Deep Neural Network-Based Method for Detecting Obstructive Meibomian Gland Dysfunction With in Vivo Laser Confocal Microscopy
Deep Neural Network-Based Method for Detecting Obstructive Meibomian Gland Dysfunction With in Vivo Laser Confocal Microscopy
复制标题
DOI：
10.1097/ico.0000000000002279
复制
发表时间：
2020-06-01
期刊：
影响因子：
2.8
通讯作者：
Katakami, Chikako
中科院分区：
文献类型：
--
作者：
Maruoka, Sachiko;Tabuchi, Hitoshi;Katakami, Chikako
目的：评价深度学习（DL）模型在体内激光共聚焦显微镜图像检测阻塞性睑板腺功能障碍（MGD）的能力。方法：在这项研究中，我们纳入了137张来自137名梗阻性MGD患者的图像（平均年龄49.9 +/- 17.7岁，男性44人，女性93人）和84张来自84名睑板腺正常患者的图像（平均年龄53.3 +/- 19.6岁，男性29人，女性55人）。我们构建并训练了9种不同的网络结构，并使用单个和集合DL模型，计算曲线下面积、灵敏度和特异性来比较DL的诊断能力。结果：对于单一DL模型（最高模型；DenseNet-201），诊断阻塞性MGD的曲线下面积、灵敏度和特异性分别为0.966%、94.2%和82.1%；对于整体DL模型（最高模型；VGG16、DenseNet-169、DenseNet-201和InceptionV3），诊断阻塞性MGD的曲线下面积、灵敏度和特异性分别为0.981%、92.1%和98.8%。结论：我们的网络结合了DL和体内激光共聚焦显微镜，学会了区分健康的睑板腺图像和阻塞性MGD图像，准确度很高，这可能会在未来对患者进行阻塞性MGD的自动诊断。
Purpose: To evaluate the ability of deep learning (DL) models to detect obstructive meibomian gland dysfunction (MGD) using in vivo laser confocal microscopy images. Methods: For this study, we included 137 images from 137 individuals with obstructive MGD (mean age, 49.9 +/- 17.7 years; 44 men and 93 women) and 84 images from 84 individuals with normal meibomian glands (mean age, 53.3 +/- 19.6 years; 29 men and 55 women). We constructed and trained 9 different network structures and used single and ensemble DL models and calculated the area under the curve, sensitivity, and specificity to compare the diagnostic abilities of the DL. Results: For the single DL model (the highest model; DenseNet-201), the area under the curve, sensitivity, and specificity for diagnosing obstructive MGD were 0.966%, 94.2%, and 82.1%, respectively, and for the ensemble DL model (the highest ensemble model; VGG16, DenseNet-169, DenseNet-201, and InceptionV3), 0.981%, 92.1%, and 98.8%, respectively. Conclusions: Our network combining DL and in vivo laser confocal microscopy learned to differentiate between images of healthy meibomian glands and images of obstructive MGD with a high level of accuracy that may allow for automatic obstructive MGD diagnoses in patients in the future.