Deep Learning and Transfer Learning for Optic Disc Laterality Detection: Implications for Machine Learning in Neuro-Ophthalmology

Conclusions: Small data sets can be used to develop high-performing DL systems for semantic labeling of neuro-ophthalmology images, specifically in distinguishing between right and left optic discs, even in the presence of neuro-ophthalmological pathologies. Although this may seem like an elementary task, this study demonstrates the power of transfer learning and provides an example of a DCNN that can help curate large medical image databases for machine-learning purposes and facilitate ophthalmologist workflow by automatically labeling images according to laterality.
Source: Journal of Neuro-Ophthalmology - Category: Opthalmology Tags: Original Contribution Source Type: research