Literature DB >> 32975661

How can we combat multicenter variability in MR radiomics? Validation of a correction procedure.

Fanny Orlhac1,2, Augustin Lecler3, Julien Savatovski3,4, Jessica Goya-Outi5, Christophe Nioche5, Frédérique Charbonneau3, Nicholas Ayache6, Frédérique Frouin5, Loïc Duron3, Irène Buvat5.   

Abstract

OBJECTIVE: Test a practical realignment approach to compensate the technical variability of MR radiomic features.
METHODS: T1 phantom images acquired on 2 scanners, FLAIR and contrast-enhanced T1-weighted (CE-T1w) images of 18 brain tumor patients scanned on both 1.5-T and 3-T scanners, and 36 T2-weighted (T2w) images of prostate cancer patients scanned in one of two centers were investigated. The ComBat procedure was used for harmonizing radiomic features. Differences in statistical distributions in feature values between 1.5- and 3-T images were tested before and after harmonization. The prostate studies were used to determine the impact of harmonization to distinguish between Gleason grades (GGs).
RESULTS: In the phantom data, 40 out of 42 radiomic feature values were significantly different between the 2 scanners before harmonization and none after. In white matter regions, the statistical distributions of features were significantly different (p < 0.05) between the 1.5- and 3-T images for 37 out of 42 features in both FLAIR and CE-T1w images. After harmonization, no statistically significant differences were observed. In brain tumors, 41 (FLAIR) or 36 (CE-T1w) out of 42 features were significantly different between the 1.5- and 3-T images without harmonization, against 1 (FLAIR) or none (CE-T1w) with harmonization. In prostate studies, 636 radiomic features were significantly different between GGs after harmonization against 461 before. The ability to distinguish between GGs using radiomic features was increased after harmonization.
CONCLUSION: ComBat harmonization efficiently removes inter-center technical inconsistencies in radiomic feature values and increases the sensitivity of studies using data from several scanners. KEY POINTS: • Radiomic feature values obtained using different MR scanners or imaging protocols can be harmonized by combining off-the-shelf image standardization and feature realignment procedures. • Harmonized radiomic features enable one to pool data from different scanners and centers without a substantial loss of statistical power caused by intra- and inter-center variability. • The proposed realignment method is applicable to radiomic features from different MR sequences and tumor types and does not rely on any phantom acquisition.

Entities:  

Keywords:  Computer-assisted methods; Diagnostic imaging; Image processing; Magnetic resonance imaging; Neoplasms

Mesh:

Year:  2020        PMID: 32975661     DOI: 10.1007/s00330-020-07284-9

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  1 in total

1.  Wavelet-based Semi-supervised Adversarial Learning for Synthesizing Realistic 7T from 3T MRI.

Authors:  Liangqiong Qu; Shuai Wang; Pew-Thian Yap; Dinggang Shen
Journal:  Med Image Comput Comput Assist Interv       Date:  2019-10-10
  1 in total
  23 in total

1.  Adding radiomics to the 2021 WHO updates may improve prognostic prediction for current IDH-wildtype histological lower-grade gliomas with known EGFR amplification and TERT promoter mutation status.

Authors:  Yae Won Park; Sooyon Kim; Chae Jung Park; Sung Soo Ahn; Kyunghwa Han; Seok-Gu Kang; Jong Hee Chang; Se Hoon Kim; Seung-Koo Lee
Journal:  Eur Radiol       Date:  2022-06-28       Impact factor: 5.315

2.  Radiomics Analysis of Fat-Saturated T2-Weighted MRI Sequences for the Prediction of Prognosis in Soft Tissue Sarcoma of the Extremities and Trunk Treated With Neoadjuvant Radiotherapy.

Authors:  Silin Chen; Ning Li; Yuan Tang; Bo Chen; Hui Fang; Shunan Qi; Ninging Lu; Yong Yang; Yongwen Song; Yueping Liu; Shulian Wang; Ye-Xiong Li; Jing Jin
Journal:  Front Oncol       Date:  2021-09-17       Impact factor: 6.244

3.  A Guide to ComBat Harmonization of Imaging Biomarkers in Multicenter Studies.

Authors:  Fanny Orlhac; Jakoba J Eertink; Anne-Ségolène Cottereau; Josée M Zijlstra; Catherine Thieblemont; Michel Meignan; Ronald Boellaard; Irène Buvat
Journal:  J Nucl Med       Date:  2021-09-16       Impact factor: 10.057

4.  Spatially coherent modeling of 3D FDG-PET data for assessment of intratumoral heterogeneity and uptake gradients.

Authors:  Eric Wolsztynski; Finbarr O'Sullivan; Janet F Eary
Journal:  J Med Imaging (Bellingham)       Date:  2022-07-29

Review 5.  Challenges in ensuring the generalizability of image quantitation methods for MRI.

Authors:  Kathryn E Keenan; Jana G Delfino; Kalina V Jordanova; Megan E Poorman; Prathyush Chirra; Akshay S Chaudhari; Bettina Baessler; Jessica Winfield; Satish E Viswanath; Nandita M deSouza
Journal:  Med Phys       Date:  2021-09-29       Impact factor: 4.506

6.  Robustness of radiomic features in magnetic resonance imaging for patients with glioblastoma: Multi-center study.

Authors:  Natalia Saltybaeva; Stephanie Tanadini-Lang; Diem Vuong; Simon Burgermeister; Michael Mayinger; Andrea Bink; Nicolaus Andratschke; Matthias Guckenberger; Marta Bogowicz
Journal:  Phys Imaging Radiat Oncol       Date:  2022-05-14

7.  MRI texture feature repeatability and image acquisition factor robustness, a phantom study and in silico study.

Authors:  Joshua Shur; Matthew Blackledge; James D'Arcy; David J Collins; Maria Bali; Martin O'Leach; Dow-Mu Koh
Journal:  Eur Radiol Exp       Date:  2021-01-19

8.  Multi-Stage Harmonization for Robust AI across Breast MR Databases.

Authors:  Heather M Whitney; Hui Li; Yu Ji; Peifang Liu; Maryellen L Giger
Journal:  Cancers (Basel)       Date:  2021-09-26       Impact factor: 6.639

9.  Radiomics-Based Detection of Radionecrosis Using Harmonized Multiparametric MRI.

Authors:  Clément Acquitter; Lucie Piram; Umberto Sabatini; Julia Gilhodes; Elizabeth Moyal Cohen-Jonathan; Soleakhena Ken; Benjamin Lemasson
Journal:  Cancers (Basel)       Date:  2022-01-07       Impact factor: 6.639

10.  Development of a Machine Learning Classifier Based on Radiomic Features Extracted From Post-Contrast 3D T1-Weighted MR Images to Distinguish Glioblastoma From Solitary Brain Metastasis.

Authors:  Alix de Causans; Alexandre Carré; Alexandre Roux; Arnault Tauziède-Espariat; Samy Ammari; Edouard Dezamis; Frederic Dhermain; Sylvain Reuzé; Eric Deutsch; Catherine Oppenheim; Pascale Varlet; Johan Pallud; Myriam Edjlali; Charlotte Robert
Journal:  Front Oncol       Date:  2021-07-13       Impact factor: 6.244

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.