New article: Computer aided diagnosis for suspect keratoconus detection

Our lab developed a new, stable and low-cost computer aided diagnosis system for early keratoconus detection. This system combines a custom-made mathematical model, a feedforward neural network and a Grossberg-Runge Kutta architecture to detect clinical and suspect keratoconus. It is able to detect suspect keratoconus with an accuracy of 96.56%, versus an accuracy of 89.00% for Belin/Ambrosio Deviation (BADD), and an accuracy of 79.00% for Topographical Keratoconus Classification (TKC). The proposed algorithm also provides a 70% reduction in computation time, while increasing stability and convergence with respect to traditional machine learning techniques. The proposed algorithm is highly accurate and provides a stable screening platform to assist ophthalmologists with the early detection of keratoconus. This framework could potentially be set up for any Scheimpflug tomography system.

Issarti I, Consejo A, Jiménez-García M, Hershko S, Koppen C, Rozema JJ. Computer aided diagnosis for suspect keratoconus detection. Comp Biol Med. 2019;109:33-42.