Harmonization Strategies in Multicenter MRI-Based Radiomics

Overview

Journal J Imaging

Publisher MDPI

Specialty Radiology

Date 2022 Nov 10

PMID 36354876

Authors

Elisavet Stamoulou

Constantinos Spanakis

Georgios C Manikis

Georgia Karanasiou

Grigoris Grigoriadis

Theodoros Foukakis

Manolis Tsiknakis

Dimitrios I Fotiadis

Kostas Marias

Affiliations

Soon will be listed here.

Abstract

Radiomics analysis is a powerful tool aiming to provide diagnostic and prognostic patient information directly from images that are decoded into handcrafted features, comprising descriptors of shape, size and textural patterns. Although radiomics is gaining momentum since it holds great promise for accelerating digital diagnostics, it is susceptible to bias and variation due to numerous inter-patient factors (e.g., patient age and gender) as well as inter-scanner ones (different protocol acquisition depending on the scanner center). A variety of image and feature based harmonization methods has been developed to compensate for these effects; however, to the best of our knowledge, none of these techniques has been established as the most effective in the analysis pipeline so far. To this end, this review provides an overview of the challenges in optimizing radiomics analysis, and a concise summary of the most relevant harmonization techniques, aiming to provide a thorough guide to the radiomics harmonization process.

Citing Articles

Regularization by Neural Style Transfer for MRI Field-Transfer Reconstruction with Limited Data.

Shen G, Zhu Y, Li M, McNaughton R, Jara H, Andersson S ArXiv. 2025; .

PMID: 40034133 PMC: 11875279.

A Comprehensive Evaluation of Radiomic Features in Normal Brain Magnetic Resonance Imaging: Investigating Robustness and Region Variations.

Shakeri M, Mostaar A, Sadeghi A, Hosseini S, Joybari A, Ghadiri H J Med Phys. 2025; 49(4):608-622.

PMID: 39926136 PMC: 11801087. DOI: 10.4103/jmp.jmp_149_24.

The potential of GPT-4 advanced data analysis for radiomics-based machine learning models.

Foltyn-Dumitru M, Rastogi A, Cho J, Schell M, Mahmutoglu M, Kessler T Neurooncol Adv. 2025; 7(1):vdae230.

PMID: 39780768 PMC: 11707530. DOI: 10.1093/noajnl/vdae230.

ESR Essentials: radiomics-practice recommendations by the European Society of Medical Imaging Informatics.

Santinha J, Pinto Dos Santos D, Laqua F, Visser J, Groot Lipman K, Dietzel M Eur Radiol. 2024; 35(3):1122-1132.

PMID: 39453470 PMC: 11835989. DOI: 10.1007/s00330-024-11093-9.

Deep feature batch correction using ComBat for machine learning applications in computational pathology.

Murchan P, Broin P, Baird A, Sheils O, Finn S J Pathol Inform. 2024; 15:100396.

PMID: 39398947 PMC: 11470259. DOI: 10.1016/j.jpi.2024.100396.

References

da Silva G, Diniz P, Ferreira J, Franca J, Silva A, de Paiva A . Superpixel-based deep convolutional neural networks and active contour model for automatic prostate segmentation on 3D MRI scans. Med Biol Eng Comput. 2020; 58(9):1947-1964. DOI: 10.1007/s11517-020-02199-5. View

Traverso A, Wee L, Dekker A, Gillies R . Repeatability and Reproducibility of Radiomic Features: A Systematic Review. Int J Radiat Oncol Biol Phys. 2018; 102(4):1143-1158. PMC: 6690209. DOI: 10.1016/j.ijrobp.2018.05.053. View

Ortiz-Ramon R, Larroza A, Ruiz-Espana S, Arana E, Moratal D . Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study. Eur Radiol. 2018; 28(11):4514-4523. DOI: 10.1007/s00330-018-5463-6. View

Saleem H, Shahid A, Raza B . Visual interpretability in 3D brain tumor segmentation network. Comput Biol Med. 2021; 133:104410. DOI: 10.1016/j.compbiomed.2021.104410. View

