Building reliable radiomic models using image perturbation

• Published in: Scientific reports Vol. 12; no. 1; p. 10035
• Main Authors: Teng, Xinzhi, Zhang, Jiang, Zwanenburg, Alex, Sun, Jiachen, Huang, Yuhua, Lam, Saikit, Zhang, Yuanpeng, Li, Bing, Zhou, Ta, Xiao, Haonan, Liu, Chenyang, Li, Wen, Han, Xinyang, Ma, Zongrui, Li, Tian, Cai, Jing
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 16-06-2022; Nature Publishing Group; Nature Portfolio
• Subjects: 631/67/2321; 631/67/70; 692/308/53; 692/700/1421/1846/2771; Cancer; Confidence intervals; Correlation coefficient; Datasets; Head & neck cancer; Humanities and Social Sciences; Medical research; multidisciplinary; Radiomics; Science; Science (multidisciplinary); Tomography
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-022-14178-x

Radiomic model reliability is a central premise for its clinical translation. Presently, it is assessed using test–retest or external data, which, unfortunately, is often scarce in reality. Therefore, we aimed to develop a novel image perturbation-based method (IPBM) for the first of its kind toward building a reliable radiomic model. We first developed a radiomic prognostic model for head-and-neck cancer patients on a training (70%) and evaluated on a testing (30%) cohort using C-index. Subsequently, we applied the IPBM to CT images of both cohorts (Perturbed-Train and Perturbed-Test cohort) to generate 60 additional samples for both cohorts. Model reliability was assessed using intra-class correlation coefficient (ICC) to quantify consistency of the C-index among the 60 samples in the Perturbed-Train and Perturbed-Test cohorts. Besides, we re-trained the radiomic model using reliable RFs exclusively (ICC > 0.75) to validate the IPBM. Results showed moderate model reliability in Perturbed-Train (ICC: 0.565, 95%CI 0.518–0.615) and Perturbed-Test (ICC: 0.596, 95%CI 0.527–0.670) cohorts. An enhanced reliability of the re-trained model was observed in Perturbed-Train (ICC: 0.782, 95%CI 0.759–0.815) and Perturbed-Test (ICC: 0.825, 95%CI 0.782–0.867) cohorts, indicating validity of the IPBM. To conclude, we demonstrated capability of the IPBM toward building reliable radiomic models, providing community with a novel model reliability assessment strategy prior to prospective evaluation.