Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
23 07 2020
23 07 2020
Historique:
received:
09
11
2019
accepted:
06
07
2020
entrez:
25
7
2020
pubmed:
25
7
2020
medline:
15
12
2020
Statut:
epublish
Résumé
Radiomics relies on the extraction of a wide variety of quantitative image-based features to provide decision support. Magnetic resonance imaging (MRI) contributes to the personalization of patient care but suffers from being highly dependent on acquisition and reconstruction parameters. Today, there are no guidelines regarding the optimal pre-processing of MR images in the context of radiomics, which is crucial for the generalization of published image-based signatures. This study aims to assess the impact of three different intensity normalization methods (Nyul, WhiteStripe, Z-Score) typically used in MRI together with two methods for intensity discretization (fixed bin size and fixed bin number). The impact of these methods was evaluated on first- and second-order radiomics features extracted from brain MRI, establishing a unified methodology for future radiomics studies. Two independent MRI datasets were used. The first one (DATASET1) included 20 institutional patients with WHO grade II and III gliomas who underwent post-contrast 3D axial T1-weighted (T1w-gd) and axial T2-weighted fluid attenuation inversion recovery (T2w-flair) sequences on two different MR devices (1.5 T and 3.0 T) with a 1-month delay. Jensen-Shannon divergence was used to compare pairs of intensity histograms before and after normalization. The stability of first-order and second-order features across the two acquisitions was analysed using the concordance correlation coefficient and the intra-class correlation coefficient. The second dataset (DATASET2) was extracted from the public TCIA database and included 108 patients with WHO grade II and III gliomas and 135 patients with WHO grade IV glioblastomas. The impact of normalization and discretization methods was evaluated based on a tumour grade classification task (balanced accuracy measurement) using five well-established machine learning algorithms. Intensity normalization highly improved the robustness of first-order features and the performances of subsequent classification models. For the T1w-gd sequence, the mean balanced accuracy for tumour grade classification was increased from 0.67 (95% CI 0.61-0.73) to 0.82 (95% CI 0.79-0.84, P = .006), 0.79 (95% CI 0.76-0.82, P = .021) and 0.82 (95% CI 0.80-0.85, P = .005), respectively, using the Nyul, WhiteStripe and Z-Score normalization methods compared to no normalization. The relative discretization makes unnecessary the use of intensity normalization for the second-order radiomics features. Even if the bin number for the discretization had a small impact on classification performances, a good compromise was obtained using the 32 bins considering both T1w-gd and T2w-flair sequences. No significant improvements in classification performances were observed using feature selection. A standardized pre-processing pipeline is proposed for the use of radiomics in MRI of brain tumours. For models based on first- and second-order features, we recommend normalizing images with the Z-Score method and adopting an absolute discretization approach. For second-order feature-based signatures, relative discretization can be used without prior normalization. In both cases, 32 bins for discretization are recommended. This study may pave the way for the multicentric development and validation of MR-based radiomics biomarkers.
Identifiants
pubmed: 32704007
doi: 10.1038/s41598-020-69298-z
pii: 10.1038/s41598-020-69298-z
pmc: PMC7378556
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
12340Références
Gillies, R. J., Kinahan, P. E. & Hricak, H. Radiomics: images are more than pictures, they are data. Radiology 278, 563–577 (2016).
pubmed: 26579733
Lambin, P. et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 14, 749–762 (2017).
pubmed: 28975929
Limkin, E. J. et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology. Ann. Oncol. 28, 1191–1206 (2017).
pubmed: 28168275
Sun, R. et al. A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study. Lancet Oncol. 19, 1180–1191 (2018).
pubmed: 30120041
Simmons, A., Tofts, P. S., Barker, G. J. & Arridge, S. R. Sources of intensity nonuniformity in spin echo images at 1.5 T. Magn. Reson. Med. 32, 121–128 (1994).
pubmed: 8084227
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, 1729071 (2018).
pubmed: 30154684
pmcid: 6091359
Molina, D. et al. Lack of robustness of textural measures obtained from 3D brain tumor MRIs impose a need for standardization. PLoS ONE 12, e0178843 (2017).
pubmed: 28586353
pmcid: 5460822
Antunes, J. et al. Radiomics analysis on FLT-PET/MRI for characterization of early treatment response in renal cell carcinoma: a proof-of-concept study. Transl. Oncol. 9, 155–162 (2016).
pubmed: 27084432
pmcid: 4833889
Chirra, P. et al. Empirical evaluation of cross-site reproducibility in radiomic features for characterizing prostate MRI. In Medical Imaging: Computer-Aided Diagnosis (2018). https://doi.org/10.1117/12.2293992 .
