Skip NavigationSkip to Content
Return Return to Search Results

Machine Learning Applications in Head and Neck Radiation Oncology: Lessons From Open-Source Radiomics Challenges

  1. Author:
    Elhalawani, Hesham
    Lin, Timothy A.
    Volpe, Stefania
    Mohamed, Abdallah S. R.
    White, Aubrey L.
    Zafereo, James
    Wong, Andrew J.
    Berends, Joel E.
    AboHashem, Shady
    Williams, Bowman
    Aymard, Jeremy M.
    Kanwar, Aasheesh
    Perni, Subha
    Rock, Crosby D.
    Cooksey, Luke
    Campbell, Shauna
    Yang, Pei
    Ger, Rachel B.
    Cardenas, Carlos E.
    Fave, Xenia J.
    Sansone, Carlo
    Piantadosi, Gabriele
    Marrone, Stefano
    Liu, Rongjie
    Huang, Chao
    Yu, Kaixian
    Li, Tengfei
    Yu, Yang
    Zhang, Youyi
    Zhu, Hongtu
    Morris, Jeffrey S.
    Baladandayuthapani, Veerabhadran
    Shumway, John W.
    Ghosh, Alakonanda
    Poehlmann, Andrei
    Phoulady, Hady A.
    Goyal, Vibhas
    Canahuate, Guadalupe
    Marai, G. Elisabeta
    Vock, David
    Lai, Stephen Y.
    Mackin, Dennis S.
    Court, Laurence E.
    Freymann, John
    Farahani, Keyvan
    Kaplathy-Cramer, Jayashree
    Fuller, Clifton D.

  2. Author Address

    Univ Texas MD Anderson Canc Ctr, Dept Radiat Oncol, Houston, TX USA.Baylor Coll Med, Houston, TX 77030 USA.Univ Milan, Milan, Italy.Alexandria Univ, Dept Clin Oncol & Nucl Med, Alexandria, Egypt.Univ Texas Houston, McGovern Med Sch, Houston, TX USA.Univ Texas Hlth Sci Ctr San Antonio, Sch Med, San Antonio, TX 78229 USA.Harvard Med Sch, Massachusetts Gen Hosp, Dept Cardiol, Boston, MA USA.Furman Univ, Greenville, SC 29613 USA.Abilene Christian Univ, Abilene, TX 79699 USA.Oregon Hlth & Sci Univ, Dept Radiat Oncol, Portland, OR 97201 USA.Mem Sloan Kettering Canc Ctr, Dept Radiat Oncol, 1275 York Ave, New York, NY 10021 USA.Texas Tech Univ Hlth Sci Ctr El Paso, El Paso, TX USA.Univ North Texas Hlth Sci Ctr, Ft Worth, TX USA.Cleveland Clin, Dept Radiat Oncol, Cleveland, OH 44106 USA.Colgate Univ, Hamilton, CA USA.MD Anderson Canc Ctr, Grad Sch Biomed Sci, Houston, TX USA.MD Anderson Canc Ctr, Grad Sch Biomed Sci, Dept Radiat Phys, Houston, TX USA.Univ Calif La Jolla, Moores Canc Ctr, San Diego, CA USA.Univ Naples Federico II, Dipartimento Ingn Elettr & Tecnol Informaz, Naples, Italy.Univ Texas MD Anderson Canc Ctr, Dept Biostat, Houston, TX 77030 USA.Fraunhofer Inst Fabrikbetrieb & Automatisierun IF, Magdeburg, Germany.Univ Southern Maine, Dept Comp Sci, Portland, OR USA.Indian Inst Technol Hyderabad, Sangareddy, India.Univ Iowa, Iowa City, IA USA.Univ Illinois, Chicago, IL USA.Univ Minnesota, Sch Publ Hlth, Dept Biostat, Minneapolis, MN USA.Univ Texas MD Anderson Canc Ctr, Dept Head & Neck Surg, Houston, TX 77030 USA.Leidos Biomed Res Inc, Frederick Natl Lab Canc Res, Frederick, MD USA.NCI, Rockville, MD USA.Johns Hopkins Med, Russell H Morgan Dept Radiol & Radiol Sci, Baltimore, MD USA.Harvard Med Sch, Dept Radiol, Boston, MA USA.Harvard Med Sch, Athinoula A Martinos Ctr Biomed Imaging, Boston, MA USA.
    1. Year: 2018
    2. Date: Aug 17
    3. Epub Date: 2018 08 17
  2. Journal: Frontiers in Oncology
  3. FRONTIERS MEDIA SA,
    1. 8
    2. Pages: 294
  5. Type of Article: Article
  6. Article Number: 294
  7. ISSN: 2234-943X
  1. Abstract:

    Radiomics leverages existing image datasets to provide non-visible data extraction via image post-processing, with the aim of identifying prognostic, and predictive imaging features at a sub-region of interest level. However, the application of radiomics is hampered by several challenges such as lack of image acquisition/analysis method standardization, impeding generalizability. As of yet, radiomics remains intriguing, but not clinically validated. We aimed to test the feasibility of a non-custom-constructed platform for disseminating existing large, standardized databases across institutions for promoting radiomics studies. Hence, University of Texas MD Anderson Cancer Center organized two public radiomics challenges in head and neck radiation oncology domain. This was done in conjunction with MICCAI 2016 satellite symposium using Kaggle-in-Class, a machine-learning and predictive analytics platform. We drew on clinical data matched to radiomics data derived from diagnostic contrast-enhanced computed tomography (CECT) images in a dataset of 315 patients with oropharyngeal cancer. Contestants were tasked to develop models for (i) classifying patients according to their human papillomavirus status, or (ii) predicting local tumor recurrence, following radiotherapy. Data were split into training, and test sets. Seventeen teams from various professional domains participated in one or both of the challenges. This review paper was based on the contestants' feedback; provided by 8 contestants only (47%). Six contestants (75%) incorporated extracted radiomics features into their predictive model building, either alone (n = 5; 62.5%), as was the case with the winner of the "HPV" challenge, or in conjunction with matched clinical attributes (n = 2; 25%). Only 23% of contestants, notably, including the winner of the "local recurrence" challenge, built their model relying solely on clinical data. In addition to the value of the integration of machine learning into clinical decision-making, our experience sheds light on challenges in sharing and directing existing datasets toward clinical applications of radiomics, including hyper-dimensionality of the clinical/imaging data attributes. Our experience may help guide researchers to create a framework for sharing and reuse of already published data that we believe will ultimately accelerate the pace of clinical applications of radiomics; both in challenge or clinical settings.

    See More

  1. Keywords:

External Sources

  1. View Full Text
  2. DOI: 10.3389/fonc.2018.00294
  3. PMID: 30175071
  4. PMCID: PMC6107800
  5. View record in Web of Science®
  6. WOS: 000441889500001

Library Notes

  1. Fiscal Year: FY2017-2018
NCI at Frederick

You are leaving a government website.

This external link provides additional information that is consistent with the intended purpose of this site. The government cannot attest to the accuracy of a non-federal site.

Linking to a non-federal site does not constitute an endorsement by this institution or any of its employees of the sponsors or the information and products presented on the site. You will be subject to the destination site's privacy policy when you follow the link.

ContinueCancel