Arian Roya, Aghababaei Ali, Soltanipour Asieh, Khodabandeh Zahra, Rakhshani Sajed, Iyer Shwasa B, Ashtari Fereshteh, Rabbani Hossein, Kafieh Raheleh
Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.
School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
Transl Vis Sci Technol. 2024 Jul 1;13(7):13. doi: 10.1167/tvst.13.7.13.
Several machine learning studies have used optical coherence tomography (OCT) for multiple sclerosis (MS) classification with promising outcomes. Infrared reflectance scanning laser ophthalmoscopy (IR-SLO) captures high-resolution fundus images, commonly combined with OCT for fixed B-scan positions. However, no machine learning research has utilized IR-SLO images for automated MS diagnosis.
This study utilized a dataset comprised of IR-SLO images and OCT data from Isfahan, Iran, encompassing 32 MS and 70 healthy individuals. A number of convolutional neural networks (CNNs)-namely, VGG-16, VGG-19, ResNet-50, ResNet-101, and a custom architecture-were trained with both IR-SLO images and OCT thickness maps as two separate input datasets. The highest performing models for each modality were then integrated to create a bimodal model that receives the combination of OCT thickness maps and IR-SLO images. Subject-wise data splitting was employed to prevent data leakage among training, validation, and testing sets.
Overall, images of the 102 patients from the internal dataset were divided into test, validation, and training subsets. Subsequently, we employed a bootstrapping approach on the training data through iterative sampling with replacement. The performance of the proposed bimodal model was evaluated on the internal test dataset, demonstrating an accuracy of 92.40% ± 4.1% (95% confidence interval [CI], 83.61-98.08), sensitivity of 95.43% ± 5.75% (95% CI, 83.71-100.0), specificity of 92.82% ± 3.72% (95% CI, 81.15-96.77), area under the receiver operating characteristic (AUROC) curve of 96.99% ± 2.99% (95% CI, 86.11-99.78), and area under the precision-recall curve (AUPRC) of 97.27% ± 2.94% (95% CI, 86.83-99.83). Furthermore, to assess the model generalization ability, we examined its performance on an external test dataset following the same bootstrap methodology, achieving promising results, with accuracy of 85.43% ± 0.08% (95% CI, 71.43-100.0), sensitivity of 97.33% ± 0.06% (95% CI, 83.33-100.0), specificity of 84.6% ± 0.10% (95% CI, 71.43-100.0), AUROC curve of 99.67% ± 0.02% (95% CI, 95.63-100.0), and AUPRC of 99.65% ± 0.02% (95% CI, 94.90-100.0).
Incorporating both modalities improves the performance of automated diagnosis of MS, showcasing the potential of utilizing IR-SLO as a complementary tool alongside OCT.
Should the results of our proposed bimodal model be validated in future work with larger and more diverse datasets, diagnosis of MS based on both OCT and IR-SLO can be reliably integrated into routine clinical practice.
多项机器学习研究已将光学相干断层扫描（OCT）用于多发性硬化症（MS）分类，取得了有前景的成果。红外反射扫描激光检眼镜（IR-SLO）可采集高分辨率眼底图像，通常与OCT结合用于固定的B扫描位置。然而，尚无机器学习研究利用IR-SLO图像进行MS的自动诊断。
本研究使用了一个数据集，该数据集包含来自伊朗伊斯法罕的IR-SLO图像和OCT数据，涵盖32例MS患者和70名健康个体。多个卷积神经网络（CNN），即VGG-16、VGG-19、ResNet-50、ResNet-101和一个定制架构，分别以IR-SLO图像和OCT厚度图作为两个独立的输入数据集进行训练。然后将每种模态下表现最佳的模型进行整合，创建一个接收OCT厚度图和IR-SLO图像组合的双峰模型。采用按受试者的数据分割方法，以防止训练集、验证集和测试集之间的数据泄漏。
总体而言，内部数据集中102例患者的图像被分为测试集、验证集和训练子集。随后，我们对训练数据采用了有放回的迭代抽样的自助法。在内部测试数据集上评估了所提出的双峰模型的性能，其准确率为92.40%±4.1%（95%置信区间[CI]，83.61 - 98.08），灵敏度为95.43%±5.75%（95%CI，83.71 - 100.0），特异性为92.82%±3.72%（95%CI，81.15 - 96.77），受试者工作特征（AUROC）曲线下面积为96.99%±2.99%（95%CI，86.11 - 99.78），精确率-召回率曲线下面积（AUPRC）为97.27%±2.94%（95%CI，86.83 - 99.83）。此外，为评估模型的泛化能力，我们按照相同的自助法在外部测试数据集上检查了其性能，取得了有前景的结果，准确率为85.43%±0.08%（95%CI，71.43 - 100.0），灵敏度为97.33%±0.06%（95%CI，83.33 - 100.0），特异性为84.6%±0.10%（95%CI，71.43 - 100.0），AUROC曲线为99.67%±0.02%（95%CI，95.63 - 100.0），AUPRC为99.65%±0.02%（95%CI，94.90 - 100.0）。
结合两种模态可提高MS自动诊断的性能，显示出将IR-SLO作为OCT辅助工具的潜力。
如果我们提出的双峰模型的结果在未来使用更大、更多样化的数据集的工作中得到验证，基于OCT和IR-SLO的MS诊断可可靠地整合到常规临床实践中。