Moradmand, H., Aghamiri, S. M. R. & Ghaderi, R. Impact of image preprocessing methods on reproducibility of radiomic features in multimodal magnetic resonance imaging in glioblastoma. J. Appl. Clin. Med. Phys. 21, 179–190 (2020).
pubmed: 31880401
Shafiq-Ul-Hassan, M. et al. Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels. Med. Phys. 44, 1050–1062 (2017).
pubmed: 28112418
pmcid: 5462462
Bologna, M., Corino, V. & Mainardi, L. Technical note: virtual phantom analyses for preprocessing evaluation and detection of a robust feature set for MRI-radiomics of the brain. Med. Phys. 46, 5116–5123 (2019).
pubmed: 31539450
pmcid: 6899873
Rathore, S. et al. Radiomic MRI signature reveals three distinct subtypes of glioblastoma with different clinical and molecular characteristics, offering prognostic value beyond IDH1. Sci. Rep. 8, 1–12 (2018).
Zinn, P. O. et al. A Coclinical radiogenomic validation study: conserved magnetic resonance radiomic appearance of periostin-expressing glioblastoma in patients and xenograft models. Clin. Cancer Res. 24, 6288–6299 (2018).
pubmed: 30054278
pmcid: 6538261
Su, X. et al. Automated machine learning based on radiomics features predicts H3 K27M mutation in midline gliomas of the brain. Neuro-Oncology https://doi.org/10.1093/neuonc/noz184 (2019).
doi: 10.1093/neuonc/noz184
pubmed: 31190077
pmcid: 6827825
Liu, H. et al. Treatment response prediction of rehabilitation program in children with cerebral palsy using radiomics strategy: protocol for a multicenter prospective cohort study in west China. Quant. Imaging Med. Surg. 9, 1402–1412 (2019).
pubmed: 31559169
pmcid: 6732071
Bologna, M., Corino, V. & Mainardi, L. Technical note: virtual phantom analyses for preprocessing evaluation and detection of a robust feature set for MRI-radiomics of the brain. Med. Phys. https://doi.org/10.1002/mp.13834 (2019).
doi: 10.1002/mp.13834
pubmed: 31539450
pmcid: 6899873
Elsheikh, S. S. M. et al. Multi-stage association analysis of glioblastoma gene expressions with texture and spatial patterns. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes Workshop, Vol. 11383, 239–250 (2019).
Tixier, F., Um, H., Young, R. J. & Veeraraghavan, H. Reliability of tumor segmentation in glioblastoma: impact on the robustness of MRI-radiomic features. Med. Phys. 46, 3582–3591 (2019).
pubmed: 31131906
Ortiz-Ramón, R. et al. Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images. Comput. Med. Imaging Graph. 74, 12–24 (2019).
pubmed: 30921550
pmcid: 6553681
Vamvakas, A. et al. (2019) Imaging biomarker analysis of advanced multiparametric MRI for glioma grading. Phys. Med. PM Int. J. Devoted Appl. Phys. Med. Biol. 60, 188–198 (2019).
