"skipMainNavigation"
Search
Quick Search in Journals
Quick Search anywhere
Advanced Search
RSNA Journals
Menu
Previous
Next
Original Research

Spatial Radiomic Graphs for Outcome Prediction in Radiation Therapy–treated Head and Neck Squamous Cell Carcinoma Using Pretreatment CT

Published Online:Feb 21 2025https://doi.org/10.1148/rycan.240161

Abstract

Radiomic graph analysis of pretreatment CT enables holistic analysis of head and neck squamous cell carcinoma tumors and their surrounding environment, showing good performance in local-regional recurrence and distant metastasis prediction and unique model interpretability.

Purpose

To develop a radiomic graph framework, RadGraph, for spatial analysis of pretreatment CT images to improve prediction of local-regional recurrence (LR) and distant metastasis (DM) in head and neck squamous cell carcinoma (HNSCC).

Materials and Methods

This retrospective study included four public pre–radiotherapy treatment CT datasets of patients with HNSCC obtained from The Cancer Imaging Archive (images collected between 2003 and 2018). Computational graphs and graph attention deep learning methods were leveraged to holistically model multiple regions in the head and neck anatomy. Clinical features, including age, sex, and human papillomavirus infection status, were collected for a baseline model. Model performance in predicting LR and DM was evaluated via area under the receiver operating characteristic curve (AUC) and qualitative interpretation of model attention.

Results

A total of 3434 patients (61 years ± 11 [SD], 2774 male) were divided into training (n = 1576), validation (n = 379), and testing (n = 1479) datasets. RadGraph achieved AUCs of up to 0.83 and 0.90 for LR and DM prediction, respectively. RadGraph showed higher performance compared with the clinical baseline (AUCs up to 0.73 for LR prediction and 0.83 for DM prediction) and previously published approaches (AUCs up to 0.81 for LR prediction and 0.87 for DM prediction). Graph attention atlases enabled visualization of regions coinciding with cervical lymph node chains as important for outcome prediction.

Conclusion

RadGraph leveraged information from tumor and nontumor regions to effectively predict LR and DM in a large multi-institutional dataset of patients with radiation therapy–treated HNSCC. Graph attention atlases enabled interpretation of model predictions.

Keywords: CT, Informatics, Neural Networks, Radiation Therapy, Head/Neck, Computer Applications–General (Informatics), Tumor Response, Head and Neck Squamous Cell Carcinoma, Locoregional Recurrence, Radiotherapy, Deep Learning, Radiomics

Supplemental material is available for this article.

