Diagnostic Accuracy of Content Based Dermatoscopic Image Retrieval with Deep Classification Features.

CONCLUSIONS: Presenting visually similar images based on features from a neural network shows comparable accuracy to the softmax probability-based diagnoses of convolutional neural networks. CBIR may be more helpful than a softmax classifier in improving diagnostic accuracy of clinicians in a routine clinical setting. This article is protected by copyright. All rights reserved. PMID: 30207594 [PubMed - as supplied by publisher]

https://www.ncbi.nlm.nih.gov/pubmed/30207594?dopt=Abstract

Source: The British Journal of Dermatology - September 12, 2018 Category: Dermatology Authors: Tschandl P, Argenziano G, Razmara M, Yap J Tags: Br J Dermatol Source Type: research