Tixier, F. et al. Preoperative MRI-radiomics features improve prediction of survival in glioblastoma patients over MGMT methylation status alone. Oncotarget 10, 660–672 (2019).
pubmed: 30774763
pmcid: 6363013
Wu, S., Meng, J., Yu, Q., Li, P. & Fu, S. Radiomics-based machine learning methods for isocitrate dehydrogenase genotype prediction of diffuse gliomas. J. Cancer Res. Clin. Oncol. 145, 543–550 (2019).
pubmed: 30719536
pmcid: 6394679
Artzi, M., Bressler, I. & Ben Bashat, D. (2019) Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis. J. Magn. Reson. Imaging JMRI 50, 519–528 (2019).
pubmed: 30635952
Kniep, H. C. et al. Radiomics of brain MRI: utility in prediction of metastatic tumor type. Radiology 290, 479–487 (2019).
pubmed: 30526358
Sanghani, P., Ang, B. T., King, N. K. K. & Ren, H. Overall survival prediction in glioblastoma multiforme patients from volumetric, shape and texture features using machine learning. Surg. Oncol. 27, 709–714 (2018).
pubmed: 30449497
Liu, X. et al. A radiomic signature as a non-invasive predictor of progression-free survival in patients with lower-grade gliomas. NeuroImage Clin. 20, 1070–1077 (2018).
pubmed: 30366279
pmcid: 6202688
Peng, L. et al. Distinguishing true progression from radionecrosis after stereotactic radiation therapy for brain metastases with machine learning and radiomics. Int. J. Radiat. Oncol. Biol. Phys. 102, 1236–1243 (2018).
pubmed: 30353872
pmcid: 6746307
Bae, S. et al. Radiomic MRI phenotyping of glioblastoma: improving survival prediction. Radiology 289, 797–806 (2018).
pubmed: 30277442
Chen, W., Liu, B., Peng, S., Sun, J. & Qiao, X. Computer-aided grading of gliomas combining automatic segmentation and radiomics. Int. J. Biomed. Imaging https://doi.org/10.1155/2018/2512037 (2018).
doi: 10.1155/2018/2512037
pubmed: 30057592
pmcid: 6051270
Nyúl, L. G. & Udupa, J. K. On standardizing the MR image intensity scale. Magn. Reson. Med. 42, 1072–1081 (1999).
pubmed: 10571928
Shah, M. et al. Evaluating intensity normalization on MRIs of human brain with multiple sclerosis. Med. Image Anal. 15, 267–282 (2011).
pubmed: 21233004
Shinohara, R. T. et al. Statistical normalization techniques for magnetic resonance imaging. NeuroImage Clin. 6, 9–19 (2014).
pubmed: 25379412
pmcid: 4215426
Chaddad, A. et al. Radiomics in glioblastoma: current status and challenges facing clinical implementation. Front. Oncol. 9, 188–198 (2019).
Leijenaar, R. T. H. et al. The effect of SUV discretization in quantitative FDG-PET radiomics: the need for standardized methodology in tumor texture analysis. Sci. Rep. 5, 11075 (2015).
pubmed: 26242464
pmcid: 4525145
Mayerhoefer, M. E., Szomolanyi, P., Jirak, D., Materka, A. & Trattnig, S. Effects of MRI acquisition parameter variations and protocol heterogeneity on the results of texture analysis and pattern discrimination: an application-oriented study. Med. Phys. 36, 1236–1243 (2009).
pubmed: 19472631
Jirák, D., Dezortová, M. & Hájek, M. Phantoms for texture analysis of MR images. Long-term and multi-center study. Med. Phys. 31, 616–622 (2004).
pubmed: 15070262
Yip, S. S. & Aerts, H. J. W. L. Applications and limitations of radiomics. Phys. Med. Biol. 61, R150–R166 (2016).
pubmed: 27269645
pmcid: 4927328
Duron, L. et al. Gray-level discretization impacts reproducible MRI radiomics texture features. PLoS ONE 14, e0213459 (2019).
pubmed: 30845221
pmcid: 6405136
Um, H. et al. Impact of image preprocessing on the scanner dependence of multi-parametric MRI radiomic features and covariate shift in multi-institutional glioblastoma datasets. Phys. Med. Biol. 64, 165011 (2019).
pubmed: 31272093
Schwier, M. et al. Repeatability of multiparametric prostate MRI radiomics features. Sci. Rep. 9, 1–16 (2019).
Tixier, F. et al. Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J. Nucl. Med. 52, 369–378 (2011).
pubmed: 21321270
pmcid: 3789272
Zwanenburg, A., Leger, S., Vallières, M. & Löck, S. Image biomarker standardisation initiative. ArXiv161207003 Cs (2016).
