Computational Ophthalmology

Our Goal

The principal goal of our computational ophthalmology group is to make high-performance computing resources easily accessible and provide state-of-the-art, custom software available to vision researchers engaged in cellular, animal, and human vision research studies. In particular, availability of structural imaging instruments such as spectral domain and swept source optical coherence tomography (OCT) and OCT angiography has dramatically increased the size and scale of data collected in ophthalmology, in both research and clinical settings. Improving our understanding of the histopathology of major eye diseases including glaucoma, age-related macular degeneration, and diabetic retinopathy requires software tools that aid researchers in managing and processing large-scale image datasets. To this end, we have developed tools to automatically analyze and extract relevant information from OCT images.

Members of Our Computational Ophthalmology Group

Contact

For more information about our Computational Ophthalmology Group, contact viscorecompute@ucsd.edu.

Software Tools

The software tools developed by the Computational Ophthalmology group use novel Bayesian, machine learning and deep learning strategies to support computational analyses of both basic science and clinical vision research projects.

San Diego Automated Layer Segmentation Algorithm (SALSA©)

San Diego Automated Layer Segmentation Algorithm (SALSA) is a custom algorithm that takes raw OCT volumes as input and generates retinal layer segmentation. SALSA not only accurately segments retinal layers that are usually provided with instrument software (such as nerve fiber and ganglion cell layers), but also provides measurements that are not routinely provided by instrument software, but are of interest to vision researchers. This includes the choroid, anterior lamina surface, minimum rim width, and beta peripapillary atrophy with intact Bruch’s membrane.

Citations

If you use SALSA in your research, please cite these publications.

The following citations describe the SALSA algorithm in more detail:

Belghith A, Bowd C, Medeiros F, Weinreb R, Zangwill L. Automated segmentation of anterior lamina cribrosa surface: how the lamina cribrosa responds to intraocular pressure change in glaucoma eyes? 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI). 2015; 222–225
Belghith A, Bowd C, Medeiros FA, et al. Does the Location of Bruch’s Membrane Opening Change Over Time? Longitudinal Analysis Using San Diego Automated Layer Segmentation Algorithm (SALSA). Investigative Ophthalmology & Visual Science. 2016;57(2):675-682.

Download SALSA

Here, academic researchers and non-commercial institutions can download a pre-compiled, executable version (Mac and Linux) SALSA to segment the retinal nerve fiber layer from raw OCT volumes.