21 53

Cited 0 times in

Assessment of deep neural networks for the diagnosis of benign and malignant skin neoplasms in comparison with dermatologists: A retrospective validation study

DC FieldValueLanguage
dc.contributor.author이주희-
dc.date.accessioned2021-01-19T07:42:06Z-
dc.date.available2021-01-19T07:42:06Z-
dc.date.issued2020-11-
dc.identifier.issn1549-1277-
dc.identifier.urihttps://ir.ymlib.yonsei.ac.kr/handle/22282913/181295-
dc.description.abstractBackground: The diagnostic performance of convolutional neural networks (CNNs) for diagnosing several types of skin neoplasms has been demonstrated as comparable with that of dermatologists using clinical photography. However, the generalizability should be demonstrated using a large-scale external dataset that includes most types of skin neoplasms. In this study, the performance of a neural network algorithm was compared with that of dermatologists in both real-world practice and experimental settings. Methods and findings: To demonstrate generalizability, the skin cancer detection algorithm (https://rcnn.modelderm.com) developed in our previous study was used without modification. We conducted a retrospective study with all single lesion biopsied cases (43 disorders; 40,331 clinical images from 10,426 cases: 1,222 malignant cases and 9,204 benign cases); mean age (standard deviation [SD], 52.1 [18.3]; 4,701 men [45.1%]) were obtained from the Department of Dermatology, Severance Hospital in Seoul, Korea between January 1, 2008 and March 31, 2019. Using the external validation dataset, the predictions of the algorithm were compared with the clinical diagnoses of 65 attending physicians who had recorded the clinical diagnoses with thorough examinations in real-world practice. In addition, the results obtained by the algorithm for the data of randomly selected batches of 30 patients were compared with those obtained by 44 dermatologists in experimental settings; the dermatologists were only provided with multiple images of each lesion, without clinical information. With regard to the determination of malignancy, the area under the curve (AUC) achieved by the algorithm was 0.863 (95% confidence interval [CI] 0.852-0.875), when unprocessed clinical photographs were used. The sensitivity and specificity of the algorithm at the predefined high-specificity threshold were 62.7% (95% CI 59.9-65.1) and 90.0% (95% CI 89.4-90.6), respectively. Furthermore, the sensitivity and specificity of the first clinical impression of 65 attending physicians were 70.2% and 95.6%, respectively, which were superior to those of the algorithm (McNemar test; p < 0.0001). The positive and negative predictive values of the algorithm were 45.4% (CI 43.7-47.3) and 94.8% (CI 94.4-95.2), respectively, whereas those of the first clinical impression were 68.1% and 96.0%, respectively. In the reader test conducted using images corresponding to batches of 30 patients, the sensitivity and specificity of the algorithm at the predefined threshold were 66.9% (95% CI 57.7-76.0) and 87.4% (95% CI 82.5-92.2), respectively. Furthermore, the sensitivity and specificity derived from the first impression of 44 of the participants were 65.8% (95% CI 55.7-75.9) and 85.7% (95% CI 82.4-88.9), respectively, which are values comparable with those of the algorithm (Wilcoxon signed-rank test; p = 0.607 and 0.097). Limitations of this study include the exclusive use of high-quality clinical photographs taken in hospitals and the lack of ethnic diversity in the study population. Conclusions: Our algorithm could diagnose skin tumors with nearly the same accuracy as a dermatologist when the diagnosis was performed solely with photographs. However, as a result of limited data relevancy, the performance was inferior to that of actual medical examination. To achieve more accurate predictive diagnoses, clinical information should be integrated with imaging information.-
dc.description.statementOfResponsibilityopen-
dc.languageEnglish-
dc.publisherPublic Library of Science-
dc.relation.isPartOfPLOS MEDICINE-
dc.rightsCC BY-NC-ND 2.0 KR-
dc.titleAssessment of deep neural networks for the diagnosis of benign and malignant skin neoplasms in comparison with dermatologists: A retrospective validation study-
dc.typeArticle-
dc.contributor.collegeCollege of Medicine (의과대학)-
dc.contributor.departmentDept. of Dermatology (피부과학교실)-
dc.contributor.googleauthorSeung Seog Han-
dc.contributor.googleauthorIk Jun Moon-
dc.contributor.googleauthorSeong Hwan Kim-
dc.contributor.googleauthorJung-Im Na-
dc.contributor.googleauthorMyoung Shin Kim-
dc.contributor.googleauthorGyeong Hun Park-
dc.contributor.googleauthorIlwoo Park-
dc.contributor.googleauthorKeewon Kim-
dc.contributor.googleauthorWoohyung Lim-
dc.contributor.googleauthorJu Hee Lee-
dc.contributor.googleauthorSung Eun Chang-
dc.identifier.doi10.1371/journal.pmed.1003381-
dc.contributor.localIdA03171-
dc.relation.journalcodeJ02539-
dc.identifier.eissn1549-1676-
dc.identifier.pmid33237903-
dc.contributor.alternativeNameLee, Ju Hee-
dc.contributor.affiliatedAuthor이주희-
dc.citation.volume17-
dc.citation.number11-
dc.citation.startPagee1003381-
dc.identifier.bibliographicCitationPLOS MEDICINE, Vol.17(11) : e1003381, 2020-11-
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Dermatology (피부과학교실) > 1. Journal Papers

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.