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

作者：Hesham Elhalawani, Timothy A. Lin, Stefania Volpe, Abdallah Mohamed, Aubrey L. White, James Zafereo, Andrew Wong, Joel Berends, Shady Abohashem, Bowman Williams, Jeremy M. Aymard, Aasheesh Kanwar, Subha Perni, Crosby D. Rock, Luke C. Cooksey, Shauna R. Campbell, Pei Yang, K.-A.-N. Nguyen, Rachel Ger, Carlos Cárdenas, Xenia Fave, Carlo Sansone, Gabriele Piantadosi, Stefano Marrone, Rongjie Liu, Chao Huang, Kaixian Yu, Tengfei Li, Yang Yu, Youyi Zhang, Hongtu Zhu, Jeffrey S. Morris, Veerabhadran Baladandayuthapani, John Shumway, Alokananda Ghosh, Andrei Pöhlmann, Hady Ahmady Phoulady, Vibhas Goyal, Guadalupe Canahuate, G. Elisabeta Marai, David M. Vock, Stephen Y. Lai, Dennis Mackin, Laurence E. Court, John Freymann, Keyvan Farahani, Jayashree Kaplathy-Cramer, Clifton D. Fuller · 发表于：Frontiers in Oncology · 年份：2018 · DOI：10.3389/fonc.2018.00294 · 被引用次数：42 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Lung Cancer Diagnosis and Treatment、Pancreatic and Hepatic Oncology Research

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 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 contesta...