Mattea L Welch1, Chris McIntosh2, Andrea McNiven3, Shao Hui Huang3, Bei-Bei Zhang3, Leonard Wee4, Alberto Traverso5, Brian O'Sullivan3, Frank Hoebers4, Andre Dekker4, David A Jaffray6. 1. 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. Electronic address: mattea.welch@rmp.uhn.ca. 2. 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. 3. Department of Radiation Oncology, University of Toronto, Toronto, Ontario, Canada; Princess Margaret Cancer Centre, University Health Network, Toronto, Ontario, Canada. 4. Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, The Netherlands. 5. 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. 6. 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.
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.
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.
Authors: Howard E Morgan; Kai Wang; Michael Dohopolski; Xiao Liang; Michael R Folkert; David J Sher; Jing Wang Journal: Quant Imaging Med Surg Date: 2021-12