in terms of precision, recall, and accuracy, with values of 93%, 92%, and 92%, respectively, for these metrics. These results demonstrate its potential to enhance diagnostic tools in ophthalmology.
在本文中，对用于检测眼前节翼状胬肉的各种卷积神经网络（CNN）架构进行了探索和比较。评估了五种CNN架构（ResNet101、ResNext101、Se-ResNext50、ResNext50和MobileNet V2），目的是确定一种超过现有解决方案的精度和诊断效能的架构。结果表明，Se-ResNext50架构在精度、召回率和准确率方面提供了最佳的整体性能，这些指标的值分别为93%、92%和92%。这些结果证明了其在增强眼科诊断工具方面的潜力。
Zotero 插件