基于改进MobileNetV3-Small的色素减退性皮肤病诊断  

Recognition of Hypopigmented Skin Diseases Based on Improved MobileNetV3-Small

作　　者：高埂 肖风丽[2] 杨飞[1] GAO Geng;XIAO Fengli;YANG Fei(School of Biomedical Engineering,Anhui Medical University,Hefei 230032,China;The First Affiliated Hospital of Anhui Medical University,Hefei 230032,China)

机构地区：[1]安徽医科大学生物医学工程学院,安徽合肥230032 [2]安徽医科大学第一附属医院,安徽合肥230032

出　　处：《计算机与现代化》2024年第5期120-126,共7页Computer and Modernization

基　　金：国家自然科学基金资助项目(81972926);安徽省自然科学基金资助项目(2108085MH303)。

摘　　要：传统的色素减退性皮肤病诊断依赖于皮肤科医生主观的临床经验,难以确保每位患者的皮肤病都能被及时精确诊断。因而,亟需一个快速而不依赖于经验的诊断方法。卷积神经网络(Convolutional Neural Network,CNN)具有强大的特征识别能力,为该方法的实现提供了可能。目前基于CNN的诊断方法主要集中在ResNet50等较深的模型,虽然取得了较高的准确率,但是这些模型存在参数量大、识别慢、在移动设备上可用性差的缺点。为此,本文基于MobileNetV3-Small提出一个新的轻量级CNN模型。首先,舍弃MobileNetV3-Small中计算复杂的挤压-激发(Squeeze-and-Excitation,SE)模块,引入较轻量的高效通道注意力(Efficient Channel Attention,ECA)机制;其次,使用计算方便、稳定性好的Leaky-ReLU激活函数;最后,在卷积层中引入空洞卷积,扩大感受野。经过实验测试表明,本文提出的模型相较于现有的诊断模型实现了参数量、识别时间和FLOPs的大幅减少,满足移动应用场景下的高可用性,同时其准确率和F1值仍取得领先性能。最后,基于提出的模型设计出一个移动端的色素减退性皮肤病临床诊断工具。In traditional hypopigmented skin disease diagnosis,reliance on the subjective clinical experience of dermatologists makes it challenging to ensure timely and accurate diagnoses for every patient.Therefore,there is a pressing need for a rapid,experience-independent diagnostic approach.Convolutional neural network(CNN)exhibits robust feature recognition capabilities,offering a potential solution.Currently,CNN-based diagnostic methods mainly focus on deeper models such as ResNet50.While achieving high accuracy,these models suffer from drawbacks like large parameter sizes,slow inference,and limited usability on mobile devices.To address these issues,this study introduces a novel lightweight CNN model based on MobileNetV3-Small.Firstly,it eliminates the computationally complex Squeeze-and-Excitation(SE)modules found in MobileNetV3-Small,replacing them with more lightweight Efficient Channel Attention(ECA)attention mechanism.Secondly,it employs the convenient and stable Leaky-ReLU activation function.Lastly,it introduces dilated convolutions in the convolutional layers to expand the receptive field.Experimental results indicate that the proposed model significantly reduces parameter size,recognition time and FLOPs compared to existing diagnostic models.It meets the high usability demands of mobile applications while still outperforming in terms of accuracy and F1 score.Ultimately,based on the proposed model,a mobile application for clinical diagnosis of hypopigmented skin disease has been developed.

关 键 词：色素减退性皮肤病 卷积神经网络 注意力机制 激活函数 空洞卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]