Radiomics prognostic analysis of PET/CT images in a multicenter head and neck cancer cohort: investigating ComBat strategies, sub-volume characterization, and automatic segmentation.
Automatic segmentation
ComBat
PET/CT
Radiomics
Sub-volume
Journal
European journal of nuclear medicine and molecular imaging
ISSN: 1619-7089
Titre abrégé: Eur J Nucl Med Mol Imaging
Pays: Germany
ID NLM: 101140988
Informations de publication
Date de publication:
05 2023
05 2023
Historique:
received:
20
10
2022
accepted:
16
01
2023
medline:
24
4
2023
pubmed:
24
1
2023
entrez:
23
1
2023
Statut:
ppublish
Résumé
This study aimed to investigate the impact of several ComBat harmonization strategies, intra-tumoral sub-volume characterization, and automatic segmentations for progression-free survival (PFS) prediction through radiomics modeling for patients with head and neck cancer (HNC) in PET/CT images. The HECKTOR MICCAI 2021 challenge set containing PET/CT images and clinical data of 325 oropharynx HNC patients was exploited. A total of 346 IBSI-compliant radiomic features were extracted for each patient's primary tumor volume defined by the reference manual contours. Modeling relied on least absolute shrinkage Cox regression (Lasso-Cox) for feature selection (FS) and Cox proportional-hazards (CoxPH) models were built to predict PFS. Within this methodological framework, 8 different strategies for ComBat harmonization were compared, including before or after FS, in feature groups separately or all features directly, and with center or clustering-determined labels. Features extracted from tumor sub-volume clustering were also investigated for their prognostic additional value. Finally, 3 automatic segmentations (2 threshold-based and a 3D U-Net) were also compared. All results were evaluated with the concordance index (C-index). Radiomics features without harmonization, combined with clinical factors, led to models with C-index values of 0.69 in the testing set. The best version of ComBat harmonization, i.e., after FS, for feature groups separately and relying on clustering-determined labels, achieved a C-index of 0.71. The use of features extracted from tumor sub-volumes further improved the C-index to 0.72. Models that relied on the automatic segmentations yielded close but slightly lower prognostic performance (0.67-0.70) compared to reference contours. A standard radiomics pipeline allowed for prediction of PFS in a multicenter HNC cohort. Applying a specific strategy of ComBat harmonization improved the performance. The extraction of intra-tumoral sub-volume features and automatic segmentation could contribute to the improvement and automation of prognosis modeling, respectively.
Identifiants
pubmed: 36690882
doi: 10.1007/s00259-023-06118-2
pii: 10.1007/s00259-023-06118-2
doi:
Types de publication
Multicenter Study
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1720-1734Subventions
Organisme : National Natural Science Foundation of China
ID : 81871437
Organisme : National Natural Science Foundation of China
ID : 12026601
Organisme : China Scholarship Council
ID : 202108440348
Informations de copyright
© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Références
Chow L. Head and neck cancer. N Engl J Med. 2020. https://doi.org/10.1056/NEJMra1715715 .
doi: 10.1056/NEJMra1715715
pubmed: 33264556
pmcid: 7492079
Hatt M, Majdoub M, Vallieres M, Tixier F, Le Rest CC, Groheux D, et al. 18F-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort. J Nucl Med. 2015. https://doi.org/10.2967/jnumed.114.144055 .
doi: 10.2967/jnumed.114.144055
pubmed: 25883123
Lambin P, Leijenaar R, Deist TM, Peerlings J, de Jong E, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017. https://doi.org/10.1038/nrclinonc.2017.141 .
doi: 10.1038/nrclinonc.2017.141
pubmed: 28975929
Hatt M, Krizsan AK, Rahmim A, Bradshaw TJ, Costa PF, Forgacs A, et al. Joint EANM/SNMMI guideline on radiomics in nuclear medicine. Eur J Nucl Med Mol I. 2022. https://doi.org/10.1007/s00259-022-06001-6 .
