Assessing robustness of radiomic features by image perturbation

• Published in: Scientific reports Vol. 9; no. 1; p. 614
• Main Authors: Zwanenburg, Alex, Leger, Stefan, Agolli, Linda, Pilz, Karoline, Troost, Esther G. C., Richter, Christian, Löck, Steffen
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 24.01.2019; Nature Publishing Group
• Subjects: 59; 631/114/1564; 692/4028/67/2321; Adaptation; Computed tomography; Confidence intervals; Correlation coefficient; Deep learning; Genotype & phenotype; Head & neck cancer; Humanities and Social Sciences; Lung cancer; Medical research; Morphology; multidisciplinary; Noise; Non-small cell lung carcinoma; Patients; Phenotypes; Radiation; Radiomics; Science; Science (multidisciplinary); Segmentation; Small cell lung carcinoma; Squamous cell carcinoma; Tumors
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-018-36938-4

Image features need to be robust against differences in positioning, acquisition and segmentation to ensure reproducibility. Radiomic models that only include robust features can be used to analyse new images, whereas models with non-robust features may fail to predict the outcome of interest accurately. Test-retest imaging is recommended to assess robustness, but may not be available for the phenotype of interest. We therefore investigated 18 combinations of image perturbations to determine feature robustness, based on noise addition (N), translation (T), rotation (R), volume growth/shrinkage (V) and supervoxel-based contour randomisation (C). Test-retest and perturbation robustness were compared for combined total of 4032 morphological, statistical and texture features that were computed from the gross tumour volume in two cohorts with computed tomography imaging: I) 31 non-small-cell lung cancer (NSCLC) patients; II): 19 head-and-neck squamous cell carcinoma (HNSCC) patients. Robustness was determined using the 95% confidence interval (CI) of the intraclass correlation coefficient (1, 1). Features with CI ≥ 0:90 were considered robust. The NTCV, TCV, RNCV and RCV perturbation chain produced similar results and identified the fewest false positive robust features (NSCLC: 0.2–0.9%; HNSCC: 1.7–1.9%). Thus, these perturbation chains may be used as an alternative to test-retest imaging to assess feature robustness.