Preliminary report on harmonization of features extraction process using the ComBat tool in the multi-center "Blue Sky Radiomics" study on stage III unresectable NSCLC

Raffaella Fiamma Cabini, Francesca Brero, Andrea Lancia, Chiara Stelitano, Olga Oneta, Elena Ballante, Emanuela Puppo, Manuel Mariani, Emanuele Alì, Valentina Bartolomeo, Marianna Montesano, Elisa Merizzoli, Diana Aluia, Francesco Agustoni, Giulia Maria Stella, Roger Sun, Linda Bianchini, Eric Deutsch, Silvia Figini, Chandra Bortolotto, Lorenzo Preda, Alessandro Lascialfari, Andrea Riccardo Filippi, Raffaella Fiamma Cabini, Francesca Brero, Andrea Lancia, Chiara Stelitano, Olga Oneta, Elena Ballante, Emanuela Puppo, Manuel Mariani, Emanuele Alì, Valentina Bartolomeo, Marianna Montesano, Elisa Merizzoli, Diana Aluia, Francesco Agustoni, Giulia Maria Stella, Roger Sun, Linda Bianchini, Eric Deutsch, Silvia Figini, Chandra Bortolotto, Lorenzo Preda, Alessandro Lascialfari, Andrea Riccardo Filippi

Abstract

Background and purpose: In the retrospective-prospective multi-center "Blue Sky Radiomics" study (NCT04364776), we plan to test a pre-defined radiomic signature in a series of stage III unresectable NSCLC patients undergoing chemoradiotherapy and maintenance immunotherapy. As a necessary preliminary step, we explore the influence of different image-acquisition parameters on radiomic features' reproducibility and apply methods for harmonization.

Material and methods: We identified the primary lung tumor on two computed tomography (CT) series for each patient, acquired before and after chemoradiation with i.v. contrast medium and with different scanners. Tumor segmentation was performed by two oncological imaging specialists (thoracic radiologist and radio-oncologist) using the Oncentra Masterplan® software. We extracted 42 radiomic features from the specific ROIs (LIFEx). To assess the impact of different acquisition parameters on features extraction, we used the Combat tool with nonparametric adjustment and the longitudinal version (LongComBat).

Results: We defined 14 CT acquisition protocols for the harmonization process. Before harmonization, 76% of the features were significantly influenced by these protocols. After, all extracted features resulted in being independent of the acquisition parameters. In contrast, 5% of the LongComBat harmonized features still depended on acquisition protocols.

Conclusions: We reduced the impact of different CT acquisition protocols on radiomic features extraction in a group of patients enrolled in a radiomic study on stage III NSCLC. The harmonization process appears essential for the quality of radiomic data and for their reproducibility. ClinicalTrials.gov Identifier: NCT04364776, First Posted:April 28, 2020, Actual Study Start Date: April 15, 2020, https://ichgcp.net/clinical-trials-registry/NCT04364776 .

Keywords: ComBat; Harmonization; NSCLC; Radiomic features; Robustness.

Conflict of interest statement

Lorenzo Preda is member of the Insights into Imaging Editorial Board. He has not taken part in the review or selection process of this article. The remaining authors declare that they have no competing interests.

© 2022. The Author(s).

Figures

Fig. 1
Fig. 1
An example of feature harmonization for the GLRLM SRE feature. On the left is the box-plot for the feature distribution across batches (defined as protocols) before ComBat harmonization, and on the right is the Box-plot after the harmonization
Fig. 2
Fig. 2
Statistical box-plots of GLRLM SRE feature distribution (pre-harmonization and post-harmonization with ComBat) across different image-acquisition parameters: Scanner, kVp, Convolutional Kernel, Exposure Time
Fig. 3
Fig. 3
An example of feature harmonization for a sample feature, GLRLM SRE. On the left is the box-plot for the feature distribution across batches (defined as protocols) before longComBat harmonization, and on the right is the Box-plot after the harmonization
Fig. 4
Fig. 4
Statistical box-plots of GLRLM SRE feature distribution (pre- and post-harmonization with longComBat) across different image-acquisition parameters: Scanner, kVp, Convolutional Kernel, Exposure Time

