Radiomic feature repeatability and its impact on prognostic model generalizability: A multi-institutional study on nasopharyngeal carcinoma patients

Jiang Zhang, Sai Kit Lam, Xinzhi Teng, Zongrui Ma, Xinyang Han, Yuanpeng Zhang, Andy Lai Yin Cheung, Tin Ching Chau, Sherry Chor Yi Ng, Francis Kar Ho Lee, Kwok Hung Au, Celia Wai Yi Yip, Victor Ho Fun Lee, Ying Han, Jing Cai

Research output: Journal article publicationJournal articleAcademic researchpeer-review

14 Citations (Scopus)

Abstract

Background and purpose: To investigate the radiomic feature (RF) repeatability via perturbation and its impact on cross-institutional prognostic model generalizability in Nasopharyngeal Carcinoma (NPC) patients. Materials and methods: 286 and 183 NPC patients from two institutions were included for model training and validation. Perturbations with random translations and rotations were applied to contrast-enhanced T1-weighted (CET1-w) MR images. RFs were extracted from primary tumor volume under a wide range of image filtering and discretization settings. RF repeatability was assessed by intraclass correlation coefficient (ICC), which was used to equally separate the RFs into low- and high-repeatable groups by the median value. After feature selection, multivariate Cox regression and Kaplan-Meier analysis were independently employed to develop and analyze prognostic models. Concordance index (C-index) and P-value from log-rank test were used to assess model performance. Results: Most textural RFs from high-pass wavelet-filtered images were susceptible to image perturbations. It was more prominent when a smaller discretization bin number was used (e.g., 8, mean ICC = 0.69). Using high-repeatable RFs for model development yielded a significantly higher C-index (0.63) in the validation cohort than when only low-repeatable RFs were used (0.57, P = 0.024), suggesting higher model generalizability. Besides, significant risk stratification in the validation cohort was observed only when high-repeatable RFs were used (P < 0.001). Conclusion: Repeatability of RFs from high-pass wavelet-filtered CET1-w MR images of primary NPC tumor was poor, particularly when a smaller bin number was used. Exclusive use of high-repeatable RFs is suggested to safeguard model generalizability for wide-spreading clinical utilization.

Original languageEnglish
Article number109578
JournalRadiotherapy and Oncology
Volume183
DOIs
Publication statusPublished - Jun 2023

Keywords

  • Disease-Free Survival
  • Nasopharyngeal Carcinoma
  • Radiomics
  • Repeatability

ASJC Scopus subject areas

  • Hematology
  • Oncology
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Radiomic feature repeatability and its impact on prognostic model generalizability: A multi-institutional study on nasopharyngeal carcinoma patients'. Together they form a unique fingerprint.

Cite this