Impact of feature harmonization on radiogenomics analysis: Prediction of EGFR and KRAS mutations from non-small cell lung cancer PET/CT images

Computers in Biology and Medicine - Tập 142 - Trang 105230 - 2022
Isaac Shiri1, Mehdi Amini1, Mostafa Nazari2,3, Ghasem Hajianfar2, Atlas Haddadi Avval4, Hamid Abdollahi5, Mehrdad Oveisi6, Hossein Arabi1, Arman Rahmim7,8, Habib Zaidi1,9,10,11
1Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland
2Rajaie Cardiovascular, Medical and Research Center, Iran University of Medical Science, Tehran, Iran
3Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran
4School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
5Department of Radiologic Technology, Faculty of Allied Medicine, Kerman University of Medical Science, Kerman, Iran
6Comprehensive Cancer Centre, School of Cancer & Pharmaceutical Sciences, Faculty of Life Sciences & Medicine, King's College London, London, United Kingdom
7Departments of Radiology and Physics, University of British Columbia, Vancouver, BC, Canada
8Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada
9Geneva University Neurocenter, Geneva University, Geneva, Switzerland
10Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands
11Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark

Tài liệu tham khảo

Ginsburg, 2009, Genomic and personalized medicine: foundations and applications, Transl. Res., 154, 277, 10.1016/j.trsl.2009.09.005 Ettinger, 2010, Non–small cell lung cancer, J. Natl. Compr. Cancer Netw., 8, 740, 10.6004/jnccn.2010.0056 Aerts, 2016, Defining a radiomic response phenotype: a pilot study using targeted therapy in NSCLC, Sci. Rep., 6, 33860, 10.1038/srep33860 Rizzo, 2019, Genomics of non-small cell lung cancer (NSCLC): association between CT-based imaging features and EGFR and K-RAS mutations in 122 patients—an external validation, Eur. J. Radiol., 110, 148, 10.1016/j.ejrad.2018.11.032 Lee, 2020, Radiomics in lung cancer from basic to advanced: current status and future directions, Kr. J. Radiol., 21, 159, 10.3348/kjr.2019.0630 Eberhard, 2005, Mutations in the epidermal growth factor receptor and in KRAS are predictive and prognostic indicators in patients with non–small-cell lung cancer treated with chemotherapy alone and in combination with erlotinib, J. Clin. Oncol., 23, 5900, 10.1200/JCO.2005.02.857 Mak, 2016, Outcomes by EGFR, KRAS and ALK genotype After combined modality therapy for locally advanced non-small cell lung cancer, Int. J. Radiat. Oncol. Biol. Phys., 96, S156, 10.1016/j.ijrobp.2016.06.378 Khodabakhshi, 2021, Overall survival prediction in renal cell carcinoma patients using computed tomography radiomic and clinical information, J. Digit. Imag., 1 Avard, 2021, Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection, Comput. Biol. Med., 141 Khodabakhshi, 2021, Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature, Comput. Biol. Med., 136, 10.1016/j.compbiomed.2021.104752 Carrier-Vallières, 2013 Vallières, 2015, 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, 10.1088/0031-9155/60/14/5471 Amini, 2021, Multi-level multi-modality (PET and CT) fusion radiomics: prognostic modeling for non-small cell lung carcinoma, Phys. Med. Biol., 66, 10.1088/1361-6560/ac287d Amini, 2021, Overall survival prognostic modelling of non-small cell lung cancer patients using positron emission tomography/computed tomography harmonised radiomics features: the quest for the optimal machine learning algorithm, Clin. Oncol. Thawani, 2018, Radiomics and radiogenomics in lung cancer: a review for the clinician, Lung Cancer, 115, 34, 10.1016/j.lungcan.2017.10.015 Sala, 2017, Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging, Clin. Radiol., 72, 3, 10.1016/j.crad.2016.09.013 Shiri, 2021, Machine learning-based prognostic modeling using clinical data and quantitative radiomic features from chest CT images in COVID-19 patients, Comput. Biol. Med., 132, 10.1016/j.compbiomed.2021.104304 Nazari, 2021, Radiomics-based machine