Back to Search Start Over

Prognostic value of PET/CT and MR-based baseline radiomics among patients with Nasopharyngeal Carcinoma

Authors :
Roshini Kulanthaivelu
Andres Kohan
Ricarda Hinzpeter
Zhihui Amy Liu
Andrew Hope
Shao Hui Huang
John Waldron
Brian O'Sullivan
Claudia Ortega
Ur Metser
Patrick Veit-Haibach
Publication Year :
2022
Publisher :
Research Square Platform LLC, 2022.

Abstract

PurposeRadiomics is an emerging imaging assessment technique, which has shown promise predicting survival among nasopharyngeal carcinoma (NPC) patients. Studies so far have focused on MR-based radiomic analysis. The aim of our study was to evaluate the prognostic value of clinical and radiomic parameters derived from both PET/CT and MR.MethodsRetrospective evaluation of 124 NPC patients with PET/CT and radiotherapy planning MR (RP-MR). Primary tumors were segmented using dedicated software (LIFEx .version 6.1) from PET, CT, contrast enhanced T1-weighted (T1-w), and T2-weighted (T2-w) MR sequences with 376 radiomic features extracted. Summary statistics described patient, disease and treatment characteristics. Kaplan Meier (KM) method estimated overall survival (OS) and progression free survival (PFS). Clinical factors selected based on univariate analysis and multivariate Cox model were subsequently constructed with radiomic features added.ResultsThe final models comparing clinical, clinical + RP-MR, clinical + PET/CT and clinical + RP-MR + PET/CT for OS and PFS demonstrated that combined radiomics signatures were significantly associated with improved survival prognostication (AUC 0.62 vs 0.81 vs 0.75 vs 0.86 at 21 months for PFS and 0.56 vs 0.85 vs 0.79 vs 0.96 at 24 months for OS). Clinical + RP-MR features initially outperform clinical + PET/CT for both OS and PFS ( 42 months).ConclusionOur study demonstrated that PET/CT-based radiomic features may improve survival prognostication among NPC patients when combined with baseline clinical and MR-based radiomic features.

Details

Database :
OpenAIRE
Accession number :
edsair.doi...........6331db9f2f0759d2c2cd443a4e12f40b