Development and Narrow Validation of Computer Vision Approach to Facilitate Assessment of Change in Pigmented Cutaneous Lesions.
JID Innov
; 3(2): 100181, 2023 Mar.
Article
em En
| MEDLINE
| ID: mdl-36960318
ABSTRACT
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 Languageâbased 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 3â11 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.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Tipo de estudo:
Screening_studies
Idioma:
En
Revista:
JID Innov
Ano de publicação:
2023
Tipo de documento:
Article
País de afiliação:
Estados Unidos