SLO-Net: Enhancing Multiple Sclerosis Diagnosis Beyond Optical Coherence Tomography Using Infrared Reflectance Scanning Laser Ophthalmoscopy Images.

Purpose: 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. Methods: 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. Results: 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). Conclusions: Incorporating both modalities improves the performance of automated diagnosis of MS, showcasing the potential of utilizing IR-SLO as a complementary tool alongside OCT. Translational Relevance: 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.

Discrimination of multiple sclerosis using scanning laser ophthalmoscopy images with autoencoder-based feature extraction.

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.

Analysis of Fundus Fluorescein Angiogram Based on the Hessian Matrix of Directional Curvelet Sub-bands and Distance Regularized Level Set Evolution.

This paper presents a new procedure for automatic extraction of the blood vessels and optic disk (OD) in fundus fluorescein angiogram (FFA). In order to extract blood vessel centerlines, the algorithm of vessel extraction starts with the analysis of directional images resulting from sub-bands of fast discrete curvelet transform (FDCT) in the similar directions and different scales. For this purpose, each directional image is processed by using information of the first order derivative and eigenvalues obtained from the Hessian matrix. The final vessel segmentation is obtained using a simple region growing algorithm iteratively, which merges centerline images with the contents of images resulting from modified top-hat transform followed by bit plane slicing. After extracting blood vessels from FFA image, candidates regions for OD are enhanced by removing blood vessels from the FFA image, using multi-structure elements morphology, and modification of FDCT coefficients. Then, canny edge detector and Hough transform are applied to the reconstructed image to extract the boundary of candidate regions. At the next step, the information of the main arc of the retinal vessels surrounding the OD region is used to extract the actual location of the OD. Finally, the OD boundary is detected by applying distance regularized level set evolution. The proposed method was tested on the FFA images from angiography unit of Isfahan Feiz Hospital, containing 70 FFA images from different diabetic retinopathy stages. The experimental results show the accuracy more than 93% for vessel segmentation and more than 87% for OD boundary extraction.