Kocher M, Ruge M, Galldiks N, Lohmann P . Applications of radiomics and machine learning for radiotherapy of malignant brain tumors. Strahlenther Onkol. 2020; 196(10):856-867. PMC: 7498494. DOI: 10.1007/s00066-020-01626-8. View

Scalco E, Belfatto A, Mastropietro A, Rancati T, Avuzzi B, Messina A . T2w-MRI signal normalization affects radiomics features reproducibility. Med Phys. 2020; 47(4):1680-1691. DOI: 10.1002/mp.14038. View

Tian D, Zeng Z, Sun X, Tong Q, Li H, He H . A deep learning-based multisite neuroimage harmonization framework established with a traveling-subject dataset. Neuroimage. 2022; 257:119297. DOI: 10.1016/j.neuroimage.2022.119297. View

Schick U, Lucia F, Dissaux G, Visvikis D, Badic B, Masson I . MRI-derived radiomics: methodology and clinical applications in the field of pelvic oncology. Br J Radiol. 2019; 92(1104):20190105. PMC: 6913356. DOI: 10.1259/bjr.20190105. View

Zheng Y, Grossman M, Awate S, Gee J . Automatic correction of intensity nonuniformity from sparseness of gradient distribution in medical images. Med Image Comput Comput Assist Interv. 2010; 12(Pt 2):852-9. PMC: 3673007. DOI: 10.1007/978-3-642-04271-3_103. View

10.

Larue R, van Timmeren J, de Jong E, Feliciani G, Leijenaar R, Schreurs W . Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses: a comprehensive phantom study. Acta Oncol. 2017; 56(11):1544-1553. DOI: 10.1080/0284186X.2017.1351624. View

11.

Baessler B, Weiss K, Pinto Dos Santos D . Robustness and Reproducibility of Radiomics in Magnetic Resonance Imaging: A Phantom Study. Invest Radiol. 2018; 54(4):221-228. DOI: 10.1097/RLI.0000000000000530. View

12.

Scherer J, Nolden M, Kleesiek J, Metzger J, Kades K, Schneider V . Joint Imaging Platform for Federated Clinical Data Analytics. JCO Clin Cancer Inform. 2020; 4:1027-1038. PMC: 7713526. DOI: 10.1200/CCI.20.00045. View

13.

Moradmand H, Aghamiri S, Ghaderi R . Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma. J Appl Clin Med Phys. 2019; 21(1):179-190. PMC: 6964771. DOI: 10.1002/acm2.12795. View

14.

van Timmeren J, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B . Radiomics in medical imaging-"how-to" guide and critical reflection. Insights Imaging. 2020; 11(1):91. PMC: 7423816. DOI: 10.1186/s13244-020-00887-2. View

15.

Khaled R, Vidal J, Vilanova J, Marti R . A U-Net Ensemble for breast lesion segmentation in DCE MRI. Comput Biol Med. 2021; 140:105093. DOI: 10.1016/j.compbiomed.2021.105093. View

16.

Martin M, Orlhac F, Akl P, Khalid F, Nioche C, Buvat I . A radiomics pipeline dedicated to Breast MRI: validation on a multi-scanner phantom study. MAGMA. 2020; 34(3):355-366. DOI: 10.1007/s10334-020-00892-y. View

17.

Ford J, Dogan N, Young L, Yang F . Quantitative Radiomics: Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain. Contrast Media Mol Imaging. 2018; 2018:1729071. PMC: 6091359. DOI: 10.1155/2018/1729071. View

18.

Johnson W, Li C, Rabinovic A . Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2006; 8(1):118-27. DOI: 10.1093/biostatistics/kxj037. View

19.

Beer J, Tustison N, Cook P, Davatzikos C, Sheline Y, Shinohara R . Longitudinal ComBat: A method for harmonizing longitudinal multi-scanner imaging data. Neuroimage. 2020; 220:117129. PMC: 7605103. DOI: 10.1016/j.neuroimage.2020.117129. View

20.

Vovk U, Pernus F, Likar B . A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans Med Imaging. 2007; 26(3):405-21. DOI: 10.1109/TMI.2006.891486. View