Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094429483> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3094429483 endingPage "e284" @default.
- W3094429483 startingPage "e284" @default.
- W3094429483 abstract "Radiomics utilizes high-throughput mining of medical imaging data to extract unique information and predict tumor behavior. Currently available clinical prediction models poorly predict treatment outcomes in pancreatic adenocarcinoma. Therefore, we used radiomic features of primary pancreatic tumors to develop outcome prediction models and compared them to traditional clinical models. We extracted and analyzed radiomics data from the contrast-enhanced simulation CTs of 74 borderline resectable and locally advanced pancreatic cancer patients that received stereotactic body radiotherapy. Images were acquired with the same protocol on the same scanner, and the tumors were manually segmented following the same guideline designed for this project excluding uncertain regions. A panel of over 800 radiomic features was screened to create overall survival and local-regional recurrence prediction models following an embedded feature selection pipeline with 1000-round 2/3 subsampling. For both endpoints, the radiomic model was compared to a clinical prediction model (resection status, T stage, N stage, gender, and tumor location) and a model combining radiomic and clinical information. Comparisons were made using Harrell concordance index (CI) and area under the receiver operating curves (AUCs) in 500-time nested 3-fold cross-validations. Patients were clustered into 4 clusters with the radiomic expression patterns and compared against clinical parameters, with association found only with resection status (p = 0.049). A 6-feature radiomic signature was identified to have the best prediction for overall survival. Mean validation CI of 0.66, 0.54, and 0.68 was achieved by the radiomic, clinical, and combined model respectively. Similarly, a 7-feature radiomic signature best predicted recurrence with mean validation AUC of 0.78, 0.66 and 0.77 for the radiomic, clinical, and combined model. The radiomic models successfully predicted risk groups for both survival and recurrence on validation sets with p<10-4. Overall survival and recurrence can be better predicted with models based on radiomic signatures than with those based on clinical features for pancreatic cancer." @default.
- W3094429483 created "2020-10-29" @default.
- W3094429483 creator A5000912631 @default.
- W3094429483 creator A5005493598 @default.
- W3094429483 creator A5006831359 @default.
- W3094429483 creator A5013487234 @default.
- W3094429483 creator A5018141029 @default.
- W3094429483 creator A5026061991 @default.
- W3094429483 creator A5048041365 @default.
- W3094429483 creator A5059620664 @default.
- W3094429483 creator A5059670664 @default.
- W3094429483 creator A5067786500 @default.
- W3094429483 creator A5081515655 @default.
- W3094429483 creator A5088063040 @default.
- W3094429483 date "2020-11-01" @default.
- W3094429483 modified "2023-09-27" @default.
- W3094429483 title "Radiomics-Based Survival and Recurrence Prediction for Pancreatic Cancer Following Stereotactic Body Radiotherapy" @default.
- W3094429483 doi "https://doi.org/10.1016/j.ijrobp.2020.07.680" @default.
- W3094429483 hasPublicationYear "2020" @default.
- W3094429483 type Work @default.
- W3094429483 sameAs 3094429483 @default.
- W3094429483 citedByCount "0" @default.
- W3094429483 crossrefType "journal-article" @default.
- W3094429483 hasAuthorship W3094429483A5000912631 @default.
- W3094429483 hasAuthorship W3094429483A5005493598 @default.
- W3094429483 hasAuthorship W3094429483A5006831359 @default.
- W3094429483 hasAuthorship W3094429483A5013487234 @default.
- W3094429483 hasAuthorship W3094429483A5018141029 @default.
- W3094429483 hasAuthorship W3094429483A5026061991 @default.
- W3094429483 hasAuthorship W3094429483A5048041365 @default.
- W3094429483 hasAuthorship W3094429483A5059620664 @default.
- W3094429483 hasAuthorship W3094429483A5059670664 @default.
- W3094429483 hasAuthorship W3094429483A5067786500 @default.
- W3094429483 hasAuthorship W3094429483A5081515655 @default.
- W3094429483 hasAuthorship W3094429483A5088063040 @default.
- W3094429483 hasBestOaLocation W30944294831 @default.
- W3094429483 hasConcept C121608353 @default.
- W3094429483 hasConcept C126322002 @default.
- W3094429483 hasConcept C126838900 @default.
- W3094429483 hasConcept C138885662 @default.
- W3094429483 hasConcept C146357865 @default.
- W3094429483 hasConcept C151730666 @default.
- W3094429483 hasConcept C160798450 @default.
- W3094429483 hasConcept C2776401178 @default.
- W3094429483 hasConcept C2778559731 @default.
- W3094429483 hasConcept C2780210213 @default.
- W3094429483 hasConcept C41895202 @default.
- W3094429483 hasConcept C58471807 @default.
- W3094429483 hasConcept C71924100 @default.
- W3094429483 hasConcept C86803240 @default.
- W3094429483 hasConceptScore W3094429483C121608353 @default.
- W3094429483 hasConceptScore W3094429483C126322002 @default.
- W3094429483 hasConceptScore W3094429483C126838900 @default.
- W3094429483 hasConceptScore W3094429483C138885662 @default.
- W3094429483 hasConceptScore W3094429483C146357865 @default.
- W3094429483 hasConceptScore W3094429483C151730666 @default.
- W3094429483 hasConceptScore W3094429483C160798450 @default.
- W3094429483 hasConceptScore W3094429483C2776401178 @default.
- W3094429483 hasConceptScore W3094429483C2778559731 @default.
- W3094429483 hasConceptScore W3094429483C2780210213 @default.
- W3094429483 hasConceptScore W3094429483C41895202 @default.
- W3094429483 hasConceptScore W3094429483C58471807 @default.
- W3094429483 hasConceptScore W3094429483C71924100 @default.
- W3094429483 hasConceptScore W3094429483C86803240 @default.
- W3094429483 hasIssue "3" @default.
- W3094429483 hasLocation W30944294831 @default.
- W3094429483 hasOpenAccess W3094429483 @default.
- W3094429483 hasPrimaryLocation W30944294831 @default.
- W3094429483 hasRelatedWork W2155887765 @default.
- W3094429483 hasRelatedWork W2356105190 @default.
- W3094429483 hasRelatedWork W3032642352 @default.
- W3094429483 hasRelatedWork W3093181812 @default.
- W3094429483 hasRelatedWork W3140157847 @default.
- W3094429483 hasRelatedWork W3155205237 @default.
- W3094429483 hasRelatedWork W4210344342 @default.
- W3094429483 hasRelatedWork W4283707141 @default.
- W3094429483 hasRelatedWork W4284989026 @default.
- W3094429483 hasRelatedWork W4290466999 @default.
- W3094429483 hasVolume "108" @default.
- W3094429483 isParatext "false" @default.
- W3094429483 isRetracted "false" @default.
- W3094429483 magId "3094429483" @default.
- W3094429483 workType "article" @default.