Dataset Information

Radiomics Repeatability Pitfalls in a Scan-Rescan MRI Study of Glioblastoma.

ABSTRACT:

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 (ClinicalTrials.gov 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 T2-weighted 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. Supplemental material is available for this article. © RSNA, 2020See also the commentary by Tiwari and Verma in this issue.

SUBMITTER: Hoebel KV

PROVIDER: S-EPMC7845781 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundPrevious quantitative synthetic MRI of the brain has been solely performed in 2D.PurposeTo evaluate the feasibility of the recently developed sequence 3D-QALAS for brain cortical thickness and volumetric analysis.Study typeReproducibility/repeatability study.SubjectsTwenty-one healthy volunteers (35.6 ± 13.8 years).Field strength/sequence3D T1 -weighted fast spoiled gradient recalled echo (FSPGR) sequence was performed once, and 3D-QALAS sequence was performed twice with a 3T scanner.AssessmentFreeSurfer and FIRST were used to measure cortical thickness and volume of subcortical structures, respectively. Agreement with FSPGR and scan-rescan repeatability were evaluated for 3D-QALAS.Statistical testsPercent relative difference and intraclass correlation coefficient (ICC) were used to assess reproducibility and scan-rescan repeatability of the 3D-QALAS sequence-derived measurements.ResultsPercent relative difference compared with FSPGR in cortical thickness of the whole cortex was 3.1%, and 89% of the regional areas showed less than 10% relative difference in cortical thickness. The mean ICC across all regions was 0.65, and 74% of the structures showed substantial to almost perfect agreement. For volumes of subcortical structures, the median percent relative differences were lower than 10% across all subcortical structures, except for the accumbens area, and all structures showed ICCs of substantial to almost perfect agreement. For the scan-rescan test, percent relative difference in cortical thickness of the whole cortex was 2.3%, and 97% of the regional areas showed less than 10% relative difference in cortical thickness. The mean ICC across all regions was 0.73, and 80% showed substantial to almost perfect agreement. For volumes of subcortical structures, relative differences were less than 10% across all subcortical structures except for the accumbens area, and all structures showed ICCs of substantial to almost perfect agreement.Data conclusion3D-QALAS could be reliably used for measuring cortical thickness and subcortical volumes in most brain regions.Level of evidence3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1834-1842.