References

    1. Baldini E, Tibaldi C, Paoli CD. Chemo-radiotherapy integration in unresectable locally advanced non-small-cell lung cancer: a review. Clin Transl Oncol. 2020;22(10):1681–1686. doi: 10.1007/s12094-020-02326-6.
    1. Antonia SJ. Durvalumab after chemoradiotherapy in stage iii non–small-cell lung cancer. N Engl J Med. 2017;377(20):1919–1929. doi: 10.1158/1535-7163.MCT-14-0983.
    1. Faivre-Finn C, Vicente D, Kurata T, et al. Four-year survival with durvalumab after chemoradiotherapy in stage iii nsclc—an update from the pacific trial. J Thorac Oncol. 2021;16(5):860–867. doi: 10.1016/j.jtho.2020.12.015.
    1. Horvath L, Thienpont B, Zhao L, Wolf D, Pircher A. Overcoming immunotherapy resistance in non-small cell lung cancer (nsclc)—novel approaches and future outlook. Mol Cancer. 2020;19:1–15. doi: 10.1186/s12943-020-01260-z.
    1. Patel SP, Kurzrock R. Pd-l1 expression as a predictive biomarker in cancer immunotherapy. Mol Cancer Ther. 2015;14(4):847–856. doi: 10.1158/1535-7163.MCT-14-0983.
    1. Newman AM, Bratman SV, To J, et al. An ultrasensitive method for quantitating circulating tumor dna with broad patient coverage. Nat Med. 2014;20(5):548–554. doi: 10.1038/nm.3519.
    1. Bortolotto C, Lancia A, Stelitano C, et al. Radiomics features as predictive and prognostic biomarkers in nsclc. Expert Rev Anticancer Ther. 2021;21:257–266. doi: 10.1080/14737140.2021.1852935.
    1. Jazieh K, Khorrami M, Saad AM et al (2021) Novel imaging biomarkers predict progression-free survival in stage 3 NSCLC treated with chemoradiation and durvalumab. J Clin Oncol 39:15_suppl, 3054
    1. Lambin P, Leijenaar RT, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14(12):749–762. doi: 10.1038/nrclinonc.2017.141.
    1. Crombé A, Kind M, Fadli D. Intensity harmonization techniques influence radiomics features and radiomics-based predictions in sarcoma patients. Sci Rep. 2020;10(1):1–13. doi: 10.1038/s41598-019-56847-4.
    1. Choe J, Lee SM, Do K-H, et al. Deep learning–based image conversion of ct reconstruction kernels improves radiomics reproducibility for pulmonary nodules or masses. Radiology. 2019;292(2):365–373. doi: 10.1148/radiol.2019181960.
    1. Da-Ano R, Masson I, Lucia F, et al. Performance comparison of modified combat for harmonization of radiomic features for multicenter studies. Sci Rep. 2020;10(1):1–12. doi: 10.1038/s41598-020-66110-w.
    1. Fortin J-P, Parker D, Tunc B, et al. Harmonization of multi-site diffusion tensor imaging data. Neuroimage. 2017;161:149–170. doi: 10.1016/j.neuroimage.2017.08.047.
    1. Fortin J-P, Cullen N, Sheline YI, et al. Harmonization of cortical thickness measurements across scanners and sites. Neuroimage. 2018;167:104–120. doi: 10.1016/j.neuroimage.2017.11.024.
    1. Masson I, Da-ano R, Lucia F, et al. Statistical harmonization can improve the development of a multicenter ct based radiomic model predictive of non-response to induction chemotherapy in laryngeal cancers. Med Phys. 2021;48:4099–4109. doi: 10.1002/mp.14948.
    1. Mahon R, Ghita M, Hugo G, Weiss E. Combat harmonization for radiomic features in independent phantom and lung cancer patient computed tomography datasets. Phys Med Biol. 2020;65(1):015010. doi: 10.1088/1361-6560/ab6177.
    1. Beer JC, Tustison NJ, Cook PA, et al. Longitudinal combat: a method for harmonizing longitudinal multi-scanner imaging data. Neuroimage. 2020;220:117129. doi: 10.1016/j.neuroimage.2020.117129.
    1. Sun R, Limkin EJ, Vakalopoulou M, Dercle L et al (2018) 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(9):1180–1191
    1. Nioche C, Orlhac F, Boughdad S et al (2018) Lifex: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78(16):4786–4789
    1. Johnson WE, Li C, Rabinovic A (2007) Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8(1):118–127. 10.1093/biostatistics/kxj037
    1. Mackin D, Ger R, Dodge C et al (2018) Effect of tube current on computed tomography radiomic features. Sci Rep 8(1). 10.1038/s41598-018-20713-6

Source: PubMed

赞助者和合作者

医疗条件

药物干预

3
订阅