Nejat Farhad, Eghtedari Shima, Alimoradi Fatemeh
Ophthalmic Department, Vision Health Reaserch Center, Tehran, Iran.
Electrical Department, AmirKabir University of Technology (Tehran Polytechnique), Tehran, Iran.
Ophthalmol Sci. 2024 May 6;4(5):100546. doi: 10.1016/j.xops.2024.100546. eCollection 2024 Sep-Oct.
This study aims to develop and assess an infrastructure using Python-based deep learning code for future diagnostic and management purposes related to dry eye disease (DED) utilizing smartphone images.
Cross-sectional study using data which was gathered in Vision Health Research Clinic.
One thousand twenty-one eye images from 734 patients were included in this article that categorizes into 70% females and 30% males, with no sex and age limit.
One specialist captured eye images using Samsung A71 (601 images) and iPhone 11 (420 images) cell phones with the flashlight on and direct gaze to the camera. These images include the area of only 1 eye (left/right).
First, our specialist did 3 different segmentations for every eye image separately for 80% of the training data. This part contains eye, lower eyelid, and iris segmentation. In 20% of test data after automated cropping of the lower eyelid margin and upscaling by 8×, the appropriate tear meniscus height segmentation will be chosen and measured using a deep learning algorithm.
The model was trained on 80% of the data and 20% of the data used for validation from both phones with different resolutions. The dice coefficient of the trained model for validation data is 98.68%, and the accuracy of the overall model is 95.39%.
It appears that this algorithm holds the potential to herald an evolution in the future of diagnosis and management of DED by homecare devices solely through smartphones.
The author(s) have no proprietary or commercial interest in any materials discussed in this article.
本研究旨在开发并评估一种基于Python的深度学习代码的基础设施，用于未来利用智能手机图像进行与干眼病（DED）相关的诊断和管理。
使用在视觉健康研究诊所收集的数据进行横断面研究。
本文纳入了来自734名患者的1021张眼部图像，其中女性占70%，男性占30%，无性别和年龄限制。
一名专家使用三星A71（601张图像）和iPhone 11（420张图像）手机在手电筒打开且直接注视相机的情况下拍摄眼部图像。这些图像仅包括一只眼睛（左/右）的区域。
首先，我们的专家对80%的训练数据中的每一张眼部图像分别进行3种不同的分割。这部分包括眼睛、下眼睑和虹膜分割。在对下眼睑边缘进行自动裁剪并放大8倍后的20%测试数据中，将使用深度学习算法选择并测量合适的泪液弯月面高度分割。
该模型在80%的数据上进行训练，20%的数据用于来自两部不同分辨率手机的验证。训练模型对验证数据的骰子系数为98.68%，整体模型的准确率为95.39%。
看来这种算法有可能预示着未来仅通过智能手机的家庭护理设备对干眼病进行诊断和管理的变革。
作者对本文中讨论的任何材料均无专有或商业利益。
