A Wavelet Guided Attention Module for Skin Cancer Classification with Gradient-based Feature Fusion

TL;DR

This paper introduces a novel attention-based model utilizing wavelet and gradient fusion techniques to improve skin cancer classification accuracy, effectively capturing lesion features and boundaries in imbalanced datasets.

Contribution

The proposed model combines wavelet-guided attention with gradient-based feature fusion to enhance skin lesion analysis, addressing boundary variations and class imbalance.

Findings

Achieved 91.17% F1-score on HAM10000 dataset.

Attained 90.75% accuracy in multi-class skin cancer classification.

Demonstrated effectiveness of wavelet and gradient fusion in medical image analysis.

Abstract

Skin cancer is a highly dangerous type of cancer that requires an accurate diagnosis from experienced physicians. To help physicians diagnose skin cancer more efficiently, a computer-aided diagnosis (CAD) system can be very helpful. In this paper, we propose a novel model, which uses a novel attention mechanism to pinpoint the differences in features across the spatial dimensions and symmetry of the lesion, thereby focusing on the dissimilarities of various classes based on symmetry, uniformity in texture and color, etc. Additionally, to take into account the variations in the boundaries of the lesions for different classes, we employ a gradient-based fusion of wavelet and soft attention-aided features to extract boundary information of skin lesions. We have tested our model on the multi-class and highly class-imbalanced dataset, called HAM10000, and achieved promising results, with a 91.17\% F1-score and 90.75\% accuracy. The code is made available at: https://github.com/AyushRoy2001/WAGF-Fusion.