Impact of MRI radiomic feature normalization for prognostic modelling in uterine endometrial and cervical cancers.
Cervical cancer
Endometrial cancer
MRI
Normalization
Radiomics
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
22 Jul 2024
22 Jul 2024
Historique:
received:
02
02
2024
accepted:
03
07
2024
medline:
23
7
2024
pubmed:
23
7
2024
entrez:
22
7
2024
Statut:
epublish
Résumé
Widespread clinical use of MRI radiomic tumor profiling for prognostication and treatment planning in cancers faces major obstacles due to limitations in standardization of radiomic features. The purpose of the current work was to assess the impact of different MRI scanning- and normalization protocols for the statistical analyses of tumor radiomic data in two patient cohorts with uterine endometrial-(EC) (n = 136) and cervical (CC) (n = 132) cancer. 1.5 T and 3 T, T1-weighted MRI 2 min post-contrast injection, T2-weighted turbo spin echo imaging, and diffusion-weighted imaging were acquired. Radiomic features were extracted from within manually segmented tumors in 3D and normalized either using z-score normalization or a linear regression model (LRM) accounting for linear dependencies with MRI acquisition parameters. Patients were clustered into two groups based on radiomic profile. Impact of MRI scanning parameters on cluster composition and prognostication were analyzed using Kruskal-Wallis tests, Kaplan-Meier plots, log-rank test, random survival forests and LASSO Cox regression with time-dependent area under curve (tdAUC) (α = 0.05). A large proportion of the radiomic features was statistically associated with MRI scanning protocol in both cohorts (EC: 162/385 [42%]; CC: 180/292 [62%]). A substantial number of EC (49/136 [36%]) and CC (50/132 [38%]) patients changed cluster when clustering was performed after z-score-versus LRM normalization. Prognostic modeling based on cluster groups yielded similar outputs for the two normalization methods in the EC/CC cohorts (log-rank test; z-score: p = 0.02/0.33; LRM: p = 0.01/0.45). Mean tdAUC for prognostic modeling of disease-specific survival (DSS) by the radiomic features in EC/CC was similar for the two normalization methods (random survival forests; z-score: mean tdAUC = 0.77/0.78; LRM: mean tdAUC = 0.80/0.75; LASSO Cox; z-score: mean tdAUC = 0.64/0.76; LRM: mean tdAUC = 0.76/0.75). Severe biases in tumor radiomics data due to MRI scanning parameters exist. Z-score normalization does not eliminate these biases, whereas LRM normalization effectively does. Still, radiomic cluster groups after z-score- and LRM normalization were similarly associated with DSS in EC and CC patients.
Identifiants
pubmed: 39039099
doi: 10.1038/s41598-024-66659-w
pii: 10.1038/s41598-024-66659-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
16826Subventions
Organisme : Trond Mohn stiftelse
ID : BFS2018TMT06
Organisme : Trond Mohn stiftelse
ID : BFS2016TMT01
Organisme : The Western Norway Regional Health Authority
ID : 461120
Organisme : Norges Forskningsråd
ID : 461136
Informations de copyright
© 2024. The Author(s).
Références
Fasmer, K. E. et al. Whole-volume tumor MRI radiomics for prognostic modeling in endometrial cancer. J. Magn. Reson. Imaging. 53(3), 928–937. https://doi.org/10.1002/jmri.27444 (2021).
doi: 10.1002/jmri.27444
pubmed: 33200420
Høivik, E. A. et al. A radiogenomics application for prognostic profiling of endometrial cancer. Commun. Biol. 4(1), 1–12 (2021).
doi: 10.1038/s42003-021-02894-5
Lin, Z. et al. Development and validation of MRI-based radiomics model to predict recurrence risk in patients with endometrial cancer: A multicenter study. Eur. Radiol. 33, 5814–5824. https://doi.org/10.1007/s00330-023-09685-y (2023).
doi: 10.1007/s00330-023-09685-y
pubmed: 37171486
Ai, Y., Zhu, H., Xie, C. & Jin, X. Radiomics in cervical cancer: Current applications and future potential. Crit. Rev. Oncol./Hematol. 152, 102985. https://doi.org/10.1016/j.critrevonc.2020.102985 (2020).
doi: 10.1016/j.critrevonc.2020.102985
pubmed: 32497972
Zheng, R.-R. et al. An MRI-based radiomics signature and clinical characteristics for survival prediction in early-stage cervical cancer. Br. J. Radiol. 95, 20210838. https://doi.org/10.1259/bjr.20210838 (2022).
doi: 10.1259/bjr.20210838
pubmed: 34797703
Guo, W. et al. Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data. J. Med. Imaging 2, 041007. https://doi.org/10.1117/1.JMI.2.4.041007 (2015).
doi: 10.1117/1.JMI.2.4.041007
Chitalia, R. et al. Radiomic tumor phenotypes augment molecular profiling in predicting recurrence free survival after breast neoadjuvant chemotherapy. Commun. Med. 3, 46. https://doi.org/10.1038/s43856-023-00273-1 (2023).
doi: 10.1038/s43856-023-00273-1
pubmed: 36997615
pmcid: 10063641
Grossmann, P. et al. Defining the biological basis of radiomic phenotypes in lung cancer. ELife. https://doi.org/10.7554/eLife.23421 (2017).
doi: 10.7554/eLife.23421
pubmed: 28731408
pmcid: 5590809
Bretzner, M. et al. MRI radiomic signature of white matter hyperintensities is associated with clinical phenotypes. Front. Neurosci. 15, 691244. https://doi.org/10.3389/fnins.2021.691244 (2021).
doi: 10.3389/fnins.2021.691244
pubmed: 34321995
pmcid: 8312571
Hodneland, E. et al. Automated segmentation of endometrial cancer on MR images using deep learning. Sci. Rep. 11(1), 1–8 (2021).
doi: 10.1038/s41598-020-80068-9
Hodneland, E. et al. Fully automatic whole-volume tumor segmentation in cervical cancer. Cancers. https://doi.org/10.3390/cancers14102372 (2022).
doi: 10.3390/cancers14102372
pubmed: 35625977
pmcid: 9139985
Traverso, A., Wee, L., Dekker, A. & Gillies, R. Repeatability and reproducibility of radiomic features: A systematic review. Int. J. Radiat. Oncol. Biol. Phys. 102, 1143–1158. https://doi.org/10.1016/j.ijrobp.2018.05.053 (2018).
doi: 10.1016/j.ijrobp.2018.05.053
pubmed: 30170872
pmcid: 6690209
Fiset, S. et al. Repeatability and reproducibility of MRI-based radiomic features in cervical cancer. Radiother. Oncol. 135, 107–114. https://doi.org/10.1016/j.radonc.2019.03.001 (2019).
doi: 10.1016/j.radonc.2019.03.001
pubmed: 31015155
Park, J. E., Park, S. Y., Kim, H. J. & Kim, H. S. Reproducibility and generalizability in radiomics modeling: Possible strategies in radiologic and statistical perspectives. Korean J. Radiol. 20, 1124–1137. https://doi.org/10.3348/kjr.2018.0070 (2019).
doi: 10.3348/kjr.2018.0070
pubmed: 31270976
pmcid: 6609433
Carré, A. et al. Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics. Sci. Rep. 10, 12340. https://doi.org/10.1038/s41598-020-69298-z (2020).
doi: 10.1038/s41598-020-69298-z
pubmed: 32704007
pmcid: 7378556
Rutt, B. K. & Lee, D. H. The impact of field strength on image quality in MRI. J. Magn. Reson. Imaging. 6, 57–62. https://doi.org/10.1002/jmri.1880060111 (1996).
doi: 10.1002/jmri.1880060111
pubmed: 8851404
Lee, J. et al. Radiomics feature robustness as measured using an MRI phantom. Sci. Rep. 11, 3973. https://doi.org/10.1038/s41598-021-83593-3 (2021).
doi: 10.1038/s41598-021-83593-3
pubmed: 33597610
pmcid: 7889870
Yuan, J. et al. Quantitative assessment of acquisition imaging parameters on MRI radiomics features: A prospective anthropomorphic phantom study using a 3D-T2W-TSE sequence for MR-guided-radiotherapy. Quant. Imaging Med. Surg. 11, 1870–1887. https://doi.org/10.21037/qims-20-865 (2021).
doi: 10.21037/qims-20-865
pubmed: 33936971
pmcid: 8047358
Zwanenburg, A. et al. The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology. 295, 328–338. https://doi.org/10.1148/radiol.2020191145 (2020).
doi: 10.1148/radiol.2020191145
pubmed: 32154773
Brancato, V. et al. Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions. Sci. Rep. 11, 643. https://doi.org/10.1038/s41598-020-80749-5 (2021).
doi: 10.1038/s41598-020-80749-5
pubmed: 33436929
pmcid: 7804929
Panic, J., Defeudis, A., Balestra, G., Giannini, V. & Rosati, S. Normalization strategies in multi-center radiomics abdominal MRI: Systematic review and meta-analyses. IEEE Open J. Eng. Med. Biol. 4, 67–76. https://doi.org/10.1109/OJEMB.2023.3271455 (2023).
doi: 10.1109/OJEMB.2023.3271455
pubmed: 37283773
Castaldo, R., Pane, K., Nicolai, E., Salvatore, M. & Franzese, M. The impact of normalization approaches to automatically detect radiogenomic phenotypes characterizing breast cancer receptors status. Cancers https://doi.org/10.3390/cancers12020518 (2020).
doi: 10.3390/cancers12020518
pubmed: 32102334
pmcid: 7072389
Da-Ano, R. et al. Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies. Sci. Rep. 10(1), 10248. https://doi.org/10.1038/s41598-020-66110-w (2020).
doi: 10.1038/s41598-020-66110-w
pubmed: 32581221
pmcid: 7314795
Zindler, T., Frieling, H., Neyazi, A., Bleich, S. & Friedel, E. Simulating ComBat: How batch correction can lead to the systematic introduction of false positive results in DNA methylation microarray studies. BMC Bioinform. 21(1), 271. https://doi.org/10.1186/s12859-020-03559-6 (2020).
doi: 10.1186/s12859-020-03559-6
Andersen, E. Imagedata: A Python library to handle medical image data in NumPy array subclass Series. J. Open Source Softw. 7(73), 4133 (2022).
doi: 10.21105/joss.04133
van Griethuysen, J. J. M. et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77, e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339 (2017).
doi: 10.1158/0008-5472.CAN-17-0339
pubmed: 29092951
pmcid: 5672828
MATLAB version: 9.13.0 (R2022b). (The MathWorks Inc., 2022).
Benjamini, Y. & Hochberg, Y. Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. R. Stat. Soc. B 57, 289–300 (1995).
doi: 10.1111/j.2517-6161.1995.tb02031.x
Pölsterl, S. scikit-survival: A library for time-to-event analysis built on top of scikit-learn. J. Mach. Learn. Res. 21(1), 1–35 (2020).
Kumar, V. et al. Radiomics: The process and the challenges. Magn. Reson. Imaging. 30(9), 1234–1248. https://doi.org/10.1016/j.mri.2012.06.010 (2012).
doi: 10.1016/j.mri.2012.06.010
pubmed: 22898692
pmcid: 3563280