Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods
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...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/11/9/842 |
| _version_ | 1797518596908253184 |
|---|---|
| author | Shruti Atul Mali Abdalla Ibrahim Henry C. Woodruff Vincent Andrearczyk Henning Müller Sergey Primakov Zohaib Salahuddin Avishek Chatterjee Philippe Lambin |
| author_facet | Shruti Atul Mali Abdalla Ibrahim Henry C. Woodruff Vincent Andrearczyk Henning Müller Sergey Primakov Zohaib Salahuddin Avishek Chatterjee Philippe Lambin |
| author_sort | Shruti Atul Mali |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T07:31:59Z |
| format | Article |
| id | doaj.art-80761bc2fb754947aab1f838c6fa7cf2 |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-10T07:31:59Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-80761bc2fb754947aab1f838c6fa7cf22023-11-22T13:49:56ZengMDPI AGJournal of Personalized Medicine2075-44262021-08-0111984210.3390/jpm11090842Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization MethodsShruti Atul Mali0Abdalla Ibrahim1Henry C. Woodruff2Vincent Andrearczyk3Henning Müller4Sergey Primakov5Zohaib Salahuddin6Avishek Chatterjee7Philippe Lambin8The D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsThe D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsThe D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsInstitute of Information Systems, University of Applied Sciences and Arts Western Switzerland (HES-SO), rue du Technopole 3, 3960 Sierre, SwitzerlandInstitute of Information Systems, University of Applied Sciences and Arts Western Switzerland (HES-SO), rue du Technopole 3, 3960 Sierre, SwitzerlandThe D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsThe D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsThe D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsThe D-Lab, Department of Precision Medicine, GROW—School for Oncology, Maastricht University, Maastricht, Universiteitssingel 40, 6229 ER Maastricht, The NetherlandsRadiomics 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.https://www.mdpi.com/2075-4426/11/9/842radiomicsharmonizationfeature reproducibilitydeep learningmedical imaging |
| spellingShingle | Shruti Atul Mali Abdalla Ibrahim Henry C. Woodruff Vincent Andrearczyk Henning Müller Sergey Primakov Zohaib Salahuddin Avishek Chatterjee Philippe Lambin Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods Journal of Personalized Medicine radiomics harmonization feature reproducibility deep learning medical imaging |
| title | Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods |
| title_full | Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods |
| title_fullStr | Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods |
| title_full_unstemmed | Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods |
| title_short | Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods |
| title_sort | making radiomics more reproducible across scanner and imaging protocol variations a review of harmonization methods |
| topic | radiomics harmonization feature reproducibility deep learning medical imaging |
| url | https://www.mdpi.com/2075-4426/11/9/842 |
| work_keys_str_mv | AT shrutiatulmali makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT abdallaibrahim makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT henrycwoodruff makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT vincentandrearczyk makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT henningmuller makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT sergeyprimakov makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT zohaibsalahuddin makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT avishekchatterjee makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods AT philippelambin makingradiomicsmorereproducibleacrossscannerandimagingprotocolvariationsareviewofharmonizationmethods |