Comparing shape-based and pixel-based approaches for melanoma detection

Abstract:

In recent years, both the number and the size of image datasets have grown at an uncontrollable rate. This creates a serious challenge for the analysis of image databases, especially for researchers who may not have access to expensive and powerful supercomputers. In this research report, we study an alternative to pixel-based analysis: a functional representation of the shapes of objects within images. This representation offers several advantages. By being of much lower dimension, it greatly reduces the computational cost of subsequent analyses; it is also far more interpretable and can leverage the extensive set of tools already developed for the analysis of multivariate functional data. We investigate this shape-based approach in the context of classification using a real dataset, the HAM10000 dataset, and our results demonstrate a clear computational benefit with similar predictive power.

Ce rapport de recherche résumé le stage de maîtrise (M1) à l’UQAM de Andréa Davila.

Télécharger ici