Advertisement

User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions

  • Mattea L. Welch
    Correspondence
    Corresponding author.
    Affiliations
    Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada

    Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada

    The Techna Institute for the Advancement of Technology for Health, Toronto, Ontario, Canada
    Search for articles by this author
  • Chris McIntosh
    Affiliations
    Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada

    The Techna Institute for the Advancement of Technology for Health, Toronto, Ontario, Canada

    Vector Institute, Toronto, Ontario, Canada

    Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada

    The Joint Department of Medical Imaging, University Health Network, Toronto, Ontario, Canada
    Search for articles by this author
  • Andrea McNiven
    Affiliations
    Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
    Search for articles by this author
  • Shao Hui Huang
    Affiliations
    Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
    Search for articles by this author
  • Bei-Bei Zhang
    Affiliations
    Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
    Search for articles by this author
  • Leonard Wee
    Affiliations
    Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands
    Search for articles by this author
  • Alberto Traverso
    Affiliations
    Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
    Search for articles by this author
  • Brian O'Sullivan
    Affiliations
    Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada
    Search for articles by this author
  • Frank Hoebers
    Affiliations
    Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands
    Search for articles by this author
  • Andre Dekker
    Affiliations
    Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands
    Search for articles by this author
  • David A. Jaffray
    Affiliations
    Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada

    Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada

    IBBME, University of Toronto, Toronto, Ontario, Canada

    Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada

    The Techna Institute for the Advancement of Technology for Health, Toronto, Ontario, Canada
    Search for articles by this author
Published:February 02, 2020DOI:https://doi.org/10.1016/j.ejmp.2020.01.027

      Highlights

      • Designed automated data analysis pipelines with varied user interaction requirements.
      • Integrated clinical, imaging and RT treatment information for H&N LRF prediction.
      • Insights regarding user-driven pipelines and unintended biases.

      Abstract

      Purpose

      Precision cancer medicine is dependent on accurate prediction of disease and treatment outcome, requiring integration of clinical, imaging and interventional knowledge. User controlled pipelines are capable of feature integration with varied levels of human interaction. In this work we present two pipelines designed to combine clinical, radiomic (quantified imaging), and RTx-omic (quantified radiation therapy (RT) plan) information for prediction of locoregional failure (LRF) in head and neck cancer (H&N).

      Methods

      Pipelines were designed to extract information and model patient outcomes based on clinical features, computed tomography (CT) imaging, and planned RT dose volumes. We predict H&N LRF using: 1) a highly user-driven pipeline that leverages modular design and machine learning for feature extraction and model development; and 2) a pipeline with minimal user input that utilizes deep learning convolutional neural networks to extract and combine CT imaging, RT dose and clinical features for model development.

      Results

      Clinical features with logistic regression in our highly user-driven pipeline had the highest precision recall area under the curve (PR-AUC) of 0.66 (0.33–0.93), where a PR-AUC = 0.11 is considered random. CONCLUSIONS: Our work demonstrates the potential to aggregate features from multiple specialties for conditional-outcome predictions using pipelines with varied levels of human interaction. Most importantly, our results provide insights into the importance of data curation and quality, as well as user, data and methodology bias awareness as it pertains to result interpretation in user controlled pipelines.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Physica Medica: European Journal of Medical Physics
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

