McGeachy, PhilipBrown, Jo-AnneBarrett, Fletcher2023-01-132023-01-132023-01-05Barrett, F. (2023). Predicting optimal motion management strategy in radiotherapy treatment of right-sided breast cancer (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.http://hdl.handle.net/1880/115668Deep inspiration breath hold (DIBH) is a motion management technique that can be used to reduce dose to healthy tissue for right-sided breast cancer radiotherapy. With DIBH being a resource-intensive technique, it is typically reserved for patients that are initially scanned under free breathing (FB) conditions but cannot meet healthy tissue dose constraints during treatment planning. This workflow requires patients to return for a new DIBH scan, leading to inefficiencies and possible delays in treatment. This thesis focuses on developing a machine learning (ML) model to predict the optimal motion management technique during the computed tomography (CT) simulation appointment, from the patient anatomy in the FB CT-sim scan. Several models combining different supervised ML algorithms and anatomic measurements were assessed in terms of accuracy predicting the optimal motion management technique. Additionally, the timing and reliability of the anatomical measurements used in the models were examined via a blind study to determine the clinical feasibility of each model. It was found that a logistic regression ML model using two anatomical measurements yielded the most favourable balance of accuracy, timing, and reliability to predict the optimal motion management technique.engUniversity of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.Chemistry--RadiationPhysicsmaster thesis