FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317702979> ?p ?o ?g. }

• W4317702979 abstract "Purpose Classifying the subtypes of non-small cell lung cancer (NSCLC) is essential for clinically adopting optimal treatment strategies and improving clinical outcomes, but the histological subtypes are confirmed by invasive biopsy or post-operative examination at present. Based on multi-center data, this study aimed to analyze the importance of extracted CT radiomics features and develop the model with good generalization performance for precisely distinguishing major NSCLC subtypes: adenocarcinoma (ADC) and squamous cell carcinoma (SCC). Methods We collected a multi-center CT dataset with 868 patients from eight international databases on the cancer imaging archive (TCIA). Among them, patients from five databases were mixed and split to training and test sets (560:140). The remaining three databases were used as independent test sets: TCGA set (n = 97) and lung3 set (n = 71). A total of 1409 features containing shape, intensity, and texture information were extracted from tumor volume of interest (VOI), then the ℓ2,1-norm minimization was used for feature selection and the importance of selected features was analyzed. Next, the prediction and generalization performance of 130 radiomics models (10 common algorithms and 120 heterogeneous ensemble combinations) were compared by the average AUC value on three test sets. Finally, predictive results of the optimal model were shown. Results After feature selection, 401 features were obtained. Features of intensity, texture GLCM, GLRLM, and GLSZM had higher classification weight coefficients than other features (shape, texture GLDM, and NGTDM), and the filtered image features exhibited significant importance than original image features (p-value = 0.0210). Moreover, five ensemble learning algorithms (Bagging, AdaBoost, RF, XGBoost, GBDT) had better generalization performance (p-value = 0.00418) than other non-ensemble algorithms (MLP, LR, GNB, SVM, KNN). The Bagging-AdaBoost-SVM model had the highest AUC value (0.815 ± 0.010) on three test sets. It obtained AUC values of 0.819, 0.823, and 0.804 on test set, TCGA set and lung3 set, respectively. Conclusion Our multi-dataset study showed that intensity features, texture features (GLCM, GLRLM, and GLSZM) and filtered image features were more important for distinguishing ADCs from SCCs. The method of ensemble learning can improve the prediction and generalization performance on the complicated multi-center data. The Bagging-AdaBoost-SVM model had the strongest generalization performance, and it showed promising clinical value for non-invasively predicting the histopathological subtypes of NSCLC." @default.
• W4317702979 created "2023-01-22" @default.
• W4317702979 creator A5012225901 @default.
• W4317702979 creator A5017292224 @default.
• W4317702979 creator A5025394425 @default.
• W4317702979 creator A5029360035 @default.
• W4317702979 creator A5048279362 @default.
• W4317702979 creator A5058682934 @default.
• W4317702979 creator A5073040834 @default.
• W4317702979 creator A5081071540 @default.
• W4317702979 creator A5086792600 @default.
• W4317702979 date "2023-02-01" @default.
• W4317702979 modified "2023-09-30" @default.
• W4317702979 title "Radiomics feature analysis and model research for predicting histopathological subtypes of non‐small cell lung cancer on CT images: A multi‐dataset study" @default.
• W4317702979 cites W127599202 @default.
• W4317702979 cites W1757407923 @default.
• W4317702979 cites W1929984647 @default.
• W4317702979 cites W1964620951 @default.
• W4317702979 cites W2013646469 @default.
• W4317702979 cites W2079650299 @default.
• W4317702979 cites W2083927153 @default.
• W4317702979 cites W2085944479 @default.
• W4317702979 cites W2087448554 @default.
• W4317702979 cites W2095699480 @default.
• W4317702979 cites W2103004421 @default.
• W4317702979 cites W2113996837 @default.
• W4317702979 cites W2146633923 @default.
• W4317702979 cites W2174661749 @default.
• W4317702979 cites W2184779060 @default.
• W4317702979 cites W2333277922 @default.
• W4317702979 cites W2346265746 @default.
• W4317702979 cites W2461805626 @default.
