FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317869168> ?p ?o ?g. }

• W4317869168 endingPage "1095" @default.
• W4317869168 startingPage "1081" @default.
• W4317869168 abstract "Compared with traditional fundus examination techniques, ultra-widefield fundus (UWF) images provide 200° panoramic images of the retina, which allows better detection of peripheral retinal lesions. The advent of UWF provides effective solutions only for detection but still lacks efficient diagnostic capabilities. This study proposed a retinal lesion detection model to automatically locate and identify six relatively typical and high-incidence peripheral retinal lesions from UWF images which will enable early screening and rapid diagnosis. A total of 24,602 augmented ultra-widefield fundus images with labels corresponding to 6 peripheral retinal lesions and normal manifestation labelled by 5 ophthalmologists were included in this study. An object detection model named You Only Look Once X (YOLOX) was modified and trained to locate and classify the six peripheral retinal lesions including rhegmatogenous retinal detachment (RRD), retinal breaks (RB), white without pressure (WWOP), cystic retinal tuft (CRT), lattice degeneration (LD), and paving-stone degeneration (PSD). We applied coordinate attention block and generalized intersection over union (GIOU) loss to YOLOX and evaluated it for accuracy, sensitivity, specificity, precision, F1 score, and average precision (AP). This model was able to show the exact location and saliency map of the retinal lesions detected by the model thus contributing to efficient screening and diagnosis. The model reached an average accuracy of 96.64%, sensitivity of 87.97%, specificity of 98.04%, precision of 87.01%, F1 score of 87.39%, and mAP of 86.03% on test dataset 1 including 248 UWF images and reached an average accuracy of 95.04%, sensitivity of 83.90%, specificity of 96.70%, precision of 78.73%, F1 score of 81.96%, and mAP of 80.59% on external test dataset 2 including 586 UWF images, showing this system performs well in distinguishing the six peripheral retinal lesions. Focusing on peripheral retinal lesions, this work proposed a deep learning model, which automatically recognized multiple peripheral retinal lesions from UWF images and localized exact positions of lesions. Therefore, it has certain potential for early screening and intelligent diagnosis of peripheral retinal lesions." @default.
• W4317869168 created "2023-01-25" @default.
• W4317869168 creator A5017822865 @default.
• W4317869168 creator A5021878269 @default.
• W4317869168 creator A5033479079 @default.
• W4317869168 creator A5034223041 @default.
• W4317869168 creator A5047614134 @default.
• W4317869168 creator A5061343191 @default.
• W4317869168 creator A5062293414 @default.
• W4317869168 creator A5067354188 @default.
• W4317869168 creator A5070980467 @default.
• W4317869168 creator A5075786464 @default.
• W4317869168 creator A5080733133 @default.
• W4317869168 creator A5083455588 @default.
• W4317869168 creator A5084397496 @default.
• W4317869168 creator A5089501328 @default.
• W4317869168 date "2023-01-24" @default.
• W4317869168 modified "2023-10-15" @default.
• W4317869168 title "Intelligent Diagnosis of Multiple Peripheral Retinal Lesions in Ultra-widefield Fundus Images Based on Deep Learning" @default.
• W4317869168 cites W1994891140 @default.
• W4317869168 cites W2027266161 @default.
• W4317869168 cites W2054186570 @default.
• W4317869168 cites W2064494956 @default.
• W4317869168 cites W2194775991 @default.
• W4317869168 cites W2314257879 @default.
• W4317869168 cites W2463187181 @default.
• W4317869168 cites W2557738935 @default.
• W4317869168 cites W2581082771 @default.
• W4317869168 cites W2761604622 @default.
• W4317869168 cites W2762672048 @default.
• W4317869168 cites W2770877241 @default.
• W4317869168 cites W2789367970 @default.
• W4317869168 cites W2790270334 @default.
• W4317869168 cites W2793843524 @default.
• W4317869168 cites W2802338305 @default.
• W4317869168 cites W2884561390 @default.
• W4317869168 cites W2886801379 @default.
• W4317869168 cites W2898192966 @default.
• W4317869168 cites W2899508414 @default.
• W4317869168 cites W2916155412 @default.
• W4317869168 cites W2918612085 @default.
• W4317869168 cites W2950497185 @default.
• W4317869168 cites W2962834855 @default.
• W4317869168 cites W2991326607 @default.
• W4317869168 cites W3003322804 @default.
• W4317869168 cites W3016955851 @default.
• W4317869168 cites W3046828655 @default.
• W4317869168 cites W3082655451 @default.
• W4317869168 cites W3089653673 @default.
• W4317869168 cites W3110054227 @default.
• W4317869168 cites W3116131963 @default.
• W4317869168 cites W3136370240 @default.
• W4317869168 cites W3137817362 @default.
• W4317869168 cites W3153301075 @default.
• W4317869168 cites W3191934798 @default.
• W4317869168 cites W4220806015 @default.
• W4317869168 cites W4224235558 @default.
• W4317869168 cites W4233026002 @default.
• W4317869168 cites W4281397620 @default.
• W4317869168 cites W4281625582 @default.
• W4317869168 cites W4281851527 @default.
• W4317869168 cites W4298347007 @default.
• W4317869168 cites W4309112584 @default.
• W4317869168 cites W4377205441 @default.
• W4317869168 doi "https://doi.org/10.1007/s40123-023-00651-x" @default.
• W4317869168 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36692813" @default.
• W4317869168 hasPublicationYear "2023" @default.
• W4317869168 type Work @default.
• W4317869168 citedByCount "1" @default.
• W4317869168 countsByYear W43178691682023 @default.
• W4317869168 crossrefType "journal-article" @default.
• W4317869168 hasAuthorship W4317869168A5017822865 @default.
• W4317869168 hasAuthorship W4317869168A5021878269 @default.
• W4317869168 hasAuthorship W4317869168A5033479079 @default.
• W4317869168 hasAuthorship W4317869168A5034223041 @default.
• W4317869168 hasAuthorship W4317869168A5047614134 @default.
• W4317869168 hasAuthorship W4317869168A5061343191 @default.
• W4317869168 hasAuthorship W4317869168A5062293414 @default.
• W4317869168 hasAuthorship W4317869168A5067354188 @default.
• W4317869168 hasAuthorship W4317869168A5070980467 @default.
• W4317869168 hasAuthorship W4317869168A5075786464 @default.
• W4317869168 hasAuthorship W4317869168A5080733133 @default.
• W4317869168 hasAuthorship W4317869168A5083455588 @default.
• W4317869168 hasAuthorship W4317869168A5084397496 @default.
• W4317869168 hasAuthorship W4317869168A5089501328 @default.
• W4317869168 hasBestOaLocation W43178691681 @default.
• W4317869168 hasConcept C118487528 @default.
• W4317869168 hasConcept C126322002 @default.
• W4317869168 hasConcept C154945302 @default.
• W4317869168 hasConcept C169760540 @default.
• W4317869168 hasConcept C2776391266 @default.
• W4317869168 hasConcept C2777093970 @default.
• W4317869168 hasConcept C2780827179 @default.
• W4317869168 hasConcept C2781040256 @default.
• W4317869168 hasConcept C41008148 @default.
• W4317869168 hasConcept C46762472 @default.
• W4317869168 hasConcept C71924100 @default.
• W4317869168 hasConcept C86803240 @default.

• next