© RSNA, 2025

Download as PowerPoint

References

  • 1. Barsouk A, Aluru JS, Rawla P, Saginala K, Barsouk A. Epidemiology, risk factors, and prevention of head and neck squamous cell carcinoma. Med Sci (Basel) 2023;11(2):42.
    Medline Google Scholar
  • 2. Taneja C, Allen H, Koness RJ, Radie-Keane K, Wanebo HJ. Changing patterns of failure of head and neck cancer. Arch Otolaryngol Head Neck Surg 2002;128(3):324–327.
    Medline Google Scholar
  • 3. Fischer CA, Kampmann M, Zlobec I, et al. p16 expression in oropharyngeal cancer: its impact on staging and prognosis compared with the conventional clinical staging parameters. Ann Oncol 2010;21(10):1961–1966.
    Medline Google Scholar
  • 4. McDuffie CM, Amirghahari N, Caldito G, Lian TS, Thompson L, Nathan CO. Predictive factors for posterior triangle metastasis in HNSCC. Laryngoscope 2005;115(12):2114–2117.
    Medline Google Scholar
  • 5. Ferlito A, Rinaldo A, Devaney KO, et al. Prognostic significance of microscopic and macroscopic extracapsular spread from metastatic tumor in the cervical lymph nodes. Oral Oncol 2002;38(8):747–751.
    Medline Google Scholar
  • 6. Prasanna P, Tiwari P, Madabhushi A. Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): A new radiomics descriptor. Sci Rep 2016;6(1):37241.
    Medline Google Scholar
  • 7. Bae J, Cattell R, Zabrocka E, et al. Pre-treatment radiomics from radiotherapy dose regions predict distant brain metastases in stereotactic radiosurgery. In: Proceedings Volume 12031, Medical Imaging 2022: Physics of Medical Imaging. SPIE, 2022; 120311O.
    Google Scholar
  • 8. Aerts HJWL, Velazquez ER, Leijenaar RTH, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 2014;5(1):4006.
    Medline Google Scholar
  • 9. Vallières M, Kay-Rivest E, Perrin LJ, et al. Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep 2017;7(1):10117.
    Medline Google Scholar
  • 10. Huang C, Cintra M, Brennan K, et al. Development and validation of radiomic signatures of head and neck squamous cell carcinoma molecular features and subtypes. EBioMedicine 2019;45:70–80.
    Medline Google Scholar
  • 11. Lv W, Feng H, Du D, Ma J, Lu L. Complementary value of intra- and peri-tumoral PET/CT radiomics for outcome prediction in head and neck cancer. IEEE Access 2021;9:81818–81827.
    Google Scholar
  • 12. Keek S, Sanduleanu S, Wesseling F, et al. Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy. PLoS One 2020;15(5):e0232639. [Published correction appears in PLoS One 2020;15(7):e0237048.]
    Medline Google Scholar
  • 13. Song B, Yang K, Viswanathan VS, et al. CT radiomic signature predicts survival and chemotherapy benefit in stage I and II HPV-associated oropharyngeal carcinoma. NPJ Precis Oncol 2023;7(1):53.
    Medline Google Scholar
  • 14. Diamant A, Chatterjee A, Vallières M, Shenouda G, Seuntjens J. Deep learning in head & neck cancer outcome prediction. Sci Rep 2019;9(1):2764.
    Medline Google Scholar
  • 15. Mateus P, Volmer L, Wee L, et al. Image based prognosis in head and neck cancer using convolutional neural networks: a case study in reproducibility and optimization. Sci Rep 2023;13(1):18176.
    Medline Google Scholar
  • 16. Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y. Graph Attention Networks. arXiv 1710.10903 [preprint]. https://arxiv.org/abs/1710.10903. Posted October 30, 2017. Accessed March 7, 2024.
    Google Scholar
  • 17. Welch M, Kim S, Hope AJ, et al. Computed Tomography Images from Large Head and Neck Cohort (RADCURE) (Version 1). The Cancer Imaging Archive.
    Google Scholar
  • 18. Kazmierski M, Welch M, Kim S, et al. Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics. Cancer Res Commun 2023;3(6):1140–1151.
    Medline Google Scholar
  • 19. Vallières M, Kay-Rivest E, Perrin LJ, et al. Head-Neck-PET-CT. The Cancer Imaging Archive. Published 2017. Accessed March 7, 2024.
    Google Scholar
  • 20. Grossberg AJ, Elhalawani H, Mohamed ASR, et al. HNSCC. The Cancer Imaging Archive. https://doi.org/10.7937/k9/tcia.2020.a8sh-7363 Published 2020. Accessed March 7, 2024.
    Google Scholar
  • 21. Grossberg AJ, Mohamed ASR, Elhalawani H, et al. Imaging and clinical data archive for head and neck squamous cell carcinoma patients treated with radiotherapy. Sci Data 2018;5(1):180173. [Published correction appears in Sci Data 2018;5(1):1.]
    Medline Google Scholar
  • 22. MICCAI/M.D. Anderson Cancer Center Head and Neck Quantitative Imaging Working Group. Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges. Sci Data 2017;4(1):170077.
    Medline Google Scholar
  • 23. Wee L, Dekker A. HEAD-NECK-RADIOMICS-HN1. The Cancer Imaging Archive. Published 2019. Accessed March 7, 2024.
    Google Scholar
  • 24. Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging 2013;26(6):1045–1057.
    Medline Google Scholar
  • 25. Leeman JE, Li JG, Pei X, et al. Patterns of treatment failure and postrecurrence outcomes among patients with locally advanced head and neck squamous cell carcinoma after chemoradiotherapy using modern radiation techniques. JAMA Oncol 2017;3(11):1487–1494.
    Medline Google Scholar
  • 26. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 2012;34(11):2274–2282.
    Medline Google Scholar
  • 27. van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017;77(21):e104–e107.
    Medline Google Scholar
  • 28. Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;27(8):1226–1238.
    Medline Google Scholar
  • 29. Fortunati V, Verhaart RF, van der Lijn F, et al. Tissue segmentation of head and neck CT images for treatment planning: a multiatlas approach combined with intensity modeling. Med Phys 2013;40(7):071905.
    Medline Google Scholar
  • 30. Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW. elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imaging 2010;29(1):196–205.
    Medline Google Scholar
  • 31. Biewald L. Machine Learning Experiment Tracking. Weights & Biases. https://wandb.ai/wandb_fc/articles/reports/Machine-Learning-Experiment-Tracking--Vmlldzo1NDI1Mjcy. Published 2020. Accessed March 7, 2024.
    Google Scholar

Article History

Received: June 14 2024
Revision requested: July 17 2024
Revision received: Dec 9 2024
Accepted: Jan 14 2025
Published online: Feb 21 2025