Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387668009> ?p ?o ?g. }
- W4387668009 abstract "Drug-induced liver injury (DILI) presents significant diagnostic challenges, and recently artificial intelligence-based deep learning technology has been used to predict various hepatic findings. In this study, we trained a set of Mask R-CNN-based deep algorithms to learn and quantify typical toxicant induced-histopathological lesions, portal area, and connective tissue in Sprague Dawley rats. We compared a set of single-finding models (SFMs) and a combined multiple-finding model (MFM) for their ability to simultaneously detect, classify, and quantify multiple hepatic findings on rat liver slide images. All of the SFMs yielded mean average precision (mAP) values above 85%, suggesting that the models had been successfully established. The MFM showed better performance than the SFMs, with a total mAP value of 92.46%. We compared the model predictions for slide images with ground-truth annotations generated by an accredited pathologist. For the MFM, the overall and individual finding predictions were highly correlated with the annotated areas, with R-squared values of 0.852, 0.952, 0.999, 0.990, and 0.958 being obtained for portal area, infiltration, necrosis, vacuolation, and connective tissue (including fibrosis), respectively. Our results indicate that the proposed MFM could be a useful tool for detecting and predicting multiple hepatic findings in basic non-clinical study settings." @default.
- W4387668009 created "2023-10-17" @default.
- W4387668009 creator A5010313638 @default.
- W4387668009 creator A5012234954 @default.
- W4387668009 creator A5019278593 @default.
- W4387668009 creator A5025182744 @default.
- W4387668009 creator A5025919672 @default.
- W4387668009 creator A5038279854 @default.
- W4387668009 creator A5044280753 @default.
- W4387668009 creator A5047466642 @default.
- W4387668009 creator A5047961867 @default.
- W4387668009 creator A5063101015 @default.
- W4387668009 date "2023-10-16" @default.
- W4387668009 modified "2023-10-18" @default.
- W4387668009 title "Application of multiple-finding segmentation utilizing Mask R-CNN-based deep learning in a rat model of drug-induced liver injury" @default.
- W4387668009 cites W1976137269 @default.
- W4387668009 cites W2068103659 @default.
- W4387668009 cites W2091298068 @default.
- W4387668009 cites W2148172086 @default.
- W4387668009 cites W2164898770 @default.
- W4387668009 cites W2234529989 @default.
- W4387668009 cites W2468387181 @default.
- W4387668009 cites W2562119703 @default.
- W4387668009 cites W2566203333 @default.
- W4387668009 cites W2612786437 @default.
- W4387668009 cites W2623033141 @default.
- W4387668009 cites W2806070179 @default.
- W4387668009 cites W2897068067 @default.
- W4387668009 cites W2938545301 @default.
- W4387668009 cites W2947282146 @default.
- W4387668009 cites W2947607756 @default.
- W4387668009 cites W2952846726 @default.
- W4387668009 cites W2964756323 @default.
- W4387668009 cites W2982649258 @default.
- W4387668009 cites W2997774926 @default.
- W4387668009 cites W3002228143 @default.
- W4387668009 cites W3004374095 @default.
- W4387668009 cites W3121943121 @default.
- W4387668009 cites W3206045732 @default.
- W4387668009 cites W3209197169 @default.
- W4387668009 cites W4200022404 @default.
- W4387668009 cites W4283077806 @default.
- W4387668009 cites W4306315062 @default.
- W4387668009 cites W4308885474 @default.
- W4387668009 cites W4309214336 @default.
- W4387668009 doi "https://doi.org/10.1038/s41598-023-44897-8" @default.
- W4387668009 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37845356" @default.
- W4387668009 hasPublicationYear "2023" @default.
- W4387668009 type Work @default.
- W4387668009 citedByCount "0" @default.
- W4387668009 crossrefType "journal-article" @default.
- W4387668009 hasAuthorship W4387668009A5010313638 @default.
- W4387668009 hasAuthorship W4387668009A5012234954 @default.
- W4387668009 hasAuthorship W4387668009A5019278593 @default.
- W4387668009 hasAuthorship W4387668009A5025182744 @default.
- W4387668009 hasAuthorship W4387668009A5025919672 @default.
- W4387668009 hasAuthorship W4387668009A5038279854 @default.
- W4387668009 hasAuthorship W4387668009A5044280753 @default.
- W4387668009 hasAuthorship W4387668009A5047466642 @default.
- W4387668009 hasAuthorship W4387668009A5047961867 @default.
- W4387668009 hasAuthorship W4387668009A5063101015 @default.
- W4387668009 hasBestOaLocation W43876680091 @default.
- W4387668009 hasConcept C108583219 @default.
- W4387668009 hasConcept C142724271 @default.
- W4387668009 hasConcept C146849305 @default.
- W4387668009 hasConcept C153180895 @default.
- W4387668009 hasConcept C154945302 @default.
- W4387668009 hasConcept C2780559512 @default.
- W4387668009 hasConcept C2994217296 @default.
- W4387668009 hasConcept C41008148 @default.
- W4387668009 hasConcept C518705261 @default.
- W4387668009 hasConcept C71924100 @default.
- W4387668009 hasConcept C81363708 @default.
- W4387668009 hasConcept C89600930 @default.
- W4387668009 hasConceptScore W4387668009C108583219 @default.
- W4387668009 hasConceptScore W4387668009C142724271 @default.
- W4387668009 hasConceptScore W4387668009C146849305 @default.
- W4387668009 hasConceptScore W4387668009C153180895 @default.
- W4387668009 hasConceptScore W4387668009C154945302 @default.
- W4387668009 hasConceptScore W4387668009C2780559512 @default.
- W4387668009 hasConceptScore W4387668009C2994217296 @default.
- W4387668009 hasConceptScore W4387668009C41008148 @default.
- W4387668009 hasConceptScore W4387668009C518705261 @default.
- W4387668009 hasConceptScore W4387668009C71924100 @default.
- W4387668009 hasConceptScore W4387668009C81363708 @default.
- W4387668009 hasConceptScore W4387668009C89600930 @default.
- W4387668009 hasFunder F4320322014 @default.
- W4387668009 hasFunder F4320322102 @default.
- W4387668009 hasIssue "1" @default.
- W4387668009 hasLocation W43876680091 @default.
- W4387668009 hasLocation W43876680092 @default.
- W4387668009 hasOpenAccess W4387668009 @default.
- W4387668009 hasPrimaryLocation W43876680091 @default.
- W4387668009 hasRelatedWork W132205291 @default.
- W4387668009 hasRelatedWork W1511403689 @default.
- W4387668009 hasRelatedWork W1990013544 @default.
- W4387668009 hasRelatedWork W2063823869 @default.
- W4387668009 hasRelatedWork W2331614048 @default.
- W4387668009 hasRelatedWork W2337271078 @default.
- W4387668009 hasRelatedWork W2992671606 @default.