Abstract：
OBJECTIVE: Optical coherence tomography (OCT) investigations have revealed that the thickness of inner retinal layers becomes decreased in multiple sclerosis (MS) patients, compared to healthy control (HC) individuals. To date, a number of studies have applied machine learning to OCT thickness measurements, aiming to enable accurate and automated diagnosis of the disease. However, there have much less emphasis on other less common retinal imaging modalities, like infrared scanning laser ophthalmoscopy (IR-SLO), for classifying MS. IR-SLO uses laser light to capture high-resolution fundus images, often performed in conjunction with OCT to lock B-scans at a fixed position.
METHODS: We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).
RESULTS: The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).
CONCLUSIONS: We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice.
METHODS: We incorporated two independent datasets of IR-SLO images from the Isfahan and Johns Hopkins centers, consisting of 164 MS and 150 HC images. A subject-wise data splitting approach was employed to ensure that there was no leakage between training and test datasets. Several state-of-the-art convolutional neural networks (CNNs), including VGG-16, VGG-19, ResNet-50, and InceptionV3, and a CNN with a custom architecture were employed. In the next step, we designed a convolutional autoencoder (CAE) to extract semantic features subsequently given as inputs to four conventional ML classifiers, including support vector machine (SVM), k-nearest neighbor (K-NN), random forest (RF), and multi-layer perceptron (MLP).
RESULTS: The custom CNN (85 % accuracy, 85 % sensitivity, 87 % specificity, 93 % area under the receiver operating characteristics [AUROC], and 94 % area under the precision-recall curve [AUPRC]) outperformed state-of-the-art models (84 % accuracy, 83 % sensitivity, 87 % specificity, 92 % AUROC, and 94 % AUPRC); however, utilizing a combination of the CAE and MLP yields even superior results (88 % accuracy, 86 % sensitivity, 91 % specificity, 94 % AUROC, and 95 % AUPRC).
CONCLUSIONS: We utilized IR-SLO images to differentiate between MS and HC eyes, with promising results achieved using a combination of CAE and MLP. Future multi-center studies involving more heterogenous data are necessary to assess the feasibility of integrating IR-SLO images into routine clinical practice.
摘要：
目的：光学相干断层扫描（OCT）研究表明，多发性硬化症（MS）患者的视网膜内层厚度减少，与健康对照（HC）个体相比。迄今为止,许多研究已经将机器学习应用于OCT厚度测量，旨在实现疾病的准确和自动化诊断。然而,对其他不太常见的视网膜成像模式的重视程度要低得多，如红外扫描激光检眼镜（IR-SLO），用于对MS进行分类IR-SLO使用激光捕获高分辨率眼底图像，通常与OCT一起执行，以将B扫描锁定在固定位置。
方法：我们合并了来自伊斯法罕和约翰霍普金斯大学中心的两个独立的IR-SLO图像数据集，由164MS和150HC图像组成。采用主题数据拆分方法来确保训练和测试数据集之间没有泄漏。几个最先进的卷积神经网络(CNN)，包括VGG-16，VGG-19，ResNet-50和InceptionV3，以及具有自定义体系结构的CNN。下一步,我们设计了一个卷积自动编码器（CAE）来提取语义特征，随后作为四个传统ML分类器的输入，包括支持向量机(SVM)，k-最近邻(K-NN)，随机森林(RF)，和多层感知器(MLP)。
结果：自定义CNN(85%的准确率，85%灵敏度,87%的特异性，93%的接收机工作特性下面积[AUROC]，准确率-召回曲线下94%的面积[AUPRC])优于最先进的模型(84%的准确率，83%灵敏度,87%的特异性，92%AUROC,和94%AUPRC)；然而，利用CAE和MLP的组合可产生更出色的结果(88%的准确度，86%灵敏度,91%特异性，94%AUROC,和95%AUPRC）。
结论：我们利用IR-SLO图像来区分MS和HC眼，使用CAE和MLP的组合取得了有希望的结果。未来涉及更多异质性数据的多中心研究对于评估将IR-SLO图像整合到常规临床实践中的可行性是必要的。
方法：我们合并了来自伊斯法罕和约翰霍普金斯大学中心的两个独立的IR-SLO图像数据集，由164MS和150HC图像组成。采用主题数据拆分方法来确保训练和测试数据集之间没有泄漏。几个最先进的卷积神经网络(CNN)，包括VGG-16，VGG-19，ResNet-50和InceptionV3，以及具有自定义体系结构的CNN。下一步,我们设计了一个卷积自动编码器（CAE）来提取语义特征，随后作为四个传统ML分类器的输入，包括支持向量机(SVM)，k-最近邻(K-NN)，随机森林(RF)，和多层感知器(MLP)。
结果：自定义CNN(85%的准确率，85%灵敏度,87%的特异性，93%的接收机工作特性下面积[AUROC]，准确率-召回曲线下94%的面积[AUPRC])优于最先进的模型(84%的准确率，83%灵敏度,87%的特异性，92%AUROC,和94%AUPRC)；然而，利用CAE和MLP的组合可产生更出色的结果(88%的准确度，86%灵敏度,91%特异性，94%AUROC,和95%AUPRC）。
结论：我们利用IR-SLO图像来区分MS和HC眼，使用CAE和MLP的组合取得了有希望的结果。未来涉及更多异质性数据的多中心研究对于评估将IR-SLO图像整合到常规临床实践中的可行性是必要的。
