Deep Learning for Prediction of AMD Progression: A Pilot Study

Abstract

PURPOSE. To develop and assess a method for predicting the likelihood of converting from early/intermediate to advanced wet age-related macular degeneration (AMD) using optical coherence tomography (OCT) imaging and methods of deep learning.METHODS. Seventy-one eyes of 71 patients with confirmed early/intermediate AMD with contralateral wet AMD were imaged with OCT three times over 2 years (baseline, year 1, year 2). These eyes were divided into two groups: eyes that had not converted to wet AMD (n ¼ 40) at year 2 and those that had (n ¼ 31). Two deep convolutional neural networks (CNN) were evaluated using 5-fold cross validation on the OCT data at baseline to attempt to predict which eyes would convert to advanced AMD at year 2: (1) VGG16, a popular CNN for image recognition was fine-tuned, and (2) a novel, simplified CNN architecture was trained from scratch. Preprocessing was added in the form of a segmentation-based normalization to reduce variance in the data and improve performance. RESULTS.Our new architecture, AMDnet, with preprocessing, achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.89 at the B-scan level and 0.91 for volumes. Results for VGG16, an established CNN architecture, with preprocessing were 0.82 for B-scans/0.87 for volumes versus 0.66 for B-scans/0.69 for volumes without preprocessing. CONCLUSIONS.A CNN with layer segmentation-based preprocessing shows strong predictive power for the progression of early/intermediate AMD to advanced AMD. Use of the preprocessing was shown to improve performance regardless of the network architecture.

A 3D Deep Learning System for Detecting Referable Glaucoma Using Full OCT Macular Cube Scans

“…Considering only the raw OCT cubes by themselves ignores a great deal of spatial context, such as the location, orientation, and scale of the retina. To account for this spatial information, we first homogenized the data by extending the technique we presented in Russakoff et al 22 to 3D using automated layer segmentation software ( Fig. 2; Orion, Voxeleron).…”

Two-Stream CNN with Loose Pair Training for Multi-modal AMD Categorization

“…The majority of previous works are based on a single modality, let it be color fundus images capturing the posterior pole [1,3,2,6] or OCT images [12,9,14,13,10]. In [1], for instance, Burlina et al employ a deep convolutional neural network (CNN) pretrained on ImageNet to extract visual features from fundus images and then train a linear SVM classifier.…”

Прогнозирование Возрастной Макулярной Дегенерации На Основании Определения Функциональной Активности Рецепторов Тромбоцитов

“…1,2 , Ковальчук К.В. 1,2,4 , Зяблицев С.В. 3 Проанализированы 9 факторных признаков и выявлено 5 значимых факторов риска, тесно связанных со стадией ВМД: активность пуриновых Р2Х-, А2А-рецепторов, ФАТ-рецепторов, а также α 2 -и β 2 -адренорецепторов.…”

“…Ключевые слова: возрастная макулярная дегенерация; рецепторы тромбоцитов; модели прогнозирования прогрессирования ВМД S.Yu. Mogilevskyy 1,2 , Kh.V. Kovalchuk 1,2,4 , S.V.…”

“…Mogilevskyy 1,2 , Kh.V. Kovalchuk 1,2,4 , S.V. Ziablitsev 3 1 Shupyk National Medical Academy of Postgraduate Education of the Ministry of Health of Ukraine, Kyiv, Ukraine 2 Kyiv City Clinical Ophthalmological Hospital «Eye Microsurgery Centre», Kyiv, Ukraine 3 Bogomolets National Medical University of the Ministry of Health of Ukraine, Kyiv, Ukraine 4 Medical center "LAZER Plus", Lviv, Ukraine…”