FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385808837> ?p ?o ?g. }

• W4385808837 abstract "Abstract Background The aim of this work is to evaluate the performance of radiomics predictions for a range of molecular, genomic and clinical targets in patients with clear cell renal cell carcinoma (ccRCC) and demonstrate the impact of novel feature selection strategies and sub-segmentations on model interpretability. Methods Contrast-enhanced CT scans from the first 101 patients recruited to the TRACERx Renal Cancer study (NCT03226886) were used to derive radiomics classification models to predict 20 molecular, histopathology and clinical target variables. Manual 3D segmentation was used in conjunction with automatic sub-segmentation to generate radiomics features from the core, rim, high and low enhancing sub-regions, and the whole tumour. Comparisons were made between two classification model pipelines: a Conventional pipeline reflecting common radiomics practice, and a Proposed pipeline including two novel feature selection steps designed to improve model interpretability. For both pipelines nested cross-validation was used to estimate prediction performance and tune model hyper-parameters, and permutation testing was used to evaluate the statistical significance of the estimated performance measures. Further model robustness assessments were conducted by evaluating model variability across the cross-validation folds. Results Classification performance was significant ( p < 0.05, H 0 :AUROC = 0.5) for 11 of 20 targets using either pipeline and for these targets the AUROCs were within ± 0.05 for the two pipelines, except for one target where the Proposed pipeline performance increased by > 0.1. Five of these targets (necrosis on histology, presence of renal vein invasion, overall histological stage, linear evolutionary subtype and loss of 9p21.3 somatic alteration marker) had AUROC > 0.8. Models derived using the Proposed pipeline contained fewer feature groups than the Conventional pipeline, leading to more straightforward model interpretations without loss of performance. Sub-segmentations lead to improved performance and/or improved interpretability when predicting the presence of sarcomatoid differentiation and tumour stage. Conclusions Use of the Proposed pipeline, which includes the novel feature selection methods, leads to more interpretable models without compromising prediction performance. Trial registration NCT03226886 (TRACERx Renal)" @default.
• W4385808837 created "2023-08-15" @default.
• W4385808837 creator A5001488915 @default.
• W4385808837 creator A5006732961 @default.
• W4385808837 creator A5018022718 @default.
• W4385808837 creator A5019570474 @default.
• W4385808837 creator A5037269194 @default.
• W4385808837 creator A5040106089 @default.
• W4385808837 creator A5040891058 @default.
• W4385808837 creator A5041244836 @default.
• W4385808837 creator A5047236287 @default.
• W4385808837 creator A5048179253 @default.
• W4385808837 creator A5069398400 @default.
• W4385808837 creator A5076054848 @default.
• W4385808837 creator A5080842961 @default.
• W4385808837 creator A5084139573 @default.
• W4385808837 creator A5090715421 @default.
• W4385808837 date "2023-08-14" @default.
• W4385808837 modified "2023-10-14" @default.
• W4385808837 title "Interpretability of radiomics models is improved when using feature group selection strategies for predicting molecular and clinical targets in clear-cell renal cell carcinoma: insights from the TRACERx Renal study" @default.
• W4385808837 cites W1562548864 @default.
• W4385808837 cites W2138019504 @default.
• W4385808837 cites W2737960652 @default.
• W4385808837 cites W2763355946 @default.
• W4385808837 cites W2767128594 @default.
• W4385808837 cites W2771041964 @default.
• W4385808837 cites W2797282777 @default.
• W4385808837 cites W2797542577 @default.
• W4385808837 cites W2811120089 @default.
• W4385808837 cites W2906817752 @default.
• W4385808837 cites W2911964244 @default.
• W4385808837 cites W2969476445 @default.
• W4385808837 cites W2998789541 @default.
• W4385808837 cites W3008527785 @default.
• W4385808837 cites W3022680805 @default.
• W4385808837 cites W3048802680 @default.
• W4385808837 cites W3111291208 @default.
