FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287511870> ?p ?o ?g. }

• W4287511870 abstract "Purpose: Retinopathy screening via digital imaging is promising for early detection and timely treatment, and tracking retinopathic abnormality over time can help to reveal the risk of disease progression. We developed an innovative physician-oriented artificial intelligence-facilitating diagnosis aid system for retinal diseases for screening multiple retinopathies and monitoring the regions of potential abnormality over time.Approach: Our dataset contains 4908 fundus images from 304 eyes with image-level annotations, including diabetic retinopathy, age-related macular degeneration, cellophane maculopathy, pathological myopia, and healthy control (HC). The screening model utilized a VGG-based feature extractor and multiple-binary convolutional neural network-based classifiers. Images in time series were aligned via affine transforms estimated through speeded-up robust features. Heatmaps of retinopathy were generated from the feature extractor using gradient-weighted class activation mapping++, and individual candidate retinopathy sites were identified from the heatmaps using clustering algorithm. Nested cross-validation with a train-to-test split of 80% to 20% was used to evaluate the performance of the screening model.Results: Our screening model achieved 99% accuracy, 93% sensitivity, and 97% specificity in discriminating between patients with retinopathy and HCs. For discriminating between types of retinopathy, our model achieved an averaged performance of 80% accuracy, 78% sensitivity, 94% specificity, 79% F1-score, and Cohen’s kappa coefficient of 0.70. Moreover, visualization results were also shown to provide reasonable candidate sites of retinopathy.Conclusions: Our results demonstrated the capability of the proposed model for extracting diagnostic information of the abnormality and lesion locations, which allows clinicians to focus on patient-centered treatment and untangles the pathological plausibility hidden in deep learning models." @default.
• W4287511870 created "2022-07-25" @default.
• W4287511870 creator A5002358687 @default.
• W4287511870 creator A5012292258 @default.
• W4287511870 creator A5026914509 @default.
• W4287511870 creator A5029656275 @default.
• W4287511870 creator A5030780126 @default.
• W4287511870 creator A5052495842 @default.
• W4287511870 creator A5063126552 @default.
• W4287511870 creator A5068327587 @default.
• W4287511870 creator A5072470661 @default.
• W4287511870 creator A5079607587 @default.
• W4287511870 creator A5086490669 @default.
• W4287511870 date "2022-07-01" @default.
• W4287511870 modified "2023-10-14" @default.
• W4287511870 title "PADAr: physician-oriented artificial intelligence-facilitating diagnosis aid for retinal diseases" @default.
• W4287511870 cites W1468480166 @default.
• W4287511870 cites W1987971958 @default.
• W4287511870 cites W2042873837 @default.
• W4287511870 cites W2046434485 @default.
• W4287511870 cites W2060609110 @default.
• W4287511870 cites W2108598243 @default.
• W4287511870 cites W2119605622 @default.
• W4287511870 cites W2133059825 @default.
• W4287511870 cites W2154290668 @default.
• W4287511870 cites W2155558397 @default.
• W4287511870 cites W2158698691 @default.
• W4287511870 cites W2159764117 @default.
• W4287511870 cites W2164777277 @default.
• W4287511870 cites W2296574068 @default.
• W4287511870 cites W2529153069 @default.
• W4287511870 cites W2543634681 @default.
• W4287511870 cites W2598442119 @default.
• W4287511870 cites W2598940121 @default.
• W4287511870 cites W2727753969 @default.
• W4287511870 cites W2767040741 @default.
• W4287511870 cites W2796809202 @default.
• W4287511870 cites W2806796234 @default.
• W4287511870 cites W2891383927 @default.
• W4287511870 cites W2901202809 @default.
• W4287511870 cites W2912100147 @default.
• W4287511870 cites W2934420704 @default.
• W4287511870 cites W2949074827 @default.
• W4287511870 cites W2970546341 @default.
• W4287511870 cites W2974726644 @default.
• W4287511870 cites W2986571423 @default.
• W4287511870 cites W3017213724 @default.
• W4287511870 cites W3102564565 @default.
• W4287511870 cites W3112251966 @default.
• W4287511870 cites W3112383662 @default.
• W4287511870 cites W3154135352 @default.
• W4287511870 cites W4252865652 @default.
• W4287511870 doi "https://doi.org/10.1117/1.jmi.9.4.044501" @default.
• W4287511870 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35903415" @default.
• W4287511870 hasPublicationYear "2022" @default.
• W4287511870 type Work @default.
• W4287511870 citedByCount "0" @default.
• W4287511870 crossrefType "journal-article" @default.
• W4287511870 hasAuthorship W4287511870A5002358687 @default.
• W4287511870 hasAuthorship W4287511870A5012292258 @default.
• W4287511870 hasAuthorship W4287511870A5026914509 @default.
• W4287511870 hasAuthorship W4287511870A5029656275 @default.
• W4287511870 hasAuthorship W4287511870A5030780126 @default.
• W4287511870 hasAuthorship W4287511870A5052495842 @default.
• W4287511870 hasAuthorship W4287511870A5063126552 @default.
• W4287511870 hasAuthorship W4287511870A5068327587 @default.
• W4287511870 hasAuthorship W4287511870A5072470661 @default.
• W4287511870 hasAuthorship W4287511870A5079607587 @default.
• W4287511870 hasAuthorship W4287511870A5086490669 @default.
• W4287511870 hasBestOaLocation W42875118701 @default.
• W4287511870 hasConcept C118487528 @default.
• W4287511870 hasConcept C118552586 @default.
• W4287511870 hasConcept C119857082 @default.
• W4287511870 hasConcept C134018914 @default.
• W4287511870 hasConcept C138885662 @default.
• W4287511870 hasConcept C153180895 @default.
• W4287511870 hasConcept C154945302 @default.
• W4287511870 hasConcept C163864269 @default.
• W4287511870 hasConcept C2776391266 @default.
• W4287511870 hasConcept C2776401178 @default.
• W4287511870 hasConcept C2778313320 @default.
• W4287511870 hasConcept C2779829184 @default.
• W4287511870 hasConcept C2780623050 @default.
• W4287511870 hasConcept C2780827179 @default.
• W4287511870 hasConcept C41008148 @default.
• W4287511870 hasConcept C41895202 @default.
• W4287511870 hasConcept C50965678 @default.
• W4287511870 hasConcept C555293320 @default.
• W4287511870 hasConcept C71924100 @default.
• W4287511870 hasConcept C81363708 @default.
• W4287511870 hasConceptScore W4287511870C118487528 @default.
• W4287511870 hasConceptScore W4287511870C118552586 @default.
• W4287511870 hasConceptScore W4287511870C119857082 @default.
• W4287511870 hasConceptScore W4287511870C134018914 @default.
• W4287511870 hasConceptScore W4287511870C138885662 @default.
• W4287511870 hasConceptScore W4287511870C153180895 @default.
• W4287511870 hasConceptScore W4287511870C154945302 @default.
• W4287511870 hasConceptScore W4287511870C163864269 @default.
• W4287511870 hasConceptScore W4287511870C2776391266 @default.
• W4287511870 hasConceptScore W4287511870C2776401178 @default.

• next