doi: 10.1007/s00259-022-06001-6
Hatt M, Cheze LRC, Antonorsi N, Tixier F, Tankyevych O, Jaouen V, et al. Radiomics in PET/CT: current status and future AI-based evolutions. Semin Nucl Med. 2021. https://doi.org/10.1053/j.semnuclmed.2020.09.002 .
doi: 10.1053/j.semnuclmed.2020.09.002
pubmed: 33509369
Hatt M, Le Rest CC, Tixier F, Badic B, Schick U, Visvikis D. Radiomics: data are also images. J Nucl Med. 2019. https://doi.org/10.2967/jnumed.118.220582 .
doi: 10.2967/jnumed.118.220582
pubmed: 31732678
Papadimitroulas P, Brocki L, Chung NC, Marchadour W, Vermet F, Gaubert L, et al. Artificial intelligence: deep learning in oncological radiomics and challenges of interpretability and data harmonization. Physica Med. 2021. https://doi.org/10.1016/j.ejmp.2021.03.009 .
doi: 10.1016/j.ejmp.2021.03.009
Yan J, Chu-Shern JL, Loi HY, Khor LK, Sinha AK, Quek ST, et al. Impact of image reconstruction settings on texture features in 18F-FDG PET. J Nucl Med. 2015. https://doi.org/10.2967/jnumed.115.156927 .
doi: 10.2967/jnumed.115.156927
pubmed: 26229145
Boellaard R, Delgado-Bolton R, Oyen WJ, Giammarile F, Tatsch K, Eschner W, et al. FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015; https://doi.org/10.1007/s00259-014-2961-x .
Pfaehler E, van Sluis J, Merema BB, van Ooijen P, Berendsen RC, van Velden FH, et al. Experimental multicenter and multivendor evaluation of the performance of PET radiomic features using 3-dimensionally printed phantom inserts. J Nucl Med. 2020. https://doi.org/10.2967/jnumed.119.229724 .
doi: 10.2967/jnumed.119.229724
pubmed: 31420497
pmcid: 7067530
Llera A, Huertas I, Mir P, Beckmann CF. Quantitative intensity harmonization of dopamine transporter SPECT images using gamma mixture models. Mol Imaging Biol. 2019. https://doi.org/10.1007/s11307-018-1217-8 .
doi: 10.1007/s11307-018-1217-8
pubmed: 29987621
Marcadent S, Hofmeister J, Preti MG, Martin SP, Van De Ville D, Montet X. Generative adversarial networks improve the reproducibility and discriminative power of radiomic features. Radiol Artif Intell. 2020. https://doi.org/10.1148/ryai.2020190035 .
doi: 10.1148/ryai.2020190035
pubmed: 33937823
pmcid: 8082326
Johnson WE, Li C, Rabinovic A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2007. https://doi.org/10.1093/biostatistics/kxj037 .
doi: 10.1093/biostatistics/kxj037
pubmed: 16984977
Orlhac F, Frouin F, Nioche C, Ayache N, Buvat I. Validation of a method to compensate multicenter effects affecting CT radiomics. Radiology. 2019. https://doi.org/10.1148/radiol.2019182023 .
doi: 10.1148/radiol.2019182023
pubmed: 30694160
Orlhac F, Boughdad S, Philippe C, Stalla-Bourdillon H, Nioche C, Champion L, et al. A postreconstruction harmonization method for multicenter radiomic studies in PET. J Nucl Med. 2018. https://doi.org/10.2967/jnumed.117.199935 .
doi: 10.2967/jnumed.117.199935
pubmed: 29301932
Orlhac F, Eertink JJ, Cottereau AS, Zijlstra JM, Thieblemont C, Meignan M, et al. A guide to ComBat harmonization of imaging biomarkers in multicenter studies. J Nucl Med. 2022. https://doi.org/10.2967/jnumed.121.262464 .
