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

Autor:	Elhalawani H; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Lin TA; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Baylor College of Medicine, Houston, TX, United States., Volpe S; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Università degli Studi di Milano, Milan, Italy., Mohamed ASR; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Department of Clinical Oncology and Nuclear Medicine, Alexandria University, Alexandria, Egypt., White AL; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; McGovern Medical School, University of Texas, Houston, TX, United States., Zafereo J; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; McGovern Medical School, University of Texas, Houston, TX, United States., Wong AJ; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; School of Medicine, The University of Texas Health Science Center San Antonio, San Antonio, TX, United States., Berends JE; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; School of Medicine, The University of Texas Health Science Center San Antonio, San Antonio, TX, United States., AboHashem S; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Department of Cardiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States., Williams B; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Furman University, Greenville, SC, United States., Aymard JM; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Abilene Christian University, Abilene, TX, United States., Kanwar A; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Department of Radiation Oncology, Oregon Health and Science University, Portland, OR, United States., Perni S; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, New York, NY, United States., Rock CD; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Texas Tech University Health Sciences Center El Paso, El Paso, TX, United States., Cooksey L; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; University of North Texas Health Science Center, Fort Worth, TX, United States., Campbell S; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Department of Radiation Oncology, Cleveland Clinic, Cleveland, OH, United States., Yang P; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Baylor College of Medicine, Houston, TX, United States., Nguyen K; Colgate University, Hamilton City, CA, United States., Ger RB; Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States.; Department of Radiation Physics, Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States., Cardenas CE; Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States.; Department of Radiation Physics, Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States., Fave XJ; Moores Cancer Center, University of California, La Jolla, San Diego, CA, United States., Sansone C; Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione, Università Degli Studi di Napoli Federico II, Naples, Italy., Piantadosi G; Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione, Università Degli Studi di Napoli Federico II, Naples, Italy., Marrone S; Dipartimento di Ingegneria Elettrica e delle Tecnologie dell'Informazione, Università Degli Studi di Napoli Federico II, Naples, Italy., Liu R; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Huang C; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Yu K; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Li T; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Yu Y; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Zhang Y; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Zhu H; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Morris JS; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Baladandayuthapani V; Baylor College of Medicine, Houston, TX, United States.; Department of Biostatistics, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Shumway JW; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Ghosh A; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Pöhlmann A; Fraunhofer-Institut für Fabrikbetrieb und Automatisierung (IFF), Magdeburg, Germany., Phoulady HA; Department of Computer Science, University of Southern Maine, Portland, OR, United States., Goyal V; Indian Institute of Technology Hyderabad, Sangareddy, India., Canahuate G; University of Iowa, Iowa City, IA, United States., Marai GE; University of Illinois at Chicago, Chicago, IL, United States., Vock D; Department of Biostatistics, School of Public Health, University of Minnesota, Minneapolis, MN, United States., Lai SY; Department of Head and Neck Surgery, University of Texas MD Anderson Cancer Center, Houston, TX, United States., Mackin DS; Colgate University, Hamilton City, CA, United States.; Department of Radiation Physics, Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States., Court LE; Colgate University, Hamilton City, CA, United States.; Department of Radiation Physics, Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States., Freymann J; Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., Frederick, MD, United States., Farahani K; National Cancer Institute, Rockville, MD, United States.; The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins Medicine, Baltimore, MD, United States., Kaplathy-Cramer J; Department of Radiology and Athinoula A. Martinos Center for Biomedical Imaging, MGH/Harvard Medical School, Boston, MA, United States., Fuller CD; Department of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, United States.; Baylor College of Medicine, Houston, TX, United States.; Department of Radiation Physics, Graduate School of Biomedical Sciences, MD Anderson Cancer Center, Houston, TX, United States.
Jazyk:	angličtina
Zdroj:	Frontiers in oncology [Front Oncol] 2018 Aug 17; Vol. 8, pp. 294. Date of Electronic Publication: 2018 Aug 17 (Print Publication: 2018).
DOI:	10.3389/fonc.2018.00294
Abstrakt:	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.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu