Radiomics repeatability pitfalls in a scan-rescan mri study of glioblastoma

Katharina V. Hoebel, Jay B. Patel, Andrew L. Beers, Ken Chang, Praveer Singh, James M. Brown, Marco C. Pinho, Tracy T. Batchelor, Elizabeth R. Gerstner, Bruce R. Rosen, Jayashree Kalpathy-Cramer

Research output: Contribution to journalArticlepeer-review

23 Scopus citations


Purpose: To determine the influence of preprocessing on the repeatability and redundancy of radiomics features extracted using a popular open-source radiomics software package in a scan-rescan glioblastoma MRI study. Materials and Methods: In this study, a secondary analysis of T2-weighted fluid-attenuated inversion recovery (FLAIR) and T1-weighted postcontrast images from 48 patients (mean age, 56 years [range, 22–77 years]) diagnosed with glioblastoma were included from two prospective studies ( NCT00662506 [2009–2011] and NCT00756106 [2008–2011]). All patients underwent two baseline scans 2–6 days apart using identical imaging protocols on 3-T MRI systems. No treatment occurred between scan and rescan, and tumors were essentially unchanged visually. Radiomic features were extracted by using PyRadiomics (https://pyradiomics.readthedocs. io/) under varying conditions, including normalization strategies and intensity quantization. Subsequently, intraclass correlation coefficients were determined between feature values of the scan and rescan. Results: Shape features showed a higher repeatability than intensity (adjusted P < .001) and texture features (adjusted P < .001) for both T2-weighted FLAIR and T1-weighted postcontrast images. Normalization improved the overlap between the region of interest intensity histograms of scan and rescan (adjusted P < .001 for both T2-weighted FLAIR and T1-weighted postcontrast images), except in scans where brain extraction fails. As such, normalization significantly improves the repeatability of intensity features from T2weighted FLAIR scans (adjusted P = .003 [z score normalization] and adjusted P = .002 [histogram matching]). The use of a relative intensity binning strategy as opposed to default absolute intensity binning reduces correlation between gray-level co-occurrence matrix features after normalization. Conclusion: Both normalization and intensity quantization have an effect on the level of repeatability and redundancy of features, emphasizing the importance of both accurate reporting of methodology in radiomics articles and understanding the limitations of choices made in pipeline design.

Original languageEnglish (US)
Article numbere190199
JournalRadiology: Artificial Intelligence
Issue number1
StatePublished - Jan 2021
Externally publishedYes

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Artificial Intelligence
  • Radiological and Ultrasound Technology


Dive into the research topics of 'Radiomics repeatability pitfalls in a scan-rescan mri study of glioblastoma'. Together they form a unique fingerprint.

Cite this