Skip to main content

Advertisement

SpringerLink
Log in

Radiomics prognostic analysis of PET/CT images in a multicenter head and neck cancer cohort: investigating ComBat strategies, sub-volume characterization, and automatic segmentation

  • Original Article
  • Published:
European Journal of Nuclear Medicine and Molecular Imaging Aims and scope Submit manuscript

Abstract

Purpose

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.

Methods

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).

Results

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.

Conclusion

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data availability

Datasets are available through the challenge website of https://www.aicrowd.com/challenges/miccai-2021-hecktor.

Code availability

Codes are available from the corresponding author on reasonable request.

Notes

  1. www.miccai2021.org.

  2. https://www.aicrowd.com/challenges/miccai-2021-hecktor.

  3. https://www.radiomics.world/rqs.

References

  1. Chow L. Head and neck cancer. N Engl J Med. 2020. https://doi.org/10.1056/NEJMra1715715.

    Article  PubMed  PubMed Central  Google Scholar 

  2. 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.

    Article  PubMed  Google Scholar 

  3. 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.

    Article  PubMed  Google Scholar 

  4. 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.

    Article  Google Scholar 

  5. 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.

    Article  PubMed  Google Scholar 

  6. 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.

    Article  PubMed  Google Scholar 

  7. 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.

    Article  Google Scholar 

  8. 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.

    Article  PubMed  Google Scholar 

  9. 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.

  10. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  11. 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.

    Article  PubMed  Google Scholar 

  12. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  13. 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.

    Article  PubMed  Google Scholar 

  14. 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.

    Article  PubMed  Google Scholar 

  15. 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.

    Article  PubMed  Google Scholar 

  16. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  17. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  18. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  19. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  20. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  21. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  22. 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.

  23. 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.

    Article  PubMed  Google Scholar 

  24. 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.

  25. Kapp AV, Tibshirani R. Are clusters found in one dataset present in another dataset? Biostatistics. 2007. https://doi.org/10.1093/biostatistics/kxj029.

    Article  PubMed  Google Scholar 

  26. Efron B, Hastie T. Computer age statistical inference. Cambridge University Press. 2016. https://doi.org/10.1017/CBO9781316576533.

  27. 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.

    Article  Google Scholar 

  28. 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.

  29. 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.

  30. 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.

  31. 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.

  32. 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.

  33. 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.

  34. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. The annals of applied statistics. 2008. https://doi.org/10.1214/08-AOAS169.

    Article  Google Scholar 

  35. 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.

    Article  PubMed  Google Scholar 

  36. 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.

    Article  Google Scholar 

  37. 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.

    Article  Google Scholar 

  38. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  39. 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.

  40. 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.

    Article  PubMed  PubMed Central  Google Scholar 

  41. 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.

  42. 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.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We thank the organizers of the HECKTOR 2021 challenge for authorizing the use of the dataset.

Funding

This work was partly funded by (1) regions Bretagne, Pays de la Loire et Centre through the project HARMONY of the Canceropole Grand Ouest; and (2) the National Natural Science Foundation of China under grants 81871437 and 12026601, and the China Scholarship Council under grant 202108440348.

Author information

Authors and Affiliations

  1. School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, Guangdong, China

    Hui Xu & Lijun Lu

  2. LaTIM, INSERM, UMR 1101, University Brest, Brest, France

    Hui Xu, Nassib Abdallah & Mathieu Hatt

  3. LARIS, Univ Angers, EA7315, Angers, France

    Jean-Marie Marion & Pierre Chauvet

  4. INSERM U930, Université François Rabelais de Tours, Tours, France

    Clovis Tauber

  5. Nuclear Medicine Department, CHU and CRCINA, INSERM, CNRS, Univ Angers, Univ Nantes, Nantes, France

    Thomas Carlier

  6. Pazhou Lab, Guangzhou, 510330, China

    Lijun Lu

Authors
  1. Hui Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nassib Abdallah
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jean-Marie Marion
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pierre Chauvet
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Clovis Tauber
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Thomas Carlier
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Lijun Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Mathieu Hatt
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Hui Xu, Nassib Abdallah, Jean-Marie Marion, Pierre Chauvet, Clovis Tauber, and Thomas Carlier searched relevant literatures and collected the data. Hui Xu, Lijun Lu, and Mathieu Hatt designed this study. Hui Xu, Nassib Abdallah, and Mathieu Hatt performed the data analysis and interpretation. Hui Xu and Mathieu Hatt drafted the primary manuscript, and all authors edited and reviewed it.

Corresponding author

Correspondence to Lijun Lu.

Ethics declarations

Ethics approval

This is a retrospective study of a publicly available dataset. The requirement of informed consent was waived.

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the Topical Collection on Oncology—Head and Neck.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 1876 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, H., Abdallah, N., Marion, JM. et al. Radiomics prognostic analysis of PET/CT images in a multicenter head and neck cancer cohort: investigating ComBat strategies, sub-volume characterization, and automatic segmentation. Eur J Nucl Med Mol Imaging 50, 1720–1734 (2023). https://doi.org/10.1007/s00259-023-06118-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00259-023-06118-2

Keywords

Search

Navigation