Automatic evaluation of Nail Psoriasis Severity Index using deep learning algorithm

IF 2.9 3区 医学 Q2 DERMATOLOGY
Kyungho Paik, Bo Ri Kim, Sang Woong Youn
{"title":"Automatic evaluation of Nail Psoriasis Severity Index using deep learning algorithm","authors":"Kyungho Paik,&nbsp;Bo Ri Kim,&nbsp;Sang Woong Youn","doi":"10.1111/1346-8138.17313","DOIUrl":null,"url":null,"abstract":"<p>Nail psoriasis is a chronic condition characterized by nail dystrophy affecting the nail matrix and bed. The severity of nail psoriasis is commonly assessed using the Nail Psoriasis Severity Index (NAPSI), which evaluates the characteristics and extent of nail involvement. Although the NAPSI is numeric, reproducible, and simple, the assessment process is time-consuming and often challenging to use in real-world clinical settings. To overcome the time-consuming nature of NAPSI assessment, we aimed to develop a deep learning algorithm that can rapidly and reliably evaluate NAPSI, thereby providing numerous clinical and research advantages. We developed a dataset consisting of 7054 single fingernail images cropped from images of the dorsum of the hands of 634 patients with psoriasis. We annotated the eight features of the NAPSI in a single nail using bounding boxes and trained the YOLOv7-based deep learning algorithm using this annotation. The performance of the deep learning algorithm (DLA) was evaluated by comparing the NAPSI estimated using the DLA with the ground truth of the test dataset. The NAPSI evaluated using the DLA differed by 2 points from the ground truth in 98.6% of the images. The accuracy and mean absolute error of the model were 67.6% and 0.449, respectively. The intraclass correlation coefficient was 0.876, indicating good agreement. Our results showed that the DLA can rapidly and accurately evaluate the NAPSI. The rapid and accurate NAPSI assessment by the DLA is not only applicable in clinical settings, but also provides research advantages by enabling rapid NAPSI evaluations of previously collected nail images.</p>","PeriodicalId":54848,"journal":{"name":"Journal of Dermatology","volume":"51 10","pages":"1310-1317"},"PeriodicalIF":2.9000,"publicationDate":"2024-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Dermatology","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/1346-8138.17313","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"DERMATOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Nail psoriasis is a chronic condition characterized by nail dystrophy affecting the nail matrix and bed. The severity of nail psoriasis is commonly assessed using the Nail Psoriasis Severity Index (NAPSI), which evaluates the characteristics and extent of nail involvement. Although the NAPSI is numeric, reproducible, and simple, the assessment process is time-consuming and often challenging to use in real-world clinical settings. To overcome the time-consuming nature of NAPSI assessment, we aimed to develop a deep learning algorithm that can rapidly and reliably evaluate NAPSI, thereby providing numerous clinical and research advantages. We developed a dataset consisting of 7054 single fingernail images cropped from images of the dorsum of the hands of 634 patients with psoriasis. We annotated the eight features of the NAPSI in a single nail using bounding boxes and trained the YOLOv7-based deep learning algorithm using this annotation. The performance of the deep learning algorithm (DLA) was evaluated by comparing the NAPSI estimated using the DLA with the ground truth of the test dataset. The NAPSI evaluated using the DLA differed by 2 points from the ground truth in 98.6% of the images. The accuracy and mean absolute error of the model were 67.6% and 0.449, respectively. The intraclass correlation coefficient was 0.876, indicating good agreement. Our results showed that the DLA can rapidly and accurately evaluate the NAPSI. The rapid and accurate NAPSI assessment by the DLA is not only applicable in clinical settings, but also provides research advantages by enabling rapid NAPSI evaluations of previously collected nail images.

利用深度学习算法自动评估指甲牛皮癣严重程度指数。
指甲银屑病是一种慢性疾病,其特征是影响指甲基质和甲床的甲营养不良。指甲银屑病的严重程度通常用指甲银屑病严重程度指数(NAPSI)来评估,该指数评估指甲受累的特征和程度。虽然 NAPSI 是数值化、可重复和简单的,但评估过程耗时,在实际临床环境中使用往往具有挑战性。为了克服 NAPSI 评估的耗时特性,我们旨在开发一种深度学习算法,它可以快速、可靠地评估 NAPSI,从而为临床和研究带来诸多优势。我们开发了一个数据集,其中包括从 634 名银屑病患者的手背图像中裁剪的 7054 张单个指甲图像。我们使用边界框标注了单个指甲中 NAPSI 的八个特征,并利用这些标注训练了基于 YOLOv7 的深度学习算法。深度学习算法(DLA)的性能是通过比较使用 DLA 估算的 NAPSI 和测试数据集的基本真实值来评估的。在 98.6% 的图像中,使用 DLA 评估的 NAPSI 与地面实况相差 2 个点。模型的准确率和平均绝对误差分别为 67.6% 和 0.449。类内相关系数为 0.876,显示出良好的一致性。我们的结果表明,DLA 可以快速准确地评估 NAPSI。通过 DLA 进行快速准确的 NAPSI 评估不仅适用于临床环境,还能对之前收集的指甲图像进行快速 NAPSI 评估,从而为研究带来优势。
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
Journal of Dermatology
Journal of Dermatology 医学-皮肤病学
CiteScore
4.60
自引率
9.70%
发文量
368
审稿时长
4-8 weeks
期刊介绍: The Journal of Dermatology is the official peer-reviewed publication of the Japanese Dermatological Association and the Asian Dermatological Association. The journal aims to provide a forum for the exchange of information about new and significant research in dermatology and to promote the discipline of dermatology in Japan and throughout the world. Research articles are supplemented by reviews, theoretical articles, special features, commentaries, book reviews and proceedings of workshops and conferences. Preliminary or short reports and letters to the editor of two printed pages or less will be published as soon as possible. Papers in all fields of dermatology will be considered.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信