Age-related Macular Degeneration (AMD) is one of the major causes of elders’ vision losses, and therefore its early screening and treatment are the most efficient way to reduce the risk of blindness. AI-based methods based on ophthalmic images have great potential for AMD diagnosis. However, low levels of accuracy, robustness, and explainability are challenges for AI approaches to be clinically applied. Traditionally unsupervised methods (Hierarchical Clustering and K-Means) and supervised methods (SVM, VGG-16, and ResNet), are used for AI-based AMD detection using different image datasets. However, single data sources and single models are not able to reflect the real data distribution, thus leading to low accuracy and robustness. Thus, this study proposes a multi-data source fusion method and a multi-model fusion approach for detecting AMD. Based on Optical Coherence Tomography (OCT), Fundus Autofluorescence (FAF), regular color fundus photography (CFP), and Ultra-Wide field Fundus (UWF) images, the multi-data source fusion method preprocesses and enhances each type of data, extracts features using unsupervised ML models, combines and normalizes them, and learns a model using a multi-layer perception (MLP) algorithm. The multi-model fusion method builds the model using different supervised machine learning and deep learning algorithms and adopts a voting mechanism for the model selection and optimization. Findings show that the proposed methods achieve higher accuracy and robustness than the traditional methods.
Macula fovea detection is a crucial molecular biological prerequisite for screening and diagnosing macular diseases. Without early detection and proper treatment, any abnormality involving the macula may lead to blindness. However, with the ophthalmologist shortage and time-consuming artificial evaluation, neither the accuracy nor effectiveness of the diagnosis process could be guaranteed. In this project, we proposed a light-weighted deep learning model based on ultra-widefield fundus (UWF) images for macula fovea detection tasks. This study collected 2300 ultra-widefield fundus images from Shenzhen Aier Eye Hospital in China. A light-weighted method based on a U-shape network (Unet) and Fully Convolution Network (FCN) approach is implemented on 1800 (before amplifying process) training fundus images, 400 (before amplifying process) validation images, and 100 test images. Three professional ophthalmologists were invited to mark the fovea. A method from the anatomy perspective is investigated. This approach is derived from the spatial relationship between the macula fovea and optic disc center in UWF. A set of parameters of this method is set based on the experience of ophthalmologists and verified to be effective. The ultra-widefield swept-source optical coherence tomography (UWF-OCT) approach is the grounded method. Through a comparison of proposed methods, we conclude that the proposed light-weighted Unet method outperformed other methods on macula fovea detection tasks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.