Back to Search
Start Over
A pretrained neural network shows similar diagnostic accuracy to medical students in categorizing dermatoscopic images after comparable training conditions
- Source :
- The British journal of dermatology. 177(3)
- Publication Year :
- 2017
-
Abstract
- Automated image classification by machine vision is evolving, largely because of the increasing efficiency of neural networks with special architectures such as convolutional neural networks (CNN)(1) . A recent study comparing board certified dermatologists with CNN suggested that CNN may achieve diagnostic accuracies similar to human experts(2) . We demonstrated that medical students without prior knowledge of dermatoscopy learn equally well from an analytic or heuristic teaching approach(3) . This article is protected by copyright. All rights reserved.
- Subjects :
- Adult
Male
Students, Medical
Computer science
Machine vision
Diagnostic accuracy
Dermoscopy
Dermatology
Machine learning
computer.software_genre
Convolutional neural network
Skin Diseases
Undergraduate methods
030207 dermatology & venereal diseases
03 medical and health sciences
0302 clinical medicine
medicine
Humans
Dermatoscopy
Artificial neural network
Contextual image classification
medicine.diagnostic_test
business.industry
Heuristic
Teaching
030220 oncology & carcinogenesis
Female
Artificial intelligence
Clinical Competence
Neural Networks, Computer
business
computer
Education, Medical, Undergraduate
Subjects
Details
- ISSN :
- 13652133
- Volume :
- 177
- Issue :
- 3
- Database :
- OpenAIRE
- Journal :
- The British journal of dermatology
- Accession number :
- edsair.doi.dedup.....84ccfbf7bddd0f75a5a14f10e78532da