• W4317702979 cites W2466662830 @default.
• W4317702979 cites W2616814208 @default.
• W4317702979 cites W2763355946 @default.
• W4317702979 cites W2767128594 @default.
• W4317702979 cites W2773826958 @default.
• W4317702979 cites W2788673917 @default.
• W4317702979 cites W2791459212 @default.
• W4317702979 cites W2796027894 @default.
• W4317702979 cites W2805630508 @default.
• W4317702979 cites W2921044437 @default.
• W4317702979 cites W2940053266 @default.
• W4317702979 cites W2985928856 @default.
• W4317702979 cites W2996024270 @default.
• W4317702979 cites W3005696256 @default.
• W4317702979 cites W3018666800 @default.
• W4317702979 cites W3038885939 @default.
• W4317702979 cites W3048173156 @default.
• W4317702979 cites W3158551918 @default.
• W4317702979 cites W3175762528 @default.
• W4317702979 doi "https://doi.org/10.1002/mp.16233" @default.
• W4317702979 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36682051" @default.
• W4317702979 hasPublicationYear "2023" @default.
• W4317702979 type Work @default.
• W4317702979 citedByCount "3" @default.
• W4317702979 countsByYear W43177029792023 @default.
• W4317702979 crossrefType "journal-article" @default.
• W4317702979 hasAuthorship W4317702979A5012225901 @default.
• W4317702979 hasAuthorship W4317702979A5017292224 @default.
• W4317702979 hasAuthorship W4317702979A5025394425 @default.
• W4317702979 hasAuthorship W4317702979A5029360035 @default.
• W4317702979 hasAuthorship W4317702979A5048279362 @default.
• W4317702979 hasAuthorship W4317702979A5058682934 @default.
• W4317702979 hasAuthorship W4317702979A5073040834 @default.
• W4317702979 hasAuthorship W4317702979A5081071540 @default.
• W4317702979 hasAuthorship W4317702979A5086792600 @default.
• W4317702979 hasConcept C121608353 @default.
• W4317702979 hasConcept C126322002 @default.
• W4317702979 hasConcept C138885662 @default.
• W4317702979 hasConcept C143998085 @default.
• W4317702979 hasConcept C148483581 @default.
• W4317702979 hasConcept C153180895 @default.
• W4317702979 hasConcept C154945302 @default.
• W4317702979 hasConcept C169903167 @default.
• W4317702979 hasConcept C2776256026 @default.
• W4317702979 hasConcept C2776401178 @default.
• W4317702979 hasConcept C2778559731 @default.
• W4317702979 hasConcept C2994114330 @default.
• W4317702979 hasConcept C41008148 @default.
• W4317702979 hasConcept C41895202 @default.
• W4317702979 hasConcept C58489278 @default.
• W4317702979 hasConcept C71924100 @default.
• W4317702979 hasConceptScore W4317702979C121608353 @default.
• W4317702979 hasConceptScore W4317702979C126322002 @default.
• W4317702979 hasConceptScore W4317702979C138885662 @default.
• W4317702979 hasConceptScore W4317702979C143998085 @default.
• W4317702979 hasConceptScore W4317702979C148483581 @default.
• W4317702979 hasConceptScore W4317702979C153180895 @default.
• W4317702979 hasConceptScore W4317702979C154945302 @default.
• W4317702979 hasConceptScore W4317702979C169903167 @default.
• W4317702979 hasConceptScore W4317702979C2776256026 @default.
• W4317702979 hasConceptScore W4317702979C2776401178 @default.
• W4317702979 hasConceptScore W4317702979C2778559731 @default.
• W4317702979 hasConceptScore W4317702979C2994114330 @default.
• W4317702979 hasConceptScore W4317702979C41008148 @default.
• W4317702979 hasConceptScore W4317702979C41895202 @default.
• W4317702979 hasConceptScore W4317702979C58489278 @default.
• W4317702979 hasConceptScore W4317702979C71924100 @default.
• W4317702979 hasFunder F4320321001 @default.

• next