Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378902057> ?p ?o ?g. }
- W4378902057 endingPage "3000" @default.
- W4378902057 startingPage "3000" @default.
- W4378902057 abstract "Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC.We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets.In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771-0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661-0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827-0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725-0.801) and 0.746 (95% CI, 0.687-0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence.Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation." @default.
- W4378902057 created "2023-06-01" @default.
- W4378902057 creator A5007651007 @default.
- W4378902057 creator A5008732060 @default.
- W4378902057 creator A5018072854 @default.
- W4378902057 creator A5029729399 @default.
- W4378902057 creator A5030584766 @default.
- W4378902057 creator A5041245981 @default.
- W4378902057 creator A5060073834 @default.
- W4378902057 creator A5060300868 @default.
- W4378902057 creator A5073216396 @default.
- W4378902057 creator A5073531557 @default.
- W4378902057 creator A5074480744 @default.
- W4378902057 creator A5074754590 @default.
- W4378902057 creator A5074885577 @default.
- W4378902057 creator A5081525840 @default.
- W4378902057 creator A5083873109 @default.
- W4378902057 date "2023-05-31" @default.
- W4378902057 modified "2023-10-16" @default.
- W4378902057 title "Predicting Lymph Node Metastasis Status from Primary Muscle-Invasive Bladder Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter Study" @default.
- W4378902057 cites W1513738801 @default.
- W4378902057 cites W1532736374 @default.
- W4378902057 cites W1533597471 @default.
- W4378902057 cites W1556453357 @default.
- W4378902057 cites W1604908658 @default.
- W4378902057 cites W1976431370 @default.
- W4378902057 cites W1984041346 @default.
- W4378902057 cites W1986277796 @default.
- W4378902057 cites W2010464208 @default.
- W4378902057 cites W2026291233 @default.
- W4378902057 cites W2029463742 @default.
- W4378902057 cites W2033820276 @default.
- W4378902057 cites W2040973221 @default.
- W4378902057 cites W2064741553 @default.
- W4378902057 cites W2078153809 @default.
- W4378902057 cites W2099060071 @default.
- W4378902057 cites W2099144920 @default.
- W4378902057 cites W2103561213 @default.
- W4378902057 cites W2113156769 @default.
- W4378902057 cites W2123981884 @default.
- W4378902057 cites W2194775991 @default.
- W4378902057 cites W2234281713 @default.
- W4378902057 cites W2328176404 @default.
- W4378902057 cites W2460380162 @default.
- W4378902057 cites W2727910366 @default.
- W4378902057 cites W2753148287 @default.
- W4378902057 cites W2789929722 @default.
- W4378902057 cites W2794486200 @default.
- W4378902057 cites W2807001445 @default.
- W4378902057 cites W2885554167 @default.
- W4378902057 cites W2885882002 @default.
- W4378902057 cites W2895379365 @default.
- W4378902057 cites W2959497269 @default.
- W4378902057 cites W2965620020 @default.
- W4378902057 cites W2983607390 @default.
- W4378902057 cites W3018428662 @default.
- W4378902057 cites W3018647685 @default.
- W4378902057 cites W3023288864 @default.
- W4378902057 cites W3048201207 @default.
- W4378902057 cites W3082869825 @default.
- W4378902057 cites W3097228551 @default.
- W4378902057 cites W3109246949 @default.
- W4378902057 cites W3128646645 @default.
- W4378902057 cites W3134004666 @default.
- W4378902057 cites W3138591331 @default.
- W4378902057 cites W3160261825 @default.
- W4378902057 cites W3162760820 @default.
- W4378902057 cites W3167219111 @default.
- W4378902057 cites W3206785039 @default.
- W4378902057 cites W3207232829 @default.
- W4378902057 cites W3210482027 @default.
- W4378902057 cites W4211053712 @default.
- W4378902057 cites W4211115520 @default.
- W4378902057 cites W4281765271 @default.
- W4378902057 cites W4282966980 @default.
- W4378902057 cites W4284891742 @default.
- W4378902057 cites W4293153457 @default.
- W4378902057 cites W4306969519 @default.
- W4378902057 cites W4310172146 @default.
- W4378902057 cites W4311045302 @default.
- W4378902057 cites W4318833929 @default.
- W4378902057 cites W4318991799 @default.
- W4378902057 doi "https://doi.org/10.3390/cancers15113000" @default.
- W4378902057 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37296961" @default.
- W4378902057 hasPublicationYear "2023" @default.
- W4378902057 type Work @default.
- W4378902057 citedByCount "1" @default.
- W4378902057 crossrefType "journal-article" @default.
- W4378902057 hasAuthorship W4378902057A5007651007 @default.
- W4378902057 hasAuthorship W4378902057A5008732060 @default.
- W4378902057 hasAuthorship W4378902057A5018072854 @default.
- W4378902057 hasAuthorship W4378902057A5029729399 @default.
- W4378902057 hasAuthorship W4378902057A5030584766 @default.
- W4378902057 hasAuthorship W4378902057A5041245981 @default.
- W4378902057 hasAuthorship W4378902057A5060073834 @default.
- W4378902057 hasAuthorship W4378902057A5060300868 @default.
- W4378902057 hasAuthorship W4378902057A5073216396 @default.
- W4378902057 hasAuthorship W4378902057A5073531557 @default.