External validation of a CT-based radiomics signature in oropharyngeal cancer: Assessing sources of variation

Philipp Guevorguian; Tricia Chinnery; Pencilla Lang; Anthony Nichols; Sarah A Mattonen

doi:10.1016/j.radonc.2022.11.023

External validation of a CT-based radiomics signature in oropharyngeal cancer: Assessing sources of variation

Radiother Oncol. 2023 Jan:178:109434. doi: 10.1016/j.radonc.2022.11.023. Epub 2022 Dec 1.

Authors

Philipp Guevorguian¹, Tricia Chinnery², Pencilla Lang³, Anthony Nichols⁴, Sarah A Mattonen⁵

Affiliations

¹ Department of Medical Biophysics, Western University, 1151 Richmond Street, London, ON, Canada; Baines Imaging Research Laboratory, 800 Commissioners Road East, London, ON, Canada. Electronic address: Pguevorg@uwo.ca.
² Department of Medical Biophysics, Western University, 1151 Richmond Street, London, ON, Canada; Baines Imaging Research Laboratory, 800 Commissioners Road East, London, ON, Canada. Electronic address: Tchinne@uwo.ca.
³ Department of Oncology, Western University, 1151 Richmond Street, London, ON, Canada. Electronic address: Pencilla.Lang@lhsc.on.ca.
⁴ Department of Otolaryngology, Western University, 1151 Richmond Street, London, ON, Canada. Electronic address: Anthony.Nichols@lhsc.on.ca.
⁵ Department of Medical Biophysics, Western University, 1151 Richmond Street, London, ON, Canada; Baines Imaging Research Laboratory, 800 Commissioners Road East, London, ON, Canada; Department of Oncology, Western University, 1151 Richmond Street, London, ON, Canada. Electronic address: sarah.mattonen@uwo.ca.

PMID: 36464179
DOI: 10.1016/j.radonc.2022.11.023

Abstract

Background and purpose: Radiomics is a high-throughput approach that allows for quantitative analysis of imaging data for prognostic applications. Medical images are used in oropharyngeal cancer (OPC) diagnosis and treatment planning and these images may contain prognostic information allowing for treatment personalization. However, the lack of validated models has been a barrier to the translation of radiomic research to the clinic. We hypothesize that a previously developed radiomics model for risk stratification in OPC can be validated in a local dataset.

Materials and methods: The radiomics signature predicting overall survival incorporates features derived from the primary gross tumor volume of OPC patients treated with radiation +/- chemotherapy at a single institution (n = 343). Model fit, calibration, discrimination, and utility were evaluated. The signature was compared with a clinical model using overall stage and a model incorporating both radiomics and clinical data. A model detecting dental artifacts on computed tomography images was also validated.

Results: The radiomics signature had a Concordance index (C-index) of 0.66 comparable to the clinical model's C-index of 0.65. The combined model significantly outperformed (C-index of 0.69, p = 0.024) the clinical model, suggesting that radiomics provides added value. The dental artifact model demonstrated strong ability in detecting dental artifacts with an area under the curve of 0.87.

Conclusion: This work demonstrates model performance comparable to previous validation work and provides a framework for future independent and multi-center validation efforts. With sufficient validation, radiomic models have the potential to improve traditional systems of risk stratification, treatment personalization and patient outcomes.

Keywords: Computed tomography; Machine learning; Oropharyngeal cancer; Overall survival; Radiomics; Validation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Humans
Oropharyngeal Neoplasms* / diagnostic imaging
Oropharyngeal Neoplasms* / therapy
Prognosis
Retrospective Studies
Tomography, X-Ray Computed*