learning model to predict risk of death within 5-years in clear cell renal cell carcinoma patients, Comput. Biol. Med., 129, 10.1016/j.compbiomed.2020.104135 Minamimoto, 2017, Prediction of EGFR and KRAS mutation in non-small cell lung cancer using quantitative 18F FDG-PET/CT metrics, Oncotarget, 8, 52792, 10.18632/oncotarget.17782 Shiri, 2020, Next-generation radiogenomics sequencing for prediction of EGFR and KRAS mutation status in NSCLC patients using multimodal imaging and machine learning algorithms, Mol. Imag. Biol., 22, 1132, 10.1007/s11307-020-01487-8 Nair, 2020, Radiogenomic models using machine learning techniques to predict EGFR mutations in non-small cell lung cancer, Can. Assoc. Radiol. J., 72, 109, 10.1177/0846537119899526 Lambin, 2017, Radiomics: the bridge between medical imaging and personalized medicine, Nat. Rev. Clin. Oncol., 14, 749, 10.1038/nrclinonc.2017.141 Traverso, 2018, Repeatability and reproducibility of radiomic features: a systematic review, Int. J. Radiat. Oncol. Biol. Phys., 102, 1143, 10.1016/j.ijrobp.2018.05.053 Ibrahim, 2021, Radiomics for precision medicine: current challenges, future prospects, and the proposal of a new framework, Methods, 188, 20, 10.1016/j.ymeth.2020.05.022 Edalat-Javid, 2022, Cardiac SPECT radiomic features repeatability and reproducibility: a multi-scanner phantom study, J. Nucl. Cardiol., 28, 2730, 10.1007/s12350-020-02109-0 Kumar, 2012, Radiomics: the process and the challenges, Magn. Reson. Imaging, 30, 1234, 10.1016/j.mri.2012.06.010 Yip, 2016, Applications and limitations of radiomics, Phys. Med. Biol., 61, R150, 10.1088/0031-9155/61/13/R150 Fave, 2016, Impact of image preprocessing on the volume dependence and prognostic potential of radiomics features in non-small cell lung cancer, Transl. Cancer Res., 5, 349, 10.21037/tcr.2016.07.11 Zwanenburg, 2019, Radiomics in nuclear medicine: robustness, reproducibility, standardization, and how to avoid data analysis traps and replication crisis, Eur. J. Nucl. Med. Mol. Imag., 46, 2638, 10.1007/s00259-019-04391-8 Johnson, 2006, Adjusting batch effects in microarray expression data using empirical Bayes methods, Biostatistics, 8, 118, 10.1093/biostatistics/kxj037 Čuklina, 2020, Review of batch effects prevention, diagnostics, and correction approaches, 373 Fortin, 2017, Harmonization of multi-site diffusion tensor imaging data, Neuroimage, 161, 149, 10.1016/j.neuroimage.2017.08.047 Fortin, 2018, Harmonization of cortical thickness measurements across scanners and sites, Neuroimage, 167, 104, 10.1016/j.neuroimage.2017.11.024 Da-Ano, 2020, Harmonization strategies for multicenter radiomics investigations, Phys. Med. Biol., 65, 24TR02, 10.1088/1361-6560/aba798 Shayesteh, 2021, Treatment response prediction using MRI-based pre-, post-, and delta-radiomic features and machine learning algorithms in colorectal cancer, Med. Phys., 48, 3691, 10.1002/mp.14896 Cackowski, 2021, ComBat versus cycleGAN for multi-center MR images harmonization Lucia, 2019, External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy, Eur. J. Nucl. Med. Mol. Imag., 46, 864, 10.1007/s00259-018-4231-9 Robinson, 2019, Radiomics robustness assessment and classification evaluation: a two‐stage method demonstrated on multivendor FFDM, Med. Phys., 46, 2145, 10.1002/mp.13455 Orlhac, 2018, A postreconstruction harmonization method for multicenter radiomic studies in PET, J. Nucl. Med., 59, 1321, 10.2967/jnumed.117.199935 Orlhac, 2019, Validation of a method to compensate multicenter effects affecting CT radiomics, Radiology, 291, 53, 10.1148/radiol.2019182023 Ibrahim, 2021, The effects of in-plane spatial resolution on CT-based radiomic features' stability with and without ComBat harmonization, Cancers, 13, 1848, 10.3390/cancers13081848 Mahon, 2020, ComBat harmonization for radiomic features in independent phantom and lung cancer patient computed tomography datasets, Phys. Med. Biol., 65, 15010, 10.1088/1361-6560/ab6177 Dissaux, 2020, Pretreatment (18)F-fdg