Goya-Outi, J. et al. Computation of reliable textural indices from multimodal brain MRI: suggestions based on a study of patients with diffuse intrinsic pontine glioma. Phys. Med. Biol. 63, 105003 (2018).
pubmed: 29633962
Lecler, A. et al. Combining multiple magnetic resonance imaging sequences provides independent reproducible radiomics features. Sci. Rep. 9, 2068 (2019).
pubmed: 30765732
pmcid: 6376058
Test–retest reliability and feature selection in physiological time series classification-ScienceDirect. https://www.sciencedirect.com/science/article/pii/S016926071000204X .
Sun, X. et al. Histogram-based normalization technique on human brain magnetic resonance images from different acquisitions. Biomed. Eng. OnLine 14, 1–7 (2015).
Palumbo, D. et al. Interplay between bias field correction, intensity standardization, and noise filtering for T2-weighted MRI. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vol. 2011, 5080–5083 (2011).
Tustison, N. J. et al. N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29, 1310–1320 (2010).
pubmed: 20378467
pmcid: 3071855
Vallières, M., Freeman, C. R., Skamene, S. R. & El Naqa, I. A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Phys. Med. Biol. 60, 5471–5496 (2015).
pubmed: 26119045
Johnson, W. E., Li, C. & Rabinovic, A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostat. Oxf. Engl. 8, 118–127 (2007).
Orlhac, F. et al. A Postreconstruction harmonization method for multicenter radiomic studies in PET. J. Nucl. Med. 59, 1321–1328 (2018).
pubmed: 29301932
Orlhac, F., Frouin, F., Nioche, C., Ayache, N. & Buvat, I. Validation of a method to compensate multicenter effects affecting CT radiomics. Radiology 291, 53–59 (2019).
pubmed: 30694160
Tselikas, L. et al. Imaging of gliomas at 1.5 and 3 Tesla—a comparative study. Neuro-Oncology 17, 895–900 (2015).
pubmed: 25526734
Bakas, S. et al. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4, 170117 (2017).
pubmed: 28872634
pmcid: 5685212
Bakas, S. et al. Segmentation labels for the pre-operative scans of the TCGA-LGG collection. Cancer Imaging Arch. https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF (2017).
doi: 10.7937/K9/TCIA.2017.GJQ7R0EF
Clark, K. et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26, 1045–1057 (2013).
pubmed: 23884657
pmcid: 3824915
ANTs by stnava. https://stnava.github.io/ANTs/ .
Smith, S. M. Fast robust automated brain extraction. Hum. Brain Mapp. 17, 143–155 (2002).
pubmed: 12391568
pmcid: 6871816
Rohlfing, T., Zahr, N. M., Sullivan, E. V. & Pfefferbaum, A. The SRI24 multichannel atlas of normal adult human brain structure. Hum. Brain Mapp. 31, 798–819 (2010).
pubmed: 20017133
Reinhold, J. C., Dewey, B. E., Carass, A. & Prince, J. L. Evaluating the impact of intensity normalization on MR image synthesis. In Medical Imaging 2019: Image Processing, Vol. 10949, 109493H (International Society for Optics and Photonics, 2019).
van Griethuysen, J. J. M. et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77, e104–e107 (2017).
pubmed: 29092951
pmcid: 5672828
Lin, J. Divergence measures based on the Shannon entropy. IEEE Trans. Inf. Theor. 37, 145–151 (2006).
Zhang, X. et al. Radiomics strategy for molecular subtype stratification of lower-grade glioma: detecting IDH and TP53 mutations based on multimodal MRI. J. Magn. Reson. Imaging 48, 916–926 (2018).
pubmed: 29394005
Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Brodersen, K. H., Ong, C. S., Stephan, K. E. & Buhmann, J. M. The balanced accuracy and its posterior distribution. In 2010 20th International Conference on Pattern Recognition, 3121–3124 (IEEE, 2010). https://doi.org/10.1109/ICPR.2010.764 .