Att2ResNet: A deep attention‐based approach for melanoma skin cancer classification

Abstract

This paper presents an in‐depth study on the contribution and integration of attention mechanisms into deep learning architectures for melanoma classification. Indeed, the concept of attention helps guide the learning process to focus on some parts of the input image deemed to be the most significant. Nevertheless, to the best of our knowledge, a study on how and where to integrate such mechanisms has never been conducted in the context of melanoma classification. Consequently, we propose such a study in three main stages. First, we propose an improvement in the transfer learning process for the specific case of melanoma classification. Then, we develop a basic variant of our architecture allowing to integrate an additive attention mechanism in an adapted ResNet network. We finally investigate the impact of the number of mechanisms and their location in the melanoma classification architecture. Better results are reported on two standard datasets.

Biomarker Discovery for Meta-Classification of Melanoma Metastatic Progression Using Transfer Learning

“…Nevertheless, cancer prognosis remains extremely challenging due to the high dimensionality of the data and the small number of patient samples. Several machine learning techniques have already been used as a disease classifier in melanoma but are primarily focused on images [ 11 , 12 , 13 , 14 , 15 , 16 ] and single predictive modeling approaches [ 17 , 18 , 19 ]; genomic signatures which may be more informative and accurate have not been considered. Compared to other related investigations [ 1 , 2 , 20 , 21 ], this study proposes a transfer learning approach as a biomarker discovery technique, and ensembles various classifiers that operate on different identified genomic signature subsets by soft voting.…”