doi: 10.2967/jnumed.121.262464
pubmed: 34531263
pmcid: 8805779
Da-ano R, Masson I, Lucia F, Doré M, Robin P, Alfieri J, et al. Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies. Sci Rep. 2020. https://doi.org/10.1038/s41598-020-66110-w .
doi: 10.1038/s41598-020-66110-w
pubmed: 32581221
pmcid: 7314795
O’Connor JP, Rose CJ, Waterton JC, Carano RA, Parker GJ, Jackson A. Imaging intratumor heterogeneity: role in therapy response, resistance, and clinical outcome. Clin Cancer Res. 2015. https://doi.org/10.1158/1078-0432.CCR-14-0990 .
doi: 10.1158/1078-0432.CCR-14-0990
pubmed: 26561559
pmcid: 5694347
Wu J, Gensheimer MF, Zhang N, Guo M, Liang R, Zhang C, et al. Tumor subregion evolution-based imaging features to assess early response and predict prognosis in oropharyngeal cancer. J Nucl Med. 2020. https://doi.org/10.2967/jnumed.119.230037 .
doi: 10.2967/jnumed.119.230037
pubmed: 32358094
pmcid: 9364898
Xu H, Lv W, Feng H, Du D, Yuan Q, Wang Q, et al. Subregional radiomics analysis of PET/CT imaging with intratumor partitioning: application to prognosis for nasopharyngeal carcinoma. Mol Imaging Biol. 2020. https://doi.org/10.1007/s11307-019-01439-x .
doi: 10.1007/s11307-019-01439-x
pubmed: 33258040
pmcid: 8105262
Vallieres M, Zwanenburg A, Badic B, Cheze LRC, Visvikis D, Hatt M. Responsible radiomics research for faster clinical translation. J Nucl Med. 2018. https://doi.org/10.2967/jnumed.117.200501 .
doi: 10.2967/jnumed.117.200501
pubmed: 29175982
pmcid: 5807530
Andrearczyk V, Oreiller V, Boughdad S, Rest CCL, Elhalawani H, Jreige M, et al. Overview of the HECKTOR challenge at MICCAI 2021: automatic head and neck tumor segmentation and outcome prediction in PET/CT images. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2021. pp. 1–37. https://doi.org/10.1007/978-3-030-98253-9_1 .
Zwanenburg A, Vallières M, Abdalah MA, Aerts HJ, Andrearczyk V, Apte A, et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology. 2020. https://doi.org/10.1148/radiol.2020191145 .
doi: 10.1148/radiol.2020191145
pubmed: 32154773
Iantsen A, Visvikis D, Hatt M. Squeeze-and-excitation normalization for automated delineation of head and neck primary tumors in combined PET and CT images. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2020. pp. 37–43. https://doi.org/10.1007/978-3-030-67194-5_4 .
Kapp AV, Tibshirani R. Are clusters found in one dataset present in another dataset? Biostatistics. 2007. https://doi.org/10.1093/biostatistics/kxj029 .
doi: 10.1093/biostatistics/kxj029
pubmed: 16613834
Efron B, Hastie T. Computer age statistical inference. Cambridge University Press. 2016. https://doi.org/10.1017/CBO9781316576533 .
Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. Journal of British Surgery. 2015. https://doi.org/10.1136/bmj.g7594 .
doi: 10.1136/bmj.g7594
Salmanpour MR, Hajianfar G, Rezaeijo SM, Ghaemi M, Rahmim A. Advanced automatic segmentation of tumors and survival prediction in head and neck cancer. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2021. pp. 202–210. https://doi.org/10.1007/978-3-030-98253-9_19 .
Starke S, Thalmeier D, Steinbach P, Piraud M. A hybrid radiomics approach to modeling progression-free survival in head and neck cancers. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2021. pp. 266–277. https://doi.org/10.1007/978-3-030-98253-9_25 .
Saeed N, Majzoub RA, Sobirov I, Yaqub M. An ensemble approach for patient prognosis of head and neck tumor using multimodal data. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2021. pp. 278–286. https://doi.org/10.1007/978-3-030-98253-9_26 .
