Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention

TL;DR

This paper introduces HierAttn, a lightweight neural network with deep supervision and multi-stage attention for skin lesion diagnosis, outperforming existing lightweight models on dermoscopy and smartphone image datasets.

Contribution

The paper proposes HierAttn, a novel lightweight neural network with deep supervision and multi-branch attention, enhancing feature learning for skin lesion classification.

Findings

HierAttn achieves superior accuracy and AUC compared to state-of-the-art lightweight networks.

The deep supervision strategy effectively learns local and global features.

HierAttn performs well on both dermoscopy and smartphone image datasets.

Abstract

Accurate and unbiased examinations of skin lesions are critical for the early diagnosis and treatment of skin diseases. Visual features of skin lesions vary significantly because the images are collected from patients with different lesion colours and morphologies by using dissimilar imaging equipment. Recent studies have reported that ensembled convolutional neural networks (CNNs) are practical to classify the images for early diagnosis of skin disorders. However, the practical use of these ensembled CNNs is limited as these networks are heavyweight and inadequate for processing contextual information. Although lightweight networks (e.g., MobileNetV3 and EfficientNet) were developed to achieve parameters reduction for implementing deep neural networks on mobile devices, insufficient depth of feature representation restricts the performance. To address the existing limitations, we develop a new lite and effective neural network, namely HierAttn. The HierAttn applies a novel deep supervision strategy to learn the local and global features by using multi-stage and multi-branch attention mechanisms with only one training loss. The efficacy of HierAttn was evaluated by using the dermoscopy images dataset ISIC2019 and smartphone photos dataset PAD-UFES-20 (PAD2020). The experimental results show that HierAttn achieves the best accuracy and area under the curve (AUC) among the state-of-the-art lightweight networks. The code is available at https://github.com/anthonyweidai/HierAttn.