Deep-Learning Ensembles for Skin-Lesion Segmentation, Analysis, Classification: RECOD Titans at ISIC Challenge 2018
This work addresses melanoma detection for medical imaging, but it is incremental as it applies ensemble methods to existing tasks without major breakthroughs.
The team tackled skin lesion segmentation, attribute detection, and classification in the ISIC Challenge 2018, achieving results of 0.728, 0.344, and 0.803 on official metrics, placing 56th, 14th, and 9th respectively.
This extended abstract describes the participation of RECOD Titans in parts 1 to 3 of the ISIC Challenge 2018 "Skin Lesion Analysis Towards Melanoma Detection" (MICCAI 2018). Although our team has a long experience with melanoma classification and moderate experience with lesion segmentation, the ISIC Challenge 2018 was the very first time we worked on lesion attribute detection. For each task we submitted 3 different ensemble approaches, varying combinations of models and datasets. Our best results on the official testing set, regarding the official metric of each task, were: 0.728 (segmentation), 0.344 (attribute detection) and 0.803 (classification). Those submissions reached, respectively, the 56th, 14th and 9th places.