Glaucoma classification based on scanning laser ophthalmoscopic images using a deep learning ensemble method

• Published in: PloS one Vol. 16; no. 6; p. e0252339
• Main Authors: Sułot, Dominika, Alonso-Caneiro, David, Ksieniewicz, Paweł, Krzyzanowska-Berkowska, Patrycja, Iskander, D. Robert
• Format: Journal Article
• Language: English
• Published: San Francisco, CA USA Public Library of Science 04.06.2021; Public Library of Science (PLoS)
• Subjects: Biology and Life Sciences; Computer and Information Sciences; Engineering and Technology; Evaluation; Glaucoma; Identification and classification; Machine learning; Medicine and Health Sciences; Research and Analysis Methods; Scanning devices; Social Sciences; Poland
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0252339

This study aimed to assess the utility of optic nerve head ( onh ) en-face images, captured with scanning laser ophthalmoscopy ( slo ) during standard optical coherence tomography ( oct ) imaging of the posterior segment, and demonstrate the potential of deep learning ( dl ) ensemble method that operates in a low data regime to differentiate glaucoma patients from healthy controls. The two groups of subjects were initially categorized based on a range of clinical tests including measurements of intraocular pressure, visual fields, oct derived retinal nerve fiber layer ( rnfl ) thickness and dilated stereoscopic examination of onh . 227 slo images of 227 subjects (105 glaucoma patients and 122 controls) were used. A new task-specific convolutional neural network architecture was developed for slo image-based classification. To benchmark the results of the proposed method, a range of classifiers were tested including five machine learning methods to classify glaucoma based on rnfl thickness—a well-known biomarker in glaucoma diagnostics, ensemble classifier based on inception v3 architecture, and classifiers based on features extracted from the image. The study shows that cross-validation dl ensemble based on slo images achieved a good discrimination performance with up to 0.962 of balanced accuracy, outperforming all of the other tested classifiers.