ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Performance of Commercial Dermatoscopic Systems That Incorporate Artificial Intelligence for the Identification of Melanoma in General Practice: A Systematic Review

Miller, Ian; Rosic, Nedeljka; Stapelberg, Michael; Hudson, Jeremy; Coxon, Paul; Furness, James; Walsh, Joe; Climstein, Mike*
Cancers2024-4DOI: 10.3390/cancers16071443
1被引2阅读
引用收藏
分享

摘要

Simple Summary Early detection of malignant melanoma (MM) has the potential to significantly reduce morbidity and mortality as the thickness of the lesion is closely associated with prognosis. Artificial intelligence (AI) is a non-invasive technology that has the potential to aid clinicians in the early diagnosis of skin cancers, including melanoma. Performance metrics of machine-based AI have been shown to rival or improve upon clinician diagnosis. However, many studies have limited this scope to pre-build image databases that may not replicate real-world settings experienced in general practice. This systematic review aimed to report the performance of commercial or market-approved dermatoscopic systems with AI in the form of convolutional neural networks (CNNs) when tasked with classifying melanoma. The sensitivity and specificity of CNNs are highly varied and illustrate the necessity of clinician-to-patient interaction in the diagnosis process. Clinicians working in unison with AI show the most promise for better performance when classifying MM.Abstract Background: Cutaneous melanoma remains an increasing global public health burden, particularly in fair-skinned populations. Advancing technologies, particularly artificial intelligence (AI), may provide an additional tool for clinicians to help detect malignancies with a more accurate success rate. This systematic review aimed to report the performance metrics of commercially available convolutional neural networks (CNNs) tasked with detecting MM. Methods: A systematic literature search was performed using CINAHL, Medline, Scopus, ScienceDirect and Web of Science databases. Results: A total of 16 articles reporting MM were included in this review. The combined number of melanomas detected was 1160, and non-melanoma lesions were 33,010. The performance of market-approved technology and clinician performance for classifying melanoma was highly heterogeneous, with sensitivity ranging from 16.4 to 100.0%, specificity between 40.0 and 98.3% and accuracy between 44.0 and 92.0%. Less heterogeneity was observed when clinicians worked in unison with AI, with sensitivity ranging between 83.3 and 100.0%, specificity between 83.7 and 87.3%, and accuracy between 86.4 and 86.9%. Conclusion: Instead of focusing on the performance of AI versus clinicians for classifying melanoma, more consistent performance has been obtained when clinicians' work is supported by AI, facilitating management decisions and improving health outcomes.

学科与关键词

关键词
computer-aided diagnosisconvolutional neural networkdeep learningdermatologydetectiondiagnosisepidemiologymachine learningskin cancertotal body photography
相关
加载中…
  • Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis
    Krakowski, Isabelle; Kim, Jiyeong; Cai, Zhuo Ran; Daneshjou, Roxana; Lapins, Jan; Eriksson, Hanna; Lykou, Anastasia; Linos, Eleni*npj Digital Medicine, 2024, 7(1): 78.被引 3
  • Deep neural networks are superior to dermatologists in melanoma image classification
    Brinker, Titus J.*; Hekler, Achim; Enk, Alexander H.; Berking, Carola; Haferkamp, Sebastian; Hauschild, Axel; Weichenthal, Michael; Klode, Joachim; Schadendorf, Dirk; Holland-Letz, Tim; von Kalle, Christof; Froehling, Stefan; Schilling, Bastian; Utikal, Jochen S.European Journal of Cancer, 2019, 119: 11-17.被引 170
  • A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis
    Salinas, Maria Paz; Sepulveda, Javiera; Hidalgo, Leonel; Peirano, Dominga; Morel, Macarena; Uribe, Pablo; Rotemberg, Veronica; Briones, Juan; Mery, Domingo; Navarrete-Dechent, Cristian*npj Digital Medicine, 2024, 7(1): 125.被引 12
查看全部 →

发表信息

论文状态
公开发表
期刊
Cancers
发表日期
2024-04
卷期
第 16 卷, 第 7 期
页码
1443
DOI
10.3390/cancers16071443
成果收录
SCIE
资助标注
Johnson and Johnson

作者

  • M

    Miller, Ian (第一作者)

  • R

    Rosic, Nedeljka

查看全部 8 位作者收起作者
  • S

    Stapelberg, Michael

  • H

    Hudson, Jeremy

  • C

    Coxon, Paul

  • F

    Furness, James

  • W

    Walsh, Joe

  • C

    Climstein, Mike (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417