Medizinische Universität Graz Austria/Österreich - Forschungsportal - Medical University of Graz
Gewählte Publikation:
SHR Neuro Krebs Kardio Lipid Stoffw Microb
Marchetti, MA; Liopyris, K; Dusza, SW; Codella, NCF; Gutman, DA; Helba, B; Kalloo, A; Halpern, AC; Soyer, HP; Curiel-Lewandrowski, C; Kittler, H; Caffery, L; Malvehy, J; Wellenhof, RH.
Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017.
J Am Acad Dermatol. 2020; 82(3):622-627
Doi: 10.1016/j.jaad.2019.07.016
[OPEN ACCESS]
Web of Science
PubMed
FullText
FullText_MUG
- Study Group Mitglieder der Med Uni Graz:
- Hofmann-Wellenhof Rainer
- Soyer Hans Peter
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P < .001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance. Copyright © 2019 American Academy of Dermatology, Inc. Published by Elsevier Inc. All rights reserved.
- Find related publications in this database (using NLM MeSH Indexing)
- -
- Cross-Sectional Studies -
- Deep Learning -
- Dermatologists - statistics & numerical data
- Dermoscopy - methods
- Dermoscopy - statistics & numerical data
- Diagnosis, Differential -
- Humans -
- Image Interpretation, Computer-Assisted - methods
- International Cooperation -
- Internship and Residency - statistics & numerical data
- Internship and Residency -
- Keratosis, Seborrheic - diagnosis
- Melanoma - diagnosis
- Melanoma - pathology
- Nevus - diagnosis
- ROC Curve -
- Skin - diagnostic imaging
- Skin - pathology
- Skin Neoplasms - diagnosis
- Skin Neoplasms - pathology
- Skin Neoplasms -
- Skin Neoplasms -
- Find related publications in this database (Keywords)
- automated melanoma diagnosis
- computer algorithm
- computer vision
- deep learning
- dermatologist
- International Skin Imaging Collaboration
- International Symposium on Biomedical Imaging
- machine learning
- melanoma
- reader study
- skin cancer