Zheng Ce, Koh Victor, Bian Fang, Li Luo, Xie Xiaolin, Wang Zilei, Yang Jianlong, Chew Paul Tec Kuan, Zhang Mingzhi
Department of Ophthalmology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China, Shanghai, China.
Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Ann Transl Med. 2021 Jul;9(13):1073. doi: 10.21037/atm-20-7436.
Semi-supervised learning algorithms can leverage an unlabeled dataset when labeling is limited or expensive to obtain. In the current study, we developed and evaluated a semi-supervised generative adversarial networks (GANs) model that detects closed-angle on anterior segment optical coherence tomography (AS-OCT) images using a small labeled dataset.
In this cross-sectional study, a semi-supervised GANs model was developed for automatic closed-angle detection training on a small labeled and large unsupervised training dataset collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong (JSIEC). The closed-angle was defined as iris-trabecular contact beyond the scleral spur in AS-OCT images. We further developed two supervised deep learning (DL) models training on the same supervised dataset and the whole dataset separately. The semi-supervised GANs model and supervised DL models' performance were compared on two independent testing datasets from JSIEC (515 images) and the Department of Ophthalmology (84 images), National University Health System, respectively. The diagnostic performance was assessed by evaluation matrices, including the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).
For closed-angle detection using clinician grading of AS-OCT imaging as the reference standard, the semi-supervised GANs model showed comparable performance, with AUCs of 0.97 (95% CI, 0.96-0.99) and 0.98 (95% CI, 0.94-1.00), compared with the supervised DL model (using the whole dataset) [AUCs of 0.97 (95% CI, 0.96-0.99), and 0.97 (95% CI, 0.94-1.00)]. When training on the same small supervised dataset, the semi-supervised GANs achieved performance at least as well as, if not better than, the supervised DL model [AUCs of 0.90 (95% CI: 0.84-0.96), and 0.92 (95% CI, 0.86-0.97)].
The semi-supervised GANs method achieves diagnostic performance at least as good as a supervised DL model when trained on small labeled datasets. Further development of semi-supervised learning methods could be useful within clinical and research settings.
ChiCTR2000037892.
当标记有限或获取成本高昂时，半监督学习算法可以利用未标记数据集。在本研究中，我们开发并评估了一种半监督生成对抗网络（GAN）模型，该模型使用少量标记数据集在前节光学相干断层扫描（AS-OCT）图像上检测闭角。
在这项横断面研究中，开发了一种半监督GAN模型，用于在从汕头大学和香港中文大学联合汕头国际眼科中心（JSIEC）收集的少量标记和大量无监督训练数据集上进行自动闭角检测训练。在AS-OCT图像中，闭角定义为虹膜与小梁接触超过巩膜突。我们还分别在相同的监督数据集和整个数据集上进一步开发了两个监督深度学习（DL）模型。在分别来自JSIEC（515张图像）和新加坡国立大学医疗系统眼科（84张图像）的两个独立测试数据集上比较了半监督GAN模型和监督DL模型的性能。通过评估矩阵评估诊断性能，包括准确性、敏感性、特异性和受试者工作特征曲线下面积（AUC）。
以临床医生对AS-OCT成像的分级作为参考标准进行闭角检测时，半监督GAN模型表现出相当的性能，AUC分别为0.97（95%CI，0.96-0.99）和0.98（95%CI，0.94-1.00），与监督DL模型（使用整个数据集）相比[AUC分别为0.97（95%CI，0.96-0.99）和0.97（95%CI，0.94-1.00）]。当在相同的少量监督数据集上进行训练时，半监督GAN模型的性能至少与监督DL模型一样好，甚至可能更好[AUC分别为0.90（95%CI：0.84-0.96）和0.92（95%CI，0.86-0.97）]。
当在少量标记数据集上进行训练时，半监督GAN方法实现的诊断性能至少与监督DL模型一样好。半监督学习方法的进一步发展在临床和研究环境中可能会很有用。
ChiCTR2000037892。
