Optical coherence tomography has revolutionized ocular imaging, transforming the way ocular tissue can be imaged in an in vivo manner. In a similar manner, deep learning has emerged as a powerful tool disrupting the field of medical image analysis. Lessons learned from applying deep learning techniques to ocular OCT image analysis will be covered, exploring the challenges encountered during the development and implementation of deep learning models for OCT images, including the need for large annotated datasets, model selection, and generalizability across different patient populations and imaging devices. A number of exciting future directions in deep learning-based OCT image analysis will be highlighted, such as generative adversarial networks, that hold promise for improving the accuracy and efficiency of disease detection, segmentation, and classification tasks. This overview of deep learning techniques should allow for a better understanding of the potential and future that these techniques can have to inform the decision-making of clinicians and researchers, and more importantly, improve patient care
About the speaker
He is a Senior Lecturer at the School of Science, Technology, and Engineering at the University of the Sunshine Coast
