Literature DB >> 32534243

Past and present of computer-assisted dermoscopic diagnosis: performance of a conventional image analyser versus a convolutional neural network in a prospective data set of 1,981 skin lesions.

Katharina Sies1, Julia K Winkler1, Christine Fink1, Felicitas Bardehle1, Ferdinand Toberer1, Timo Buhl2, Alexander Enk1, Andreas Blum3, Albert Rosenberger4, Holger A Haenssle5.   

Abstract

BACKGROUND: Convolutional neural networks (CNNs) have shown a dermatologist-level performance in the classification of skin lesions. We aimed to deliver a head-to-head comparison of a conventional image analyser (CIA), which depends on segmentation and weighting of handcrafted features, to a CNN trained by deep learning.
METHODS: Cross-sectional study using a real-world, prospectively acquired, dermoscopic dataset of 1981 skin lesions to compare the diagnostic performance of a market-approved CNN (Moleanalyzer-Pro™, developed in 2018) to a CIA (Moleanalyzer-3™/Dynamole™; developed in 2004, all FotoFinder Systems Inc, Germany). As a reference standard, we used histopathological diagnoses (n = 785) or, in non-excised benign lesions (n = 1196), expert consensus plus an uneventful follow-up by sequential digital dermoscopy for at least 2 years.
RESULTS: A total of 281 malignant lesions and 1700 benign lesions from 435 patients (62.2% male, mean age: 52 years) were prospectively imaged. The CNN showed a sensitivity of 77.6% (95% confidence interval [CI]: [72.4%-82.1%]), specificity of 95.3% (95% CI: [94.2%-96.2%]), and receiver operating characteristic (ROC)-area under the curve (AUC) of 0.945 (95% CI: [0.930-0.961]). In contrast, the CIA achieved a sensitivity of 53.4% (95% CI: [47.5%-59.1%]), specificity of 86.6% (95% CI: [84.9%-88.1%]) and ROC-AUC of 0.738 (95% CI: [0.701-0.774]). The data set included melanomas originally diagnosed by dynamic changes during sequential digital dermoscopy (52 of 201, 20.6%), which reduced the sensitivities of both classifiers. Pairwise comparisons of sensitivities, specificities, and ROC-AUCs indicated a clear outperformance by the CNN (all p < 0.001).
CONCLUSIONS: The superior diagnostic performance of the CNN argues against a continued application of former CIAs as an aide to physicians' clinical management decisions.
Copyright © 2020 Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Automated melanoma detection; Computer-assisted diagnosis; Convolutional neural network; Deep learning; Dermoscopy; Skin cancer; Skin lesions

Year:  2020        PMID: 32534243     DOI: 10.1016/j.ejca.2020.04.043

Source DB:  PubMed          Journal:  Eur J Cancer        ISSN: 0959-8049            Impact factor:   9.162


  2 in total

Review 1.  Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review.

Authors:  Roxana Daneshjou; Mary P Smith; Mary D Sun; Veronica Rotemberg; James Zou
Journal:  JAMA Dermatol       Date:  2021-11-01       Impact factor: 11.816

2.  Clinically Inspired Skin Lesion Classification through the Detection of Dermoscopic Criteria for Basal Cell Carcinoma.

Authors:  Carmen Serrano; Manuel Lazo; Amalia Serrano; Tomás Toledo-Pastrana; Rubén Barros-Tornay; Begoña Acha
Journal:  J Imaging       Date:  2022-07-12
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.