A Robustness Study of Machine Learning Based Methods for Macula Detection in Pathological Fundus Images

The macula detection is an important step for screening retinal diseases. Several methods have been proposed for detecting macula, with the aim of achieving a higher detection performance despite retinal pathologies. Their processing principles are based on well-known anatomical criteria of macula. However, these criteria are subject to significant changes caused by various eye pathologies. Therefore, it leads to a non-performing macula detection, and hence pathology screening. The objective of this work is to study the robustness of the macula detection methods in terms of each retinal pathologies. For this purpose, the main macular criteria are extracted. Then, recent macula detection methods are detailed where the macula criteria taken into account are identified. Thereafter, the retinal pathologies that affect the macula are listed where caused macula changes are figured out. This study allows us to synthesise the robustness of each method in terms of pathologies.