Department of Technology and Design Thinking for Medicine, Hiroshima University, Hiroshima, Japan.
Department of Ophthalmology, Saneikai Tsukazaki Hospital, 68-1 Waku, Aboshi-ku, Himeji City, Hyogo, 671-1227, Japan.
Graefes Arch Clin Exp Ophthalmol. 2022 Apr;260(4):1329-1335. doi: 10.1007/s00417-021-05475-8. Epub 2021 Nov 4.
To assess the performance of artificial intelligence in the automated classification of images taken with a tablet device of patients with blepharoptosis and subjects with normal eyelid.
This is a prospective and observational study. A total of 1276 eyelid images (624 images from 347 blepharoptosis cases and 652 images from 367 normal controls) from 606 participants were analyzed. In order to obtain a sufficient number of images for analysis, 1 to 4 eyelid images were obtained from each participant. We developed a model by fully retraining the pre-trained MobileNetV2 convolutional neural network. Subsequently, we verified whether the automatic diagnosis of blepharoptosis was possible using the images. In addition, we visualized how the model captured the features of the test data with Score-CAM. k-fold cross-validation (k = 5) was adopted for splitting the training and validation. Sensitivity, specificity, and the area under the curve (AUC) of the receiver operating characteristic curve for detecting blepharoptosis were examined.
We found the model had a sensitivity of 83.0% (95% confidence interval [CI], 79.8-85.9) and a specificity of 82.5% (95% CI, 79.4-85.4). The accuracy of the validation data was 82.8%, and the AUC was 0.900 (95% CI, 0.882-0.917).
Artificial intelligence was able to classify with high accuracy images of blepharoptosis and normal eyelids taken using a tablet device. Thus, the diagnosis of blepharoptosis with a tablet device is possible at a high level of accuracy.
Date of registration: 2021-06-25.
UMIN000044660. Registration site: https://upload.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000051004.
评估人工智能在使用平板电脑设备对眼睑下垂患者和正常眼睑患者的图像进行自动分类方面的性能。
这是一项前瞻性和观察性研究。共分析了 606 名参与者的 1276 张眼睑图像（347 例眼睑下垂病例的 624 张图像和 367 例正常对照组的 652 张图像）。为了获得足够数量的分析图像，每个参与者获得 1 到 4 张眼睑图像。我们通过完全重新训练预先训练的 MobileNetV2 卷积神经网络来开发模型。随后，我们验证了使用这些图像是否可以自动诊断眼睑下垂。此外，我们使用 Score-CAM 可视化模型如何捕获测试数据的特征。采用 k 折交叉验证（k=5）将训练和验证数据分开。检查检测眼睑下垂的接收器工作特征曲线的灵敏度、特异性和曲线下面积（AUC）。
我们发现该模型的灵敏度为 83.0%（95%置信区间[CI]，79.8-85.9），特异性为 82.5%（95% CI，79.4-85.4）。验证数据的准确率为 82.8%，AUC 为 0.900（95% CI，0.882-0.917）。
人工智能能够对使用平板电脑设备拍摄的眼睑下垂和正常眼睑的图像进行高精度分类。因此，使用平板电脑设备诊断眼睑下垂可以达到很高的准确率。
注册日期：2021 年 6 月 25 日。
UMIN000044660。注册地点：https://upload.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000051004。
