Artificial intelligence (AI) based system for the diagnosis and classification of scalp health: AI-ScalpGrader

IF 1.3 4区工程技术 Q4 CHEMISTRY, ANALYTICAL

Instrumentation Science & Technology Pub Date : 2022-10-07 DOI:10.1080/10739149.2022.2129382

Jeong-Il Jeong, Dong-Soon Park, Ji-eun Koo, Woo-Sang Song, Duck-Jin Pae, Hwa-Jung Choi

{"title":"Artificial intelligence (AI) based system for the diagnosis and classification of scalp health: AI-ScalpGrader","authors":"Jeong-Il Jeong, Dong-Soon Park, Ji-eun Koo, Woo-Sang Song, Duck-Jin Pae, Hwa-Jung Choi","doi":"10.1080/10739149.2022.2129382","DOIUrl":null,"url":null,"abstract":"Abstract Many people suffer from scalp disorders but common treatment devices have faults such as inaccuracy of results and inconvenience of use. This study proposes a deep learning-based intelligent scalp diagnosis and classification system, named artificial intelligence (AI)-ScalpGrader. The proposed system consists of a portable scalp imaging device (ASM-202), a mobile device app, a cloud-based AI training server, and a cloud-based management platform. The instrumentation diagnoses and classifies ten scalp symptoms (normal, drying, oily, sensitivity, atopy, seborrheic, trouble, dry dandruff, oily dandruff, and hair loss) based on seven dermatologist-based indices (microkeratin, sebaceous, erythema between hair follicles, follicular erythema/pustules, dandruff, and hair loss) by AI-based characterization of the symptoms and indices. EfficientNet, a convolutional neural network (CNN) learning model, is MBConvolution composed with depthwise convolution, squeeze excitation, and width scaling and was adopted to diagnose and classify scalp conditions through retraining of images in the system. The results and verification on the reliability of AI-based data show that the system is able to diagnose and classify these symptoms and severity of the indices with accuracy values from 87.3 to 91.3%. Therefore, the AI-ScalpGrader is a novel approach to diagnose and classify scalp status.","PeriodicalId":13547,"journal":{"name":"Instrumentation Science & Technology","volume":"51 1","pages":"371 - 381"},"PeriodicalIF":1.3000,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Instrumentation Science & Technology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/10739149.2022.2129382","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CHEMISTRY, ANALYTICAL","Score":null,"Total":0}

引用次数: 2

Abstract

Abstract Many people suffer from scalp disorders but common treatment devices have faults such as inaccuracy of results and inconvenience of use. This study proposes a deep learning-based intelligent scalp diagnosis and classification system, named artificial intelligence (AI)-ScalpGrader. The proposed system consists of a portable scalp imaging device (ASM-202), a mobile device app, a cloud-based AI training server, and a cloud-based management platform. The instrumentation diagnoses and classifies ten scalp symptoms (normal, drying, oily, sensitivity, atopy, seborrheic, trouble, dry dandruff, oily dandruff, and hair loss) based on seven dermatologist-based indices (microkeratin, sebaceous, erythema between hair follicles, follicular erythema/pustules, dandruff, and hair loss) by AI-based characterization of the symptoms and indices. EfficientNet, a convolutional neural network (CNN) learning model, is MBConvolution composed with depthwise convolution, squeeze excitation, and width scaling and was adopted to diagnose and classify scalp conditions through retraining of images in the system. The results and verification on the reliability of AI-based data show that the system is able to diagnose and classify these symptoms and severity of the indices with accuracy values from 87.3 to 91.3%. Therefore, the AI-ScalpGrader is a novel approach to diagnose and classify scalp status.

查看原文本刊更多论文

基于人工智能的头皮健康诊断和分类系统：AI ScalpGrader

摘要许多人患有头皮疾病，但常见的治疗设备存在结果不准确和使用不便等缺陷。本研究提出了一种基于深度学习的智能头皮诊断和分类系统，命名为人工智能（AI）-ScalpGrader。该系统由便携式头皮成像设备（ASM-202）、移动设备应用程序、基于云的人工智能培训服务器和基于云的管理平台组成。该仪器通过基于AI的症状和指标表征，根据皮肤科医生的七个指标（微角蛋白、皮脂腺、毛囊间红斑、毛囊红斑/脓疱、头皮屑和脱发），诊断和分类十种头皮症状（正常、干燥、油性、敏感、特应性、脂溢、麻烦、干燥头皮屑、油性头皮屑）。EfficientNet是一种卷积神经网络（CNN）学习模型，是由深度卷积、挤压激励和宽度缩放组成的MBConvolution，用于通过系统中图像的再训练来诊断和分类头皮状况。结果和基于AI的数据可靠性验证表明，该系统能够诊断和分类这些症状和指标的严重程度，准确率在87.3%至91.3%之间。因此，AI头皮分级器是诊断和分类头皮状态的一种新方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Instrumentation Science & Technology 工程技术-分析化学

CiteScore

3.50

自引率

0.00%

发文量

审稿时长

>12 weeks

期刊介绍： Instrumentation Science & Technology is an internationally acclaimed forum for fast publication of critical, peer reviewed manuscripts dealing with innovative instrument design and applications in chemistry, physics biotechnology and environmental science. Particular attention is given to state-of-the-art developments and their rapid communication to the scientific community. Emphasis is on modern instrumental concepts, though not exclusively, including detectors, sensors, data acquisition and processing, instrument control, chromatography, electrochemistry, spectroscopy of all types, electrophoresis, radiometry, relaxation methods, thermal analysis, physical property measurements, surface physics, membrane technology, microcomputer design, chip-based processes, and more. Readership includes everyone who uses instrumental techniques to conduct their research and development. They are chemists (organic, inorganic, physical, analytical, nuclear, quality control) biochemists, biotechnologists, engineers, and physicists in all of the instrumental disciplines mentioned above, in both the laboratory and chemical production environments. The journal is an important resource of instrument design and applications data.