{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["181(1)"],"submitter":["Tschandl P"],"funding":["MetaOptima Technology Inc."],"pubmed_abstract":["<h4>Background</h4>Automated classification of medical images through neural networks can reach high accuracy rates but lacks interpretability.<h4>Objectives</h4>To compare the diagnostic accuracy obtained by using content-based image retrieval (CBIR) to retrieve visually similar dermatoscopic images with corresponding disease labels against predictions made by a neural network.<h4>Methods</h4>A neural network was trained to predict disease classes on dermatoscopic images from three retrospectively collected image datasets containing 888, 2750 and 16 691 images, respectively. Diagnosis predictions were made based on the most commonly occurring diagnosis in visually similar images, or based on the top-1 class prediction of the softmax output from the network. Outcome measures were area unde"],"journal":["The British journal of dermatology"],"pagination":["155-165"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC7379719"],"repository":["biostudies-literature"],"pubmed_title":["Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features."],"pmcid":["PMC7379719"],"pubmed_authors":["Yap J","Argenziano G","Razmara M","Tschandl P"],"additional_accession":[]},"is_claimable":false,"name":"Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features.","description":"<h4>Background</h4>Automated classification of medical images through neural networks can reach high accuracy rates but lacks interpretability.<h4>Objectives</h4>To compare the diagnostic accuracy obtained by using content-based image retrieval (CBIR) to retrieve visually similar dermatoscopic images with corresponding disease labels against predictions made by a neural network.<h4>Methods</h4>A neural network was trained to predict disease classes on dermatoscopic images from three retrospectively collected image datasets containing 888, 2750 and 16 691 images, respectively. Diagnosis predictions were made based on the most commonly occurring diagnosis in visually similar images, or based on the top-1 class prediction of the softmax output from the network. Outcome measures were area unde","dates":{"release":"2019-01-01T00:00:00Z","publication":"2019 Jul","modification":"2025-04-05T13:44:35.881Z","creation":"2025-04-05T13:44:35.881Z"},"accession":"S-EPMC7379719","cross_references":{"pubmed":["30207594"],"doi":["10.1111/bjd.17189"]}}