KEYWORDS: Optical coherence tomography, Data modeling, Machine learning, Education and training, Deep learning, 3D modeling, Image classification, Retina, Matrices, 3D image processing
This study presents an approach to identifying retinal structural biomarkers in ophthalmology, which is essential for accurate diagnosis and effective treatment of eye diseases. We develop a multi-modal, multi-task deep learning framework that integrates supervised and semi-supervised training methods. This model effectively processes a combination of 3D Optical Coherence Tomography (OCT) images and one-dimensional clinical data. A key advancement is introducing a custom post-processing method that significantly improves the precision of biomarker detection. Our model successfully identifies six distinct biomarkers in the retina and achieves a notable macro f1-score of 71.62%, representing a substantial 14.48% improvement over the baseline performance. This advancement underscores the potential of deep learning in enhancing diagnostic accuracy and treatment efficacy in ophthalmology.
Ophthalmic Biomarkers, as an objective and quantifiable approach to identifying the ophthalmological disease process, are proven to be useful not only in assisting healthcare professionals in disease diagnosis but also in the identification of phenomena and risk factors in the early stages, which greatly contribute to disease prevention and better treatment of patients. In this study, a deep learning method is introduced to achieve simultaneous automatic recognition of six prevalent ophthalmic biomarkers in the OLIVES dataset. To enhance identification accuracy, semi-supervised learning techniques are adopted in this research and different data modalities are jointly optimized using a guided loss function. The experimental results reveal that the method reaches an F1 score of 0.70 on a test set with 3,872 images.
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.