      1. Gospodarowicz M.K. Henson D.E. Hutter R.V.P. O’Sullivan B. Sobin L.H. Wittekind C. Prognostic factors in cancer. 2nd ed. Wiley-Liss, New York2001
        • Edelstein L.
        Ancient medicine: selected papers of Ludwig Edelstein.
        Johns Hopkins University Press, Baltimore and London1967
        • Moons K.G.M.
        • Royston P.
        • Vergouwe Y.
        • Grobbee D.E.
        • Altman D.G.
        Prognosis and prognostic research: what, why, and how?.
        BMJ. 2009; 338: b375https://doi.org/10.1136/bmj.b375
        • Buchanan S.
        The doctrine of signatures.
        2nd ed. University of Illinois Press, 1991
        • Raghupathi W.
        • Raghupathi V.
        Big data analytics in healthcare: promise and potential.
        Heal Inf Sci Syst. 2014; 2: 10
        • Wu P.-Y.
        • Cheng C.-W.
        • Kaddi C.
        • Venugopalan J.
        • Hoffman R.
        • Wang M.D.
        –Omic and Electronic health record big data analytics for precision medicine.
        IEEE Trans Biomed Eng. 2017; 64: 263-273
        • Desmond-Hellmann S.
        • et al.
        Toward precision medicine: building a knowledge network for biomedical research and a new taxonomy of disease.
        The National Academies Press, Washington, D.C.2011
        • Cadoni G.
        • et al.
        Prognostic factors in head and neck cancer: a 10-year retrospective analysis in a single-institution in Italy.
        Acta Otorhinolaryngol Ital. 2017; 37: 458-466
        • Wopken K.
        • Bijl H.P.
        • Langendijk J.A.
        Prognostic factors for tube feeding dependence after curative (chemo-) radiation in head and neck cancer: a systematic review of literature.
        Radiother Oncol. 2018; 126: 56-67
        • Lin B.M.
        • et al.
        Long-term prognosis and risk factors among patients with HPV-associated oropharyngeal squamous cell carcinoma.
        Cancer. 2013; 119: 3462-3471
        • Mayne S.T.
        • Cartmel B.
        • Kirsh V.
        • Goodwin W.J.
        Alcohol and tobacco use prediagnosis and postdiagnosis, and survival in a cohort of patients with early stage cancers of the oral cavity, pharynx, and larynx.
        Cancer Epidemiol Biomarkers Prev. 2009; 18: 3368-3374
        • Jaffray D.A.
        Image-guided radiotherapy: from current concept to future perspectives.
        Nat Rev Clin Oncol. 2012; 9: 688-699
        • Welch M.L.
        • Jaffray D.A.
        Editorial: radiomics: the new world or another road to El Dorado?.
        JNCI J Natl Cancer Inst. 2017; 109: 7-8
        • Gillies R.J.
        • Kinahan P.E.
        • Hricak H.
        Radiomics: images are more than pictures, they are data.
        Radiology. 2015; 278151169
        • Welch M.L.
        • et al.
        Vulnerabilities of radiomic signature development: the need for safeguards.
        Radiother Oncol. 2019; 130: 2-9
        • Overgaard J.
        • et al.
        Five compared with six fractions per week of conventional radiotherapy of squamous-cell carcinoma of head and neck: DAHANCA 6&7 randomised controlled trial.
        Lancet. 2003; 362: 933-940
        • Bourhis J.
        • et al.
        Hyperfractionated or accelerated radiotherapy in head and neck cancer: a meta-analysis.
        Lancet. 2006; 368: 843-854
        • Peters L.J.
        • et al.
        Critical impact of radiotherapy protocol compliance and quality in the treatment of advanced head and neck cancer: Results from TROG 02.02.
        J Clin Oncol. 2010; 28: 2996-3001
        • Shipley W.U.
        Proton radiation as boost therapy for localized prostatic carcinoma.
        JAMA J Am Med Assoc. 1979; 241: 1912
        • Lyman J.T.
        Complication probability as assessed from dose-volume histograms.
        Radiat Res. 1985; 104: S13-S19
        • Hope A.J.
        • et al.
        Modeling radiation pneumonitis risk with clinical, dosimetric, and spatial parameters.
        Int J Radiat Oncol. 2006; 65: 112-124
        • Jiang W.
        • et al.
        Machine learning methods uncover radio-morphologic dose patterns in salivary glands that predict xerostomia in head and neck cancer patients.
        Int J Radiat Oncol. 2018; 102: S212
        • Monti S.
        • et al.
        Voxel-based analysis unveils regional dose differences associated with radiation-induced morbidity in head and neck cancer patients.
        Sci Rep. 2017; 7https://doi.org/10.1038/s41598-017-07586-x
        • Murdoch T.B.
        • Detsky A.S.
        The inevitable application of big data to health care.
        JAMA. 2014; 309: 1351-1352
        • Mobadersany P.
        • et al.
        Predicting cancer outcomes from histology and genomics using convolutional networks.
        Proc Natl Acad Sci. 2018; 115: E2970-E2979
        • van Griethuysen J.J.M.
        • et al.
        Computational radiomics system to decode the radiographic phenotype.
        Cancer Res. 2017; 77: e104-e107
      2. Zwanenburg A, Leger S, Vallières M, Löck S. Image biomarker standardisation initiative, Dec. 2016.

      3. “pyradiomics” https://pyradiomics.readthedocs.io/en/latest/.

        • Pedregosa F.
        • et al.
        Scikit-learn: machine learning in python.
        J Mach Learn Res. Jan. 2012; 12: 2825-2830
        • Peng C.-Y.J.
        • Lee K.L.
        • Ingersoll G.M.
        An introduction to logistic regression analysis and reporting.
        J Educ Res. 2002; 96: 3-14
        • Breiman L.
        Random forests.
        Mach Learn. 2001; 45: 5-32
        • Ishwaran H.
        • Kogalur U.B.
        • Blackstone E.H.
        • Lauer M.S.
        Random survival forests.
        Ann Appl Stat. 2008; 2: 841-860
      4. Liu FT, Ting KM, Zhou Z-H. Isolation Forest. In: 2008 Eighth IEEE International Conference on Data Mining, 2008, pp. 413–22.

