Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313650473> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4313650473 endingPage "12" @default.
- W4313650473 startingPage "12" @default.
- W4313650473 abstract "To determine whether convolutional neural networks can detect morphological differences between images of microbiologically positive and negative corneal ulcers.A cross-sectional comparison of prospectively collected data consisting of bacterial and fungal cultures and smears from eyes with acute infectious keratitis at Aravind Eye Hospital. Two convolutional neural network architectures (DenseNet and MobileNet) were trained using images obtained from handheld cameras collected from culture-positive and negative images and smear-positive and -negative images. Each architecture was trained on two image sets: (1) one with labels assigned using only culture results and (2) one using culture and smear results. The outcome measure was area under the receiver operating characteristic curve for predicting whether an ulcer would be microbiologically positive or negative.There were 1970 images from 886 patients were included. None of the models were better than random chance at predicting positive microbiologic results (area under the receiver operating characteristic curve ranged from 0.49 to 0.56; all confidence intervals included 0.5).These two state-of-the-art deep convolutional neural network architectures could not reliably predict whether a corneal ulcer would be microbiologically positive or negative based on clinical photographs. This absence of detectable morphological differences informs the future development of computer vision models trained to predict the causative agent in infectious keratitis using corneal photography.These deep learning models were not able to identify morphological differences between microbiologically positive and negative corneal ulcers. This finding suggests that similar artificial intelligence models trained to identify the causative pathogen using only microbiologically positive cases may have potential to generalize well, including to cases with falsely negative microbiologic testing." @default.
- W4313650473 created "2023-01-07" @default.
- W4313650473 creator A5031651070 @default.
- W4313650473 creator A5033034428 @default.
- W4313650473 creator A5035227516 @default.
- W4313650473 creator A5055633443 @default.
- W4313650473 creator A5055729842 @default.
- W4313650473 creator A5075161120 @default.
- W4313650473 creator A5075952432 @default.
- W4313650473 creator A5087014948 @default.
- W4313650473 date "2023-01-06" @default.
- W4313650473 modified "2023-10-01" @default.
- W4313650473 title "Deep Convolutional Neural Networks Detect no Morphological Differences Between Culture-Positive and Culture-Negative Infectious Keratitis Images" @default.
- W4313650473 cites W1976071803 @default.
- W4313650473 cites W1984409867 @default.
- W4313650473 cites W2000791215 @default.
- W4313650473 cites W2013370934 @default.
- W4313650473 cites W2030162048 @default.
- W4313650473 cites W2048679677 @default.
- W4313650473 cites W2052780047 @default.
- W4313650473 cites W2074986866 @default.
- W4313650473 cites W2082727434 @default.
- W4313650473 cites W2114624496 @default.
- W4313650473 cites W2116723563 @default.
- W4313650473 cites W2117539524 @default.
- W4313650473 cites W2122104511 @default.
- W4313650473 cites W2123215356 @default.
- W4313650473 cites W2138157471 @default.
- W4313650473 cites W2156947972 @default.
- W4313650473 cites W2159093932 @default.
- W4313650473 cites W2541010041 @default.
- W4313650473 cites W2761604622 @default.
- W4313650473 cites W2807756120 @default.
- W4313650473 cites W3165196676 @default.
- W4313650473 cites W3177778205 @default.
- W4313650473 cites W4200272808 @default.
- W4313650473 cites W4210638541 @default.
- W4313650473 cites W4226325157 @default.
- W4313650473 doi "https://doi.org/10.1167/tvst.12.1.12" @default.
- W4313650473 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36607623" @default.
- W4313650473 hasPublicationYear "2023" @default.
- W4313650473 type Work @default.
- W4313650473 citedByCount "0" @default.
- W4313650473 crossrefType "journal-article" @default.
- W4313650473 hasAuthorship W4313650473A5031651070 @default.
- W4313650473 hasAuthorship W4313650473A5033034428 @default.
- W4313650473 hasAuthorship W4313650473A5035227516 @default.
- W4313650473 hasAuthorship W4313650473A5055633443 @default.
- W4313650473 hasAuthorship W4313650473A5055729842 @default.
- W4313650473 hasAuthorship W4313650473A5075161120 @default.
- W4313650473 hasAuthorship W4313650473A5075952432 @default.
- W4313650473 hasAuthorship W4313650473A5087014948 @default.
- W4313650473 hasBestOaLocation W43136504731 @default.
- W4313650473 hasConcept C108583219 @default.
- W4313650473 hasConcept C118487528 @default.
- W4313650473 hasConcept C119767625 @default.
- W4313650473 hasConcept C126322002 @default.
- W4313650473 hasConcept C142724271 @default.
- W4313650473 hasConcept C153180895 @default.
- W4313650473 hasConcept C154945302 @default.
- W4313650473 hasConcept C2778560704 @default.
- W4313650473 hasConcept C41008148 @default.
- W4313650473 hasConcept C58471807 @default.
- W4313650473 hasConcept C71924100 @default.
- W4313650473 hasConcept C81363708 @default.
- W4313650473 hasConceptScore W4313650473C108583219 @default.
- W4313650473 hasConceptScore W4313650473C118487528 @default.
- W4313650473 hasConceptScore W4313650473C119767625 @default.
- W4313650473 hasConceptScore W4313650473C126322002 @default.
- W4313650473 hasConceptScore W4313650473C142724271 @default.
- W4313650473 hasConceptScore W4313650473C153180895 @default.
- W4313650473 hasConceptScore W4313650473C154945302 @default.
- W4313650473 hasConceptScore W4313650473C2778560704 @default.
- W4313650473 hasConceptScore W4313650473C41008148 @default.
- W4313650473 hasConceptScore W4313650473C58471807 @default.
- W4313650473 hasConceptScore W4313650473C71924100 @default.
- W4313650473 hasConceptScore W4313650473C81363708 @default.
- W4313650473 hasIssue "1" @default.
- W4313650473 hasLocation W43136504731 @default.
- W4313650473 hasLocation W43136504732 @default.
- W4313650473 hasLocation W43136504733 @default.
- W4313650473 hasOpenAccess W4313650473 @default.
- W4313650473 hasPrimaryLocation W43136504731 @default.
- W4313650473 hasRelatedWork W2731899572 @default.
- W4313650473 hasRelatedWork W2999805992 @default.
- W4313650473 hasRelatedWork W3011074480 @default.
- W4313650473 hasRelatedWork W3116150086 @default.
- W4313650473 hasRelatedWork W3133861977 @default.
- W4313650473 hasRelatedWork W3192840557 @default.
- W4313650473 hasRelatedWork W4200173597 @default.
- W4313650473 hasRelatedWork W4291897433 @default.
- W4313650473 hasRelatedWork W4312417841 @default.
- W4313650473 hasRelatedWork W4321369474 @default.
- W4313650473 hasVolume "12" @default.
- W4313650473 isParatext "false" @default.
- W4313650473 isRetracted "false" @default.
- W4313650473 workType "article" @default.