Data-Driven Deep Supervision for Skin Lesion Classification

TL;DR

This paper introduces a novel deep neural network approach that uses data-driven deep supervision based on activation mapping and receptive field analysis to improve skin lesion classification accuracy across various datasets.

Contribution

It presents a new method for selecting deep supervision layers in neural networks based on input data analysis, enhancing feature extraction for skin lesion classification.

Findings

Improved classification accuracy across multiple datasets.

Effective deep supervision layer selection based on activation mapping.

Robust feature extraction despite imaging variations.

Abstract

Automatic classification of pigmented, non-pigmented, and depigmented non-melanocytic skin lesions have garnered lots of attention in recent years. However, imaging variations in skin texture, lesion shape, depigmentation contrast, lighting condition, etc. hinder robust feature extraction, affecting classification accuracy. In this paper, we propose a new deep neural network that exploits input data for robust feature extraction. Specifically, we analyze the convolutional network's behavior (field-of-view) to find the location of deep supervision for improved feature extraction. To achieve this, first, we perform activation mapping to generate an object mask, highlighting the input regions most critical for classification output generation. Then the network layer whose layer-wise effective receptive field matches the approximated object shape in the object mask is selected as our focus for deep supervision. Utilizing different types of convolutional feature extractors and classifiers on three melanoma detection datasets and two vitiligo detection datasets, we verify the effectiveness of our new method.