Evolving the structure of Hidden Markov models for micro aneurysms detection

Abstract

Micro aneurysms are one of the first visible clinical signs of diabetic retinopathy and their detection can help diagnose the progression of the disease. In this paper, a novel technique based on Genetic Algorithms is used to evolve the structure of the Hidden Markov Models to obtain an optimised model that indicates the presence of micro aneurysms located in a sub-region. This technique not only identifies the optimal number of states, but also determines the topology of the Hidden Markov Model, along with the initial model parameters.