Development and Narrow Validation of Computer Vision Approach to Facilitate Assessment of Change in Pigmented Cutaneous Lesions.
CI, confidence interval
Journal
JID innovations : skin science from molecules to population health
ISSN: 2667-0267
Titre abrégé: JID Innov
Pays: Netherlands
ID NLM: 101776173
Informations de publication
Date de publication:
Mar 2023
Mar 2023
Historique:
received:
22
04
2022
revised:
10
11
2022
accepted:
16
11
2022
entrez:
24
3
2023
pubmed:
25
3
2023
medline:
25
3
2023
Statut:
epublish
Résumé
The documentation of the change in the number and appearance of pigmented cutaneous lesions over time is critical to the early detection of skin cancers and may provide preliminary signals of efficacy in early-phase therapeutic prevention trials for melanoma. Despite substantial progress in computer-aided diagnosis of melanoma, automated methods to assess the evolution of lesions are relatively undeveloped. This report describes the development and narrow validation of mathematical algorithms to register nevi between sequential digital photographs of large areas of skin and to align images for improved detection and quantification of changes. Serial posterior truncal photographs from a pre-existing database were processed and analyzed by the software, and the results were evaluated by a panel of clinicians using a separate Extensible Markup Language‒based application. The software had a high sensitivity for the detection of cutaneous lesions as small as 2 mm. The software registered lesions accurately, with occasional errors at the edges of the images. In one pilot study with 17 patients, the use of the software enabled clinicians to identify new and/or enlarged lesions in 3‒11 additional patients versus the unregistered images. Automated quantification of size change performed similarly to that of human raters. These results support the further development and broader validation of this technique.
Identifiants
pubmed: 36960318
doi: 10.1016/j.xjidi.2023.100181
pii: S2667-0267(23)00002-4
pmc: PMC10030255
doi:
Types de publication
Journal Article
Langues
eng
Pagination
100181Informations de copyright
© 2023 The Authors.
Références
Nat Rev Cancer. 2016 Jun;16(6):345-58
pubmed: 27125352
Arch Dermatol. 2005 Aug;141(8):998-1006
pubmed: 16103329
IEEE Trans Med Imaging. 2015 Jan;34(1):317-38
pubmed: 25222947
Cancer Prev Res (Phila). 2018 Jul;11(7):429-438
pubmed: 29691233
Lancet Oncol. 2019 Jul;20(7):938-947
pubmed: 31201137
Int J Environ Res Public Health. 2021 Feb 10;18(4):
pubmed: 33578996
Psychometrika. 2016 Jun;81(2):399-410
pubmed: 25516203
JAMA Dermatol. 2019 Nov 01;155(11):1291-1299
pubmed: 31215969
IEEE J Biomed Health Inform. 2019 Mar;23(2):501-508
pubmed: 29993849
Med J Aust. 2017 Oct 16;207(8):348-350
pubmed: 29020893
Ann Oncol. 2020 Jan;31(1):137-143
pubmed: 31912788
J Am Acad Dermatol. 2018 May;78(5):927-934.e6
pubmed: 29678380
N Engl J Med. 2015 Oct 22;373(17):1618-26
pubmed: 26488693
J Cosmet Dermatol. 2003 Jul;2(3-4):131-4
pubmed: 17163918
JAMA Dermatol. 2022 Jan 01;158(1):90-96
pubmed: 34851366
Med Image Anal. 2016 Jan;27:84-92
pubmed: 25960342
Dermatol Surg. 2007 Oct;33(10):1198-206; discussion 1205-6
pubmed: 17903152
Dermatol Pract Concept. 2017 Apr 30;7(2):7-16
pubmed: 28515986
BMJ. 2020 Feb 10;368:m127
pubmed: 32041693
Future Oncol. 2020 Mar;16(9):413-415
pubmed: 32100570
Sci Data. 2021 Mar 5;8(1):81
pubmed: 33674616
Dermatol Clin. 2017 Oct;35(4):409-416
pubmed: 28886797
Br J Cancer. 2021 May;124(11):1749-1750
pubmed: 33742148
J Am Acad Dermatol. 2019 Apr;80(4):1121-1131
pubmed: 30528310
JAMA Dermatol. 2017 May 1;153(5):453-457
pubmed: 28241182
J Invest Dermatol. 2012 May;132(5):1497-500
pubmed: 22297641