A Narrative Review: Opportunities and Challenges in Artificial Intelligence Skin Image Analyses Using Total Body Photography

被引：10

作者：

Primiero, Clare A. ^{[1
,2
,3
]}

Rezze, Gisele Gargantini ^{[1
,2
]}

Caffery, Liam J. ^{[3
,4
,5
]}

Carrera, Cristina ^{[1
,2
,6
,7
]}

Podlipnik, Sebastian ^{[1
,2
,7
]}

Espinosa, Natalia ^{[1
,2
]}

Puig, Susana ^{[1
,2
,6
,7
]}

Janda, Monika ^{[4
]}

Soyer, H. Peter ^{[3
,8
]}

Malvehy, Josep ^{[1
,2
,6
,7
]}

机构：

[1] Inst Invest Biomed August Pi i Sunyer IDIBAPS, Hosp Clin, Dermatol Dept, Barcelona, Spain

[2] Inst Invest Biomed August Pi i Sunyer IDIBAPS, Fundacio Clin Recerca Biomed, Barcelona, Spain

[3] Univ Queensland, Frazer Inst, Dermatol Res Ctr, Brisbane, Australia

[4] Univ Queensland, Fac Med, Ctr Hlth Serv Res, Brisbane, Australia

[5] Univ Queensland, Ctr Online Hlth, Brisbane, Australia

[6] Univ Barcelona, Med Dept, Barcelona, Spain

[7] Inst Salud Carlos III, CIBER Enfermedades Raras, Barcelona, Spain

[8] Princess Alexandra Hosp, Dermatol Dept, Brisbane, Qld, Australia

来源：

JOURNAL OF INVESTIGATIVE DERMATOLOGY | 2024年 / 144卷 / 06期

基金：

英国医学研究理事会;

关键词：

Artificial intelligence; Dermatology; Melanoma; Total body photography; CONVOLUTIONAL NEURAL-NETWORK; FOLLOW-UP; CANCER; MELANOMA; CLASSIFICATION; DERMOSCOPY; IDENTIFICATION; LIMITATIONS; GUIDELINES; LESIONS;

D O I：

10.1016/j.jid.2023.11.007

中图分类号：

R75 [皮肤病学与性病学];

学科分类号：

100206 ;

摘要：

Artificial intelligence (AI) algorithms for skin lesion classification have reported accuracy at par with and even outperformance of expert dermatologists in experimental settings. However, the majority of algorithms do not represent real-world clinical approach where skin phenotype and clinical background information are considered. We review the current state of AI for skin lesion classification and present opportunities and challenges when applied to total body photography (TBP). AI in TBP analysis presents opportunities for intrapatient assessment of skin phenotype and holistic risk assessment by incorporating patient-level metadata, although challenges exist for protecting patient privacy in algorithm development and improving explainable AI methods.

引用

页码：1200 / 1207

页数：8

共 57 条

[1] Reproducible Naevus Counts Using 3D Total Body Photography and Convolutional Neural Networks [J].

Betz-Stablein, Brigid ;

D'Alessandro, Brian ;

Koh, Uyen ;

Plasmeijer, Elsemieke ;

Janda, Monika ;

Menzies, Scott W. ;

Hofmann-Wellenhof, Rainer ;

Green, Adele C. ;

Soyer, H. Peter .

DERMATOLOGY, 2022, 238 (01) :4-11

[2] DICOM in Dermoscopic Research: an Experience Report and a Way Forward [J].

Caffery, Liam ;

Weber, Jochen ;

Kurtansky, Nicholas ;

Clunie, David ;

Langer, Steve ;

Shih, George ;

Halpern, Allan ;

Rotemberg, Veronica .

JOURNAL OF DIGITAL IMAGING, 2021, 34 (04) :967-973

[3] The Role of DICOM in Artificial Intelligence for Skin Disease [J].

Caffery, Liam J. ;

Rotemberg, Veronica ;

Weber, Jochen ;

Soyer, H. Peter ;

Malvehy, Josep ;

Clunie, David .

FRONTIERS IN MEDICINE, 2021, 7

[4] Transforming Dermatologic Imaging for the Digital Era: Metadata and Standards [J].

Caffery, Liam J. ;

Clunie, David ;

Curiel-Lewandrowski, Clara ;

Malvehy, Josep ;

Soyer, H. Peter ;

Halpern, Allan C. .

JOURNAL OF DIGITAL IMAGING, 2018, 31 (04) :568-577

[5] Lesion border detection in dermoscopy images [J].

Celebi, M. Emre ;

Iyatomi, Hitoshi ;

Schaefer, Gerald ;

Stoecker, William V. .

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2009, 33 (02) :148-153

[6] Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening? [J].

Cerminara, Sara E. ;

Cheng, Phil ;

Kostner, Lisa ;

Huber, Stephanie ;

Kunz, Michael ;

Maul, Julia-Tatjana ;

Bohm, Jette S. ;

Dettwiler, Chiara F. ;

Geser, Anna ;

Jakopovic, Cecile ;

Stoffel, Livia M. ;

Peter, Jelissa K. ;

Levesque, Mitchell ;

Navarini, Alexander A. ;

Maul, Lara Valeska .

EUROPEAN JOURNAL OF CANCER, 2023, 190

[7] Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge [J].

Combalia, Marc ;

Codella, Noel ;

Rotemberg, Veronica ;

Carrera, Cristina ;

Dusza, Stephen ;

Gutman, David ;

Helba, Brian ;

Kittler, Harald ;

Kurtansky, Nicholas R. ;

Liopyris, Konstantinos ;

Marchetti, Michael A. ;

Podlipnik, Sebastian ;

Puig, Susana ;

Rinner, Christoph ;

Tschandl, Philipp ;

Weber, Jochen ;

Halpern, Allan ;

Malvehy, Josep .

LANCET DIGITAL HEALTH, 2022, 4 (05) :E330-E339

[8] Research Techniques Made Simple: Deep Learning for the Classification of Dermatological Images [J].

Cullell-Dalmau, Marta ;

Otero-Vinas, Marta ;

Manzo, Carlo .

JOURNAL OF INVESTIGATIVE DERMATOLOGY, 2020, 140 (03) :507-+

[9] Checklist for Evaluation of Image-Based Artificial Intelligence Reports in Dermatology CLEAR Derm Consensus Guidelines From the International Skin Imaging Collaboration Artificial Intelligence Working Group [J].

Daneshjou, Roxana ;

Barata, Catarina ;

Betz-Stablein, Brigid ;

Celebi, M. Emre ;

Codella, Noel ;

Combalia, Marc ;

Guitera, Pascale ;

Gutman, David ;

Halpern, Allan ;

Helba, Brian ;

Kittler, Harald ;

Kose, Kivanc ;

Liopyris, Konstantinos ;

Malvehy, Josep ;

Seog, Han Seung ;

Soyer, H. Peter ;

Tkaczyk, Eric R. ;

Tschandl, Philipp ;

Rotemberg, Veronica .

JAMA DERMATOLOGY, 2022, 158 (01) :90-96

[10] Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms A Scoping Review [J].

Daneshjou, Roxana ;

Smith, Mary P. ;

Sun, Mary D. ;

Rotemberg, Veronica ;

Zou, James .

JAMA DERMATOLOGY, 2021, 157 (11) :1362-1369

← 1 2 3 4 5 6 →