Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220884013> ?p ?o ?g. }
- W4220884013 endingPage "153303382210878" @default.
- W4220884013 startingPage "153303382210878" @default.
- W4220884013 abstract "Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR images of 140 female patients with mass-like breast lesions (70 benign and 70 malignant), consisting of Dynamic Contrast Enhanced (DCE) and T2-weighted sequences, and the Apparent Diffusion Coefficient (ADC) calculated from the Diffusion Weighted Imaging (DWI) sequence. Tumor masks were manually defined in all consecutive slices of the respective MRI volumes and 3D radiomic features were extracted with the Pyradiomics package. Feature dimensionality reduction was based on statistical tests and the Boruta wrapper. Hierarchical Clustering on Spearman's rank correlation coefficients between features and Random Forest classification for obtaining feature importance, were implemented for selecting the final feature subset. Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) classifiers, were trained and tested with bootstrap validation in differentiating breast lesions. A Support Vector Machine (SVM) classifier was also exploited for comparison. The Receiver Operator Characteristic (ROC) curves and DeLong's test were utilized to evaluate the classification performances. Results: The final feature subset consisted of 5 features derived from the lesion shape and the first order histogram of DCE and ADC images volumes. XGboost and LGBM achieved statistically significantly higher average classification performances [AUC = 0.95 and 0.94 respectively], followed by Adaboost [AUC = 0.90], GB [AUC = 0.89] and SVM [AUC = 0.88]. Conclusion: Overall, the integration of Ensemble Learning methods within mpMRI radiomic analysis can improve the performance of computer-assisted diagnosis of breast cancer lesions." @default.
- W4220884013 created "2022-04-03" @default.
- W4220884013 creator A5003698235 @default.
- W4220884013 creator A5003988908 @default.
- W4220884013 creator A5021257378 @default.
- W4220884013 creator A5058869899 @default.
- W4220884013 creator A5077605061 @default.
- W4220884013 date "2022-01-01" @default.
- W4220884013 modified "2023-10-14" @default.
- W4220884013 title "Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods" @default.
- W4220884013 cites W1988790447 @default.
- W4220884013 cites W2011301426 @default.
- W4220884013 cites W2049013109 @default.
- W4220884013 cites W2059796825 @default.
- W4220884013 cites W2156665896 @default.
- W4220884013 cites W2328176404 @default.
- W4220884013 cites W2593591744 @default.
- W4220884013 cites W2632817523 @default.
- W4220884013 cites W2767128594 @default.
- W4220884013 cites W2802611745 @default.
- W4220884013 cites W2803768410 @default.
- W4220884013 cites W2891752665 @default.
- W4220884013 cites W2898574163 @default.
- W4220884013 cites W2898948611 @default.
- W4220884013 cites W2899287920 @default.
- W4220884013 cites W2904778411 @default.
- W4220884013 cites W2912128568 @default.
- W4220884013 cites W2960473173 @default.
- W4220884013 cites W2961148067 @default.
- W4220884013 cites W2963716858 @default.
- W4220884013 cites W2971334062 @default.
- W4220884013 cites W2979078804 @default.
- W4220884013 cites W2981380606 @default.
- W4220884013 cites W2981783341 @default.
- W4220884013 cites W2982478384 @default.
- W4220884013 cites W2985260969 @default.
- W4220884013 cites W2985755379 @default.
- W4220884013 cites W2990944862 @default.
- W4220884013 cites W2991592623 @default.
- W4220884013 cites W2998789541 @default.
- W4220884013 cites W3006372133 @default.
- W4220884013 cites W3080773387 @default.
- W4220884013 cites W3081032187 @default.
- W4220884013 cites W3082011984 @default.
- W4220884013 cites W3093472376 @default.
- W4220884013 cites W3095170425 @default.
- W4220884013 cites W3105457166 @default.
- W4220884013 cites W3119003305 @default.
- W4220884013 cites W3128646645 @default.
- W4220884013 cites W3128968837 @default.
- W4220884013 cites W3138919133 @default.
- W4220884013 cites W3165125143 @default.
- W4220884013 cites W3172367553 @default.
- W4220884013 cites W3174711868 @default.
- W4220884013 doi "https://doi.org/10.1177/15330338221087828" @default.
- W4220884013 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35341421" @default.
- W4220884013 hasPublicationYear "2022" @default.
- W4220884013 type Work @default.
- W4220884013 citedByCount "8" @default.
- W4220884013 countsByYear W42208840132022 @default.
- W4220884013 countsByYear W42208840132023 @default.
- W4220884013 crossrefType "journal-article" @default.
- W4220884013 hasAuthorship W4220884013A5003698235 @default.
- W4220884013 hasAuthorship W4220884013A5003988908 @default.
- W4220884013 hasAuthorship W4220884013A5021257378 @default.
- W4220884013 hasAuthorship W4220884013A5058869899 @default.
- W4220884013 hasAuthorship W4220884013A5077605061 @default.
- W4220884013 hasBestOaLocation W42208840131 @default.
- W4220884013 hasConcept C115961682 @default.
- W4220884013 hasConcept C119857082 @default.
- W4220884013 hasConcept C121608353 @default.
- W4220884013 hasConcept C12267149 @default.
- W4220884013 hasConcept C126322002 @default.
- W4220884013 hasConcept C126838900 @default.
- W4220884013 hasConcept C141404830 @default.
- W4220884013 hasConcept C143409427 @default.
- W4220884013 hasConcept C153180895 @default.
- W4220884013 hasConcept C154945302 @default.
- W4220884013 hasConcept C169258074 @default.
- W4220884013 hasConcept C2777111374 @default.
- W4220884013 hasConcept C2780472235 @default.
- W4220884013 hasConcept C33923547 @default.
- W4220884013 hasConcept C41008148 @default.
- W4220884013 hasConcept C46686674 @default.
- W4220884013 hasConcept C530470458 @default.
- W4220884013 hasConcept C53533937 @default.
- W4220884013 hasConcept C58471807 @default.
- W4220884013 hasConcept C70153297 @default.
- W4220884013 hasConcept C71924100 @default.
- W4220884013 hasConceptScore W4220884013C115961682 @default.
- W4220884013 hasConceptScore W4220884013C119857082 @default.
- W4220884013 hasConceptScore W4220884013C121608353 @default.
- W4220884013 hasConceptScore W4220884013C12267149 @default.
- W4220884013 hasConceptScore W4220884013C126322002 @default.
- W4220884013 hasConceptScore W4220884013C126838900 @default.
- W4220884013 hasConceptScore W4220884013C141404830 @default.
- W4220884013 hasConceptScore W4220884013C143409427 @default.
- W4220884013 hasConceptScore W4220884013C153180895 @default.