Thesis Format
Integrated Article
Degree
Doctor of Philosophy
Program
Medical Biophysics
Supervisor
Mattonen, Sarah A.
Abstract
Patients with oropharyngeal cancer (OPC) treated with chemoradiation can experience weight loss and tumor shrinkage, altering the prescribed radiation treatment. In addition, nearly all patients with OPC will suffer treatment-related toxicities. Treatment replanning ensures patients do not receive excessive doses to the normal tissue. There remains an unmet clinical need for robust, predictive models to assist in identifying patients who could benefit from a replan, allowing for better patient management and reduced toxicities. Similarly, given the high survival rates in OPC, clinicians are focused on methods of treatment de-escalation to reduce toxicity. However, there is limited data correlating dosimetry and patient-reported outcomes (PROs) in the de-escalated setting. There remains a need to identify dosimetric predictors to inform current treatment planning. Computed tomography (CT) images are typically taken during the routine radiotherapy workflow. Radiomics aims to extract quantitative imaging features which can be used to develop predictive models. These features can be used in combination with clinical and dosimetric information. The objective of this work was to develop and evaluate tools to assist clinicians in providing personalized treatment options to help reduce treatment-related toxicities and improve quality of life for patients with OPC. Radiomic features were extracted from tumor volumes and parotid glands in a retrospective dataset of patients treated with chemoradiation. Multiple machine learning classifiers were built using the top radiomics features to predict the need for a replan. The best-performing classifier significantly outperformed the baseline clinical model. Next, the model was evaluated in a prospective dataset. The model successfully validated, in addition to achieving a higher accuracy compared to clinicians who were asked to predict which patients they think will require a replan. Finally, regression analyses were performed to evaluate correlations between normal tissue dose metrics and PROs from a randomized control trial investigating de-escalation. Multiple predictors of toxicity were identified, across swallowing, saliva, speech, and general domains. This work has the potential to aid clinicians in identifying patients at a higher risk of the need for a replan, and establish toxicity predictors in patients receiving radiation, to help reduce treatment-related toxicities and improve quality of life.
Summary for Lay Audience
Medical imaging is commonly used to visualize and treat disease. Furthermore, it is now possible to extract quantitative information from medical images. This research is focused on developing software tools to help physicians in prescribing personalized treatment interventions for cancer patients. Patients with oropharyngeal cancer (OPC) who get treated with radiation to the head and neck often experience tumor shrinkage and weight loss, altering