Murugesan GK, Brunner E, McCrumb D, Kumar J, VanOss J, Moore S, et al. Head and neck primary tumor segmentation using deep neural networks and adaptive ensembling. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2021. pp. 224–235. https://doi.org/10.1007/978-3-030-98253-9_21 .
Naser MA, Wahid KA, Mohamed AS, Abdelaal MA, He R, Dede C, et al. Progression free survival prediction for head and neck cancer using deep learning based on clinical and PET/CT imaging data. In: 3D head and neck tumor segmentation in PET/CT challenge. Springer; 2021. pp. 287–299. https://doi.org/10.1007/978-3-030-98253-9_27 .
Nagpal C, Yadlowsky S, Rostamzadeh N, Heller K. Deep Cox mixtures for survival regression. In: Machine learning for healthcare conference. PMLR; 2021. pp. 674–708. https://doi.org/10.48550/arXiv.2101.06536 .
Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. The annals of applied statistics. 2008. https://doi.org/10.1214/08-AOAS169 .
doi: 10.1214/08-AOAS169
Bogowicz M, Riesterer O, Stark LS, Studer G, Unkelbach J, Guckenberger M, et al. Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma. Acta Oncol. 2017. https://doi.org/10.1080/0284186X.2017.1346382 .
doi: 10.1080/0284186X.2017.1346382
pubmed: 28820287
Ferreira M, Lovinfosse P, Hermesse J, Decuypere M, Rousseau C, Lucia F, et al. [18F] FDG PET radiomics to predict disease-free survival in cervical cancer: a multi-scanner/center study with external validation. Eur J Nucl Med Mol I. 2021. https://doi.org/10.1007/s00259-021-05397-x .
doi: 10.1007/s00259-021-05397-x
Chatterjee A, Vallières M, Dohan A, Levesque IR, Ueno Y, Saif S, et al. Creating robust predictive radiomic models for data from independent institutions using normalization. IEEE Transactions on Radiation and Plasma Medical Sciences. 2019. https://doi.org/10.1109/TRPMS.2019.2893860 .
doi: 10.1109/TRPMS.2019.2893860
Chen C, Grennan K, Badner J, Zhang D, Gershon E, Jin L, et al. Removing batch effects in analysis of expression microarray data: an evaluation of six batch adjustment methods. PLoS ONE. 2011. https://doi.org/10.1371/journal.pone.0017238 .
doi: 10.1371/journal.pone.0017238
pubmed: 22242141
pmcid: 3248448
Masson I, Da-ano R, Lucia F, Doré M, Castelli J, Goislard De Monsabert C, et al. Statistical harmonization can improve the development of a multicenter CT-based radiomic model predictive of nonresponse to induction chemotherapy in laryngeal cancers. Med Phys. 2021; https://doi.org/10.1002/mp.14948 .
Fontaine P, Andrearczyk V, Oreiller V, Abler D, Castelli J, Acosta O, et al. Cleaning radiotherapy contours for radiomics studies, is it worth it? A head and neck cancer study. Clinical and Translational Radiation Oncology. 2022. https://doi.org/10.1016/j.ctro.2022.01.003 .
doi: 10.1016/j.ctro.2022.01.003
pubmed: 35243026
pmcid: 8881196
Sepehri S, Tankyevych O, Iantsen A, Visvikis D, Hatt M, Le Rest CC. Accurate tumor delineation vs. rough volume of interest analysis for 18F-FDG PET/CT radiomics-based prognostic modeling in non-small cell lung cancer. Front Oncol. 2021. https://doi.org/10.3389/fonc.2021.726865 .
Pietras K, Östman A. Hallmarks of cancer: interactions with the tumor stroma. Exp Cell Res. 2010. https://doi.org/10.1016/j.yexcr.2010.02.045 .
doi: 10.1016/j.yexcr.2010.02.045
pubmed: 20211171