Using shape entropy as a feature to lesion boundary segmentation with level sets

<p>Accurate lesion segmentation in retinal imagery is an area of vast research. Of the many segmentation methodsavailable very few are insensitive to topological changes on noisy surfaces. This paper presents an extension toearlier work on a novel stopping mechanism for level sets. The elementary features scheme (ELS) in [5] isextended to include shape entropy as a feature used to ’look back in time’ and find the point at which the curvebest fits the real object. We compare the proposed extension against the original algorithm for timing andaccuracy using 50 randomly selected images of exudates with a database of clinician demarcated boundaries asground truth. While this work is presented applied to medical imagery, it can be used for any applicationinvolving the segmentation of bright or dark blobs on noisy images.</p>