Vulnerabilities of radiomic signature development: The need for safeguards

Mattea L. Welch, Chris McIntosh, Benjamin Haibe-Kains, Michael F. Milosevic, Leonard Wee, Andre Dekker, Shao Hui Huang, Thomas G. Purdie, Brian O'Sullivan, Hugo J. W. L. Aerts, David A. Jaffray*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

155 Citations (Web of Science)

Abstract

Purpose: Refinement of radiomic results and methodologies is required to ensure progression of the field. In this work, we establish a set of safeguards designed to improve and support current radiomic methodologies through detailed analysis of a radiomic signature.

Methods: A radiomic model (MW2018) was fitted and externally validated using features extracted from previously reported lung and head and neck (H&N) cancer datasets using gross-tumour-volume contours, as well as from images with randomly permuted voxel index values; i.e. images without meaningful texture. To determine MW2018's added benefit, the prognostic accuracy of tumour volume alone was calculated as a baseline.

Results: MW2018 had an external validation concordance index (c-index) of 0.64. However, a similar performance was achieved using features extracted from images with randomized signal intensities (c-index = 0.64 and 0.60 for H&N and lung, respectively). Tumour volume had a c-index = 0.64 and correlated strongly with three of the four model features. It was determined that the signature was a surrogate for tumour volume and that intensity and texture values were not pertinent for prognostication.

Conclusion: Our experiments reveal vulnerabilities in radiomic signature development processes and suggest safeguards that can be used to refine methodologies, and ensure productive radiomic development using objective and independent features. (C) 2018 The Author(s). Published by Elsevier B.V.

Original languageEnglish
Pages (from-to)2-9
Number of pages8
JournalRadiotherapy and Oncology
Volume130
DOIs
Publication statusPublished - Jan 2019

Keywords

  • Radiomics
  • Signature development
  • Safeguards
  • Volume
  • Lung cancer
  • Head and neck cancer
  • FEATURES
  • DELINEATION
  • THERAPY
  • IMPACT

Cite this