• W4385808837 cites W3118247837 @default.
• W4385808837 cites W3158340897 @default.
• W4385808837 cites W3163583760 @default.
• W4385808837 cites W3204030525 @default.
• W4385808837 cites W3216823841 @default.
• W4385808837 cites W4200318664 @default.
• W4385808837 cites W4214920103 @default.
• W4385808837 cites W4226136430 @default.
• W4385808837 doi "https://doi.org/10.1186/s40644-023-00594-3" @default.
• W4385808837 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37580840" @default.
• W4385808837 hasPublicationYear "2023" @default.
• W4385808837 type Work @default.
• W4385808837 citedByCount "0" @default.
• W4385808837 crossrefType "journal-article" @default.
• W4385808837 hasAuthorship W4385808837A5001488915 @default.
• W4385808837 hasAuthorship W4385808837A5006732961 @default.
• W4385808837 hasAuthorship W4385808837A5018022718 @default.
• W4385808837 hasAuthorship W4385808837A5019570474 @default.
• W4385808837 hasAuthorship W4385808837A5037269194 @default.
• W4385808837 hasAuthorship W4385808837A5040106089 @default.
• W4385808837 hasAuthorship W4385808837A5040891058 @default.
• W4385808837 hasAuthorship W4385808837A5041244836 @default.
• W4385808837 hasAuthorship W4385808837A5047236287 @default.
• W4385808837 hasAuthorship W4385808837A5048179253 @default.
• W4385808837 hasAuthorship W4385808837A5069398400 @default.
• W4385808837 hasAuthorship W4385808837A5076054848 @default.
• W4385808837 hasAuthorship W4385808837A5080842961 @default.
• W4385808837 hasAuthorship W4385808837A5084139573 @default.
• W4385808837 hasAuthorship W4385808837A5090715421 @default.
• W4385808837 hasBestOaLocation W43858088371 @default.
• W4385808837 hasConcept C119857082 @default.
• W4385808837 hasConcept C126838900 @default.
• W4385808837 hasConcept C143998085 @default.
• W4385808837 hasConcept C148483581 @default.
• W4385808837 hasConcept C153180895 @default.
• W4385808837 hasConcept C154945302 @default.
• W4385808837 hasConcept C199360897 @default.
• W4385808837 hasConcept C2777472916 @default.
• W4385808837 hasConcept C2778559731 @default.
• W4385808837 hasConcept C2781067378 @default.
• W4385808837 hasConcept C41008148 @default.
• W4385808837 hasConcept C43521106 @default.
• W4385808837 hasConcept C71924100 @default.
• W4385808837 hasConceptScore W4385808837C119857082 @default.
• W4385808837 hasConceptScore W4385808837C126838900 @default.
• W4385808837 hasConceptScore W4385808837C143998085 @default.
• W4385808837 hasConceptScore W4385808837C148483581 @default.
• W4385808837 hasConceptScore W4385808837C153180895 @default.
• W4385808837 hasConceptScore W4385808837C154945302 @default.
• W4385808837 hasConceptScore W4385808837C199360897 @default.
• W4385808837 hasConceptScore W4385808837C2777472916 @default.
• W4385808837 hasConceptScore W4385808837C2778559731 @default.
• W4385808837 hasConceptScore W4385808837C2781067378 @default.
• W4385808837 hasConceptScore W4385808837C41008148 @default.
• W4385808837 hasConceptScore W4385808837C43521106 @default.
• W4385808837 hasConceptScore W4385808837C71924100 @default.
• W4385808837 hasFunder F4320308296 @default.
• W4385808837 hasFunder F4320311904 @default.
• W4385808837 hasFunder F4320315071 @default.
• W4385808837 hasFunder F4320316976 @default.
• W4385808837 hasFunder F4320319985 @default.
• W4385808837 hasFunder F4320320320 @default.
• W4385808837 hasFunder F4320338126 @default.

• next