FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094348081> ?p ?o ?g. }

• W3094348081 endingPage "e613" @default.
• W3094348081 startingPage "e612" @default.
• W3094348081 abstract "To utilize Artificial Neural Networks (ANN) to predict pathological response after neoadjuvant chemoradiation (NACRT), based on Radiomics data extracted from pre-NACRT Computed Tomography (CT) datasets. Between 2013 to 2019, 201 patients with Stage II-IVa esophageal carcinoma underwent NACRT followed by radical esophagectomy at our institution, out of which 97 patients were randomly selected to form our study cohort. All patients received radiotherapy [median dose: 41.4 Gy (Range: 39.6-50.4) / 23 Fx (Range: 22-28)] via IMRT or 3DCRT technique and concurrent weekly platinum & taxane-based chemotherapy [Median cycles: 5 (Range: 1-6)]. 55 patients achieved a pathological complete response (pCR). The pre-NACRT CT datasets of 97 patients (in DICOM-RT format) underwent the following sequence for Radiomics feature extraction: (1) gross tumor volume delineation by a single radiation oncologist; (2) image pre-processing and standardization; (3) image import into Computation Environment for Radiation Research, and; (4) engineered radiomics feature extraction (compliant with the Imaging Biomarker Standardization Initiative). Feature selection before ANN modelling was performed using Random Forest (RF) classifier, to avoid over-fitting multi-dimensional radiomics data. 1000-fold bootstrapping was applied to correct for the variance inherent with RF. Features with ≥ 95% probability of predicting the pathological outcome (pCR present/absent) were selected and subjected to multivariable logistic regression for additional dimensionality reduction (features with p < 0.05 were selected), to match the size our study cohort. ANN-based predictive modelling [using Multi-Layer Perceptron (MLP) network] split the entire cohort into training and validation datasets, with the pathological outcome (pCR present/absent) as the binary output layer. 2 hidden layers were utilized, activated by hyperbolic tangent function. Softmax activation was used in the output layer. The predictive accuracy of the generated model was assessed by an Area Under Curve (AUC) analysis. A total of 254 features were extracted from each patient’s CT dataset. RF yielded 15 features with ≥ 95% probability of predicting pathological outcome, and following multivariable logistic regression, 7 features served as the input layer for the MLP model. The selected features described the sphericity and 3-dimensional higher-order features associated with the tumor. The overall accuracy of the model was 80% and 77.8% in the training and validation cohort, respectively (AUC = 0.87). ANN-based predictive modelling of pathological outcome after NACRT for esophageal carcinomas, utilizing only Radiomic features (after appropriate dimensionality reduction) is feasible and warrants further investigation." @default.
• W3094348081 created "2020-10-29" @default.
• W3094348081 creator A5011546218 @default.
• W3094348081 creator A5030641531 @default.
• W3094348081 creator A5046956814 @default.
• W3094348081 creator A5048552476 @default.
• W3094348081 creator A5074441939 @default.
• W3094348081 creator A5091066647 @default.
• W3094348081 date "2020-11-01" @default.
• W3094348081 modified "2023-09-23" @default.
• W3094348081 title "Pathological Response Prediction To Neo-Adjuvant Chemoradiation In Esophageal Carcinoma Using Artificial Intelligence And Radiomics: An Exploratory Analysis" @default.
• W3094348081 doi "https://doi.org/10.1016/j.ijrobp.2020.07.1860" @default.
• W3094348081 hasPublicationYear "2020" @default.
• W3094348081 type Work @default.
• W3094348081 sameAs 3094348081 @default.
• W3094348081 citedByCount "1" @default.
• W3094348081 countsByYear W30943480812023 @default.
• W3094348081 crossrefType "journal-article" @default.
• W3094348081 hasAuthorship W3094348081A5011546218 @default.
• W3094348081 hasAuthorship W3094348081A5030641531 @default.
• W3094348081 hasAuthorship W3094348081A5046956814 @default.
• W3094348081 hasAuthorship W3094348081A5048552476 @default.
• W3094348081 hasAuthorship W3094348081A5074441939 @default.
• W3094348081 hasAuthorship W3094348081A5091066647 @default.
• W3094348081 hasBestOaLocation W30943480811 @default.
• W3094348081 hasConcept C126322002 @default.
• W3094348081 hasConcept C126838900 @default.
• W3094348081 hasConcept C151956035 @default.
• W3094348081 hasConcept C154945302 @default.
• W3094348081 hasConcept C2778559731 @default.
• W3094348081 hasConcept C2989005 @default.
• W3094348081 hasConcept C41008148 @default.
• W3094348081 hasConcept C509974204 @default.
• W3094348081 hasConcept C71924100 @default.
• W3094348081 hasConceptScore W3094348081C126322002 @default.
• W3094348081 hasConceptScore W3094348081C126838900 @default.
• W3094348081 hasConceptScore W3094348081C151956035 @default.
• W3094348081 hasConceptScore W3094348081C154945302 @default.
• W3094348081 hasConceptScore W3094348081C2778559731 @default.
• W3094348081 hasConceptScore W3094348081C2989005 @default.
• W3094348081 hasConceptScore W3094348081C41008148 @default.
• W3094348081 hasConceptScore W3094348081C509974204 @default.
• W3094348081 hasConceptScore W3094348081C71924100 @default.
• W3094348081 hasIssue "3" @default.
• W3094348081 hasLocation W30943480811 @default.
• W3094348081 hasOpenAccess W3094348081 @default.
• W3094348081 hasPrimaryLocation W30943480811 @default.
• W3094348081 hasRelatedWork W141524600 @default.
• W3094348081 hasRelatedWork W1841185769 @default.
• W3094348081 hasRelatedWork W1999397587 @default.
• W3094348081 hasRelatedWork W2021771973 @default.
• W3094348081 hasRelatedWork W2022944059 @default.
• W3094348081 hasRelatedWork W2070138482 @default.
• W3094348081 hasRelatedWork W2155887765 @default.
• W3094348081 hasRelatedWork W2168923614 @default.
• W3094348081 hasRelatedWork W2384708512 @default.
• W3094348081 hasRelatedWork W2428341374 @default.
• W3094348081 hasVolume "108" @default.
• W3094348081 isParatext "false" @default.
• W3094348081 isRetracted "false" @default.
• W3094348081 magId "3094348081" @default.
• W3094348081 workType "article" @default.