SANet:Superpixel Attention Network for Skin Lesion Attributes Detection

TL;DR

SANet is a novel deep learning framework that enhances skin lesion attribute detection by addressing class imbalance and feature discrimination through superpixel segmentation, attention mechanisms, and a global balancing loss.

Contribution

The paper introduces SANet, a new superpixel attention network with a global balancing loss for improved lesion attribute detection in skin images.

Findings

Achieves high performance on ISIC 2018 Task 2 dataset.

Effectively handles class imbalance and small sample issues.

Utilizes superpixel segmentation and attention modules for discriminative feature extraction.

Abstract

The accurate detection of lesion attributes is meaningful for both the computeraid diagnosis system and dermatologists decisions. However, unlike lesion segmentation and melenoma classification, there are few deep learning methods and literatures focusing on this task. Currently, the lesion attribute detection still remains challenging due to the extremely unbalanced class distribution and insufficient samples, as well as large intraclass and low interclass variations. To solve these problems, we propose a deep learning framework named superpixel attention network (SANet). Firstly, we segment input images into small regions and shuffle the obtained regions by the random shuttle mechanism (RSM). Secondly, we apply the SANet to capture discriminative features and reconstruct input images. Specifically, SANet contains two sub modules: superpixel average pooling and superpixel at tention module. We introduce a superpixel average pooling to reformulate the superpixel classification problem as a superpixel segmentation problem and a SAMis utilized to focus on discriminative superpixel regions and feature channels. Finally, we design a novel but effective loss, namely global balancing loss to address the serious data imbalance in ISIC 2018 Task 2 lesion attributes detection dataset. The proposed method achieves quite good performance on the ISIC 2018 Task 2 challenge.