PET/CT radiomics predict local recurrence in patients treated with stereotactic body radiotherapy for early-stage non-small cell lung cancer: a multicentric study, J. Nucl. Med., 61, 814, 10.2967/jnumed.119.228106 Bakr, 2018, A radiogenomic dataset of non-small cell lung cancer, Sci. Data, 5, 10.1038/sdata.2018.202 Clark, 2013, The cancer imaging archive (TCIA): maintaining and operating a public information repository, J. Digit. Imag., 26, 1045, 10.1007/s10278-013-9622-7 Gevaert, 2012, Non–small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data—methods and preliminary results, Radiology, 264, 387, 10.1148/radiol.12111607 Prior, 2013, TCIA: an information resource to enable open science, 1282 Ashrafinia, 2019 Zwanenburg, 2020, The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping, Radiology, 295, 328, 10.1148/radiol.2020191145 McNitt-Gray, 2020, Standardization in quantitative imaging: a multicenter comparison of radiomic features from different software packages on digital reference objects and patient data sets, Tomography, 6, 118, 10.18383/j.tom.2019.00031 Da-Ano, 2020, Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies, Sci. Rep., 10, 10248, 10.1038/s41598-020-66110-w Peng, 2005, Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy, IEEE Trans. Pattern Anal. Mach. Intell., 27, 1226, 10.1109/TPAMI.2005.159 Zhang, 2017, Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma, Cancer Lett., 403, 21, 10.1016/j.canlet.2017.06.004 Suh, 2020, Oropharyngeal squamous cell carcinoma: radiomic machine-learning classifiers from multiparametric MR images for determination of HPV infection status, Sci. Rep., 10, 17525, 10.1038/s41598-020-74479-x Orlhac, 2020, How can we combat multicenter variability in MR radiomics? Validation of a correction procedure, Eur. Radiol., 1 Doot, 2012, Design considerations for using PET as a response measure in single site and multicenter clinical trials, Acad. Radiol., 19, 184, 10.1016/j.acra.2011.10.008 Rios Velazquez, 2017, Somatic mutations drive distinct imaging phenotypes in lung cancer, Cancer Res., 77, 3922, 10.1158/0008-5472.CAN-17-0122 Zhang, 2018, Quantitative biomarkers for prediction of epidermal growth factor receptor mutation in non-small cell lung cancer, Transl. Oncol., 11, 94, 10.1016/j.tranon.2017.10.012 Wang, 2019, Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning, Eur. Respir. J., 53, 10.1183/13993003.00986-2018 Zhao, 2019, Toward automatic prediction of EGFR mutation status in pulmonary adenocarcinoma with 3D deep learning, Canc. Med., 8, 3532, 10.1002/cam4.2233 Tu, 2019, Radiomics signature: a potential and incremental predictor for EGFR mutation status in NSCLC patients, comparison with CT morphology, Lung Cancer, 132, 28, 10.1016/j.lungcan.2019.03.025 Lasnon, 2016, (18)F-FDG PET/CT heterogeneity quantification through textural features in the era of harmonisation programs: a focus on lung cancer, Eur. J. Nucl. Med. Mol. Imag., 43, 2324, 10.1007/s00259-016-3441-2 Pfaehler, 2020, Experimental multicenter and multivendor evaluation of the performance of PET radiomic features using 3-dimensionally printed phantom inserts, J. Nucl. Med., 61, 469, 10.2967/jnumed.119.229724 Kaalep, 2018, Feasibility of state of the art PET/CT systems performance harmonisation, Eur. J. Nucl. Med. Mol. Imag., 45, 1344, 10.1007/s00259-018-3977-4 Shafiq-ul-Hassan, 2018, Voxel size and gray level normalization of CT radiomic features in lung cancer, Sci. Rep., 8, 10545, 10.1038/s41598-018-28895-9 Shafiq-Ul-Hassan, 2017, Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels, Med. Phys., 44, 1050, 10.1002/mp.12123 Chen, 2011, Removing batch effects in analysis of expression microarray data: an evaluation of six batch Adjustment methods, PLoS One, 6 Parmar, 2015, Machine learning methods for quantitative radiomic biomarkers, Sci. Rep., 5, 13087, 10.1038/srep13087 Da-Ano, 2021, A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets, PLoS One, 16, 10.1371/journal.pone.0253653