      5. Liu FT, Ting KM. Isolation-based Anomaly Detection, vol. V, pp. 1–44.

        • van der Walt S.
        • et al.
        scikit-image: image processing in Python.
        PeerJ. 2014; 2e453
      6. Shaikh F. An Introduction to PyTorch – A Simple yet Powerful Deep Learning Library, 2018. [Online]. Available: https://www.analyticsvidhya.com/blog/2018/02/pytorch-tutorial/.

      7. Klambauer G, Unterthiner T, Mayr A, Hochreiter S. Self-normalizing neural networks, Adv. Neural Inf. Process. Syst., vol. 2017-Decem, pp. 972–81, 2017.

        • Nielsen M.A.
        Neural networks and deep learning.
        Determination Press, 2015
        • LeCun Y.
        • Bengio Y.
        • Hinton G.
        Deep learning.
        Nature. 2015; 521: 436-444
        • Saito T.
        • Rehmsmeier M.
        The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.
        PLoS ONE. 2015; 10: 1-21
        • Chao K.S.C.
        • et al.
        Intensity-modulated radiation therapy for oropharyngeal carcinoma: impact of tumor volume.
        Int J Radiat Oncol. 2004; 59: 43-50
        • O’Sullivan B.
        • et al.
        Outcomes of HPV-related oropharyngeal cancer patients treated by radiotherapy alone using altered fractionation.
        Radiother Oncol. 2012; 103: 49-56
        • Brierley J.
        • et al.
        Global Consultation on Cancer Staging: promoting consistent understanding and use.
        Nat Rev Clin Oncol. 2019;
        • Tirkes T.
        • Hollar M.A.
        • Tann M.
        • Kohli M.D.
        • Akisik F.
        • Sandrasegaran K.
        Response criteria in oncologic imaging: review of traditional and new criteria.
        RadioGraphics. 2013; 33: 1323-1341
        • Leger S.
        • et al.
        A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling.
        Sci Rep. 2017; 7: 13206
        • Parmar C.
        • Grossmann P.
        • Bussink J.
        • Lambin P.
        • Aerts H.J.W.L.
        Machine learning methods for quantitative radiomic biomarkers.
        Sci Rep. 2015; 5: 13087
      8. Hall EL, et al. A Survey of Preprocessing and Feature Extraction Techniques for Radiographic Images, IEEE Trans. Comput., vol. C–20, no. 9, pp. 1032–1044, 1971.

        • Harlow C.A.
        • Eisenbeis S.A.
        The analysis of radiographic images.
        IEEE Trans Comput. 1973; C-22: 678-689https://doi.org/10.1109/TC.1973.5009135
        • Bogowicz M.
        • et al.
        Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma.
        Acta Oncol (Madr). 2017; 56: 1531-1536
        • Kuno H.
        • et al.
        CT texture analysis potentially predicts local failure in head and neck squamous cell carcinoma treated with chemoradiotherapy.
        Am J Neuroradiol. 2017; 38: 2334-2340
        • Vallières M.
        • et al.
        Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer.
        Sci Rep. 2017; 7: 10117
        • Diehn M.
        • et al.
        Identification of noninvasive imaging surrogates for brain tumor gene-expression modules.
        PNAS. 2008; 105: 5213-5218
        • Aerts H.J.W.L.
        • et al.
        Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.
        Nat Commun. 2014; 5: 4006
        • Bogowicz M.
        • Tanadini-Lang S.
        • Guckenberger M.
        • Riesterer O.
        Combined CT radiomics of primary tumor and metastatic lymph nodes improves prediction of loco-regional control in head and neck cancer.
        Sci Rep. 2019; 9https://doi.org/10.1038/s41598-019-51599-7
        • Kim D.W.
        • Lee S.
        • Kwon S.
        • Nam W.
        • Cha I.H.
        • Kim H.J.
        Deep learning-based survival prediction of oral cancer patients.
        Sci Rep. 2019; 9: 1-10
        • Diamant A.
        • Chatterjee A.
        • Vallières M.
        • Shenouda G.
        • Seuntjens J.
        Deep learning in head & neck cancer outcome prediction.
        Sci Rep. 2019; 9: 1-10
        • Ger R.B.
        • et al.
        Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients.
        PLoS ONE. 2019; 14: 1-13
        • Hazra A.
        Using the confidence interval confidently.
        J Thorac Dis. 2017; 9: 4125-4130
        • Biau D.J.
        • Kernéis S.
        • Porcher R.
        Statistics in brief: the importance of sample size in the planning and interpretation of medical research.
        Clin Orthop Relat Res. 2008; 466: 2282-2288
      9. Su X. Practical Machine Learning Course Notes, Feb.

      10. Dekker A. Who is Building the Big Machine, 2016. [Online]. Available: https://github.com/andredekker/BigMachine/wiki/Who-is-building-the-Big-Machine%3F.