 Stargardt disease is a rare genetic disorder that causes progressive vision loss in children and young adults. It is caused by mutations in the ABCA4 gene, which leads to a build-up of lipophusin in the retina. A new study has shown that spectral domain optical coherence tomography, STOCT, a non-invasive imaging technique, can be used to detect early signs of stargardt disease. The researchers developed a deep learning algorithm that uses multiple layers of OCT data to predict the severity of the disease. The algorithm was able to achieve higher accuracy than existing methods, suggesting that it could be used as a diagnostic tool for stargardt disease. This article was authored by Zubin Mishra, Zuhun Wang, Srinivas Arsada, and others.