Seems to Be Low, but Is it Really Poor? Need for Cohort and Comparative Studies to Clarify the Performance of Deep Neural Networks
- 15 October 2020
- journal article
- letter
- Published by Elsevier BV in Journal of Investigative Dermatology
- Vol. 141 (5), 1329-1331
- https://doi.org/10.1016/j.jid.2020.08.024
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- Human versus machine in medicine: can scientific literature answer the question?The Lancet Digital Health, 2019
- Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, web-based, international, diagnostic studyThe Lancet Oncology, 2019
- Diagnostic Accuracy StudiesSeminars in Nuclear Medicine, 2019
- Comparing artificial intelligence algorithms to 157 German dermatologists: the melanoma classification benchmarkEuropean Journal of Cancer, 2019
- Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional studyPLoS Medicine, 2018
- Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologistsAnnals of Oncology, 2018
- Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and PredictionRadiology, 2018
- Erratum: Corrigendum: Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Accuracy of clinical diagnosis of skin lesionsBritish Journal of Dermatology, 2008