User-controlled pipelines for feature integration and head and neck radiation therapy outcome predictions |
| |
| Institution: | 1. Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada;2. Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada;3. IBBME, University of Toronto, Toronto, Ontario, Canada;4. Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands;5. Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada;6. The Techna Institute for the Advancement of Technology for Health, Toronto, Ontario, Canada;7. Vector Institute, Toronto, Ontario, Canada;8. Peter Munk Cardiac Centre, University Health Network, Toronto, Ontario, Canada;9. The Joint Department of Medical Imaging, University Health Network, Toronto, Ontario, Canada;1. Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences, Guangzhou, 510080, China;2. Internal Medicine Residency, Florida Hospital, Orlando, FL, 32804, USA;1. Department of Radiation Oncology, The University of Michigan, Ann Arbor, MI, USA;2. London Health Sciences Centre, Western University, London, ON, Canada;3. Department of Radiation Oncology, UCSF Medical Center at Mission Bay, San Francisco, CA, USA;1. Department of Radiation Oncology, Cancer Center and State Key Laboratory of Biotherapy, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, China;2. Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, Guangdong, China;3. Department of Biostatistics, Gillings School of Public Health, University of North Carolina-Chapel Hill, Chapel Hill, NC 27599, United States;4. School of Basic Medical Sciences and Forensic Medicine, Sichuan University, Chengdu, Sichuan 610041, China;1. Department of Radiology, The Netherlands Cancer Institute, Amsterdam, the Netherlands;2. Department of Head and Neck Oncology and Surgery, The Netherlands Cancer Institute, Amsterdam, the Netherlands;3. GROW School for Oncology and Developmental Biology – University of Maastricht, Maastricht, the Netherlands;4. Department of Oral and Maxillofacial Surgery, Amsterdam University Medical Center (AUMC), Amsterdam, the Netherlands;5. Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, the Netherlands;6. Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, United States;7. Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, the Netherlands;8. Department of Regional Health Research, University of Southern Denmark, Denmark;9. Department of Radiology, Amsterdam University Medical Center, Amsterdam, the Netherlands |
| |
| Abstract: | PurposePrecision 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).MethodsPipelines 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.ResultsClinical 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: | Head and neck Outcome prediction Deep learning Machine learning User-controlled Bias |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
