PMID- 34575619 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20240403 IS - 2075-4426 (Print) IS - 2075-4426 (Electronic) IS - 2075-4426 (Linking) VI - 11 IP - 9 DP - 2021 Aug 27 TI - Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods. LID - 10.3390/jpm11090842 [doi] LID - 842 AB - Radiomics converts medical images into mineable data via a high-throughput extraction of quantitative features used for clinical decision support. However, these radiomic features are susceptible to variation across scanners, acquisition protocols, and reconstruction settings. Various investigations have assessed the reproducibility and validation of radiomic features across these discrepancies. In this narrative review, we combine systematic keyword searches with prior domain knowledge to discuss various harmonization solutions to make the radiomic features more reproducible across various scanners and protocol settings. Different harmonization solutions are discussed and divided into two main categories: image domain and feature domain. The image domain category comprises methods such as the standardization of image acquisition, post-processing of raw sensor-level image data, data augmentation techniques, and style transfer. The feature domain category consists of methods such as the identification of reproducible features and normalization techniques such as statistical normalization, intensity harmonization, ComBat and its derivatives, and normalization using deep learning. We also reflect upon the importance of deep learning solutions for addressing variability across multi-centric radiomic studies especially using generative adversarial networks (GANs), neural style transfer (NST) techniques, or a combination of both. We cover a broader range of methods especially GANs and NST methods in more detail than previous reviews. FAU - Mali, Shruti Atul AU - Mali SA AUID- ORCID: 0000-0002-8307-8051 AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. FAU - Ibrahim, Abdalla AU - Ibrahim A AUID- ORCID: 0000-0003-4138-5755 AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. AD - Department of Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University Medical Center+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands. AD - Department of Medical Physics, Division of Nuclear Medicine and Oncological Imaging, Hospital Center Universitaire de Liege, 4000 Liege, Belgium. AD - Department of Nuclear Medicine and Comprehensive Diagnostic Center Aachen (CDCA), University Hospital RWTH Aachen University, 52074 Aachen, Germany. FAU - Woodruff, Henry C AU - Woodruff HC AUID- ORCID: 0000-0001-7911-5123 AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. AD - Department of Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University Medical Center+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands. FAU - Andrearczyk, Vincent AU - Andrearczyk V AUID- ORCID: 0000-0003-0793-5821 AD - Institute of Information Systems, University of Applied Sciences and Arts Western Switzerland (HES-SO), rue du Technopole 3, 3960 Sierre, Switzerland. FAU - Muller, Henning AU - Muller H AUID- ORCID: 0000-0001-6800-9878 AD - Institute of Information Systems, University of Applied Sciences and Arts Western Switzerland (HES-SO), rue du Technopole 3, 3960 Sierre, Switzerland. FAU - Primakov, Sergey AU - Primakov S AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. FAU - Salahuddin, Zohaib AU - Salahuddin Z AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. FAU - Chatterjee, Avishek AU - Chatterjee A AUID- ORCID: 0000-0003-3536-670X AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. FAU - Lambin, Philippe AU - Lambin P AUID- ORCID: 0000-0001-7961-0191 AD - The D-Lab, Department of Precision Medicine, GROW-School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The Netherlands. AD - Department of Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University Medical Center+, P.O. Box 5800, 6202 AZ Maastricht, The Netherlands. LA - eng GR - EuCanImage n degrees 952103/Horizon 2020/ GR - ERC-ADG-2015 n degrees 694812 - Hypoximmuno/ERC_/European Research Council/International GR - CHAIMELEON n degrees 952172/Horizon 2020/ GR - JTC2016 CLEARLY n degrees UM 2017-8295/Horizon 2020/ GR - DRAGON - 101005122/Horizon 2020/ GR - iCOVID - 101016131/Horizon 2020/ GR - IMI-OPTIMA n degrees 10103434/Horizon 2020/ PT - Journal Article PT - Review DEP - 20210827 PL - Switzerland TA - J Pers Med JT - Journal of personalized medicine JID - 101602269 PMC - PMC8472571 OTO - NOTNLM OT - deep learning OT - feature reproducibility OT - harmonization OT - medical imaging OT - radiomics COIS- Dutch patent filed by A.C. titled 'Method of processing medical images by an analysis system for enabling radiomics signature analysis' Patent no. P127348NL00. EDAT- 2021/09/29 06:00 MHDA- 2021/09/29 06:01 PMCR- 2021/08/27 CRDT- 2021/09/28 01:16 PHST- 2021/07/21 00:00 [received] PHST- 2021/08/21 00:00 [revised] PHST- 2021/08/24 00:00 [accepted] PHST- 2021/09/28 01:16 [entrez] PHST- 2021/09/29 06:00 [pubmed] PHST- 2021/09/29 06:01 [medline] PHST- 2021/08/27 00:00 [pmc-release] AID - jpm11090842 [pii] AID - jpm-11-00842 [pii] AID - 10.3390/jpm11090842 [doi] PST - epublish SO - J Pers Med. 2021 Aug 27;11(9):842. doi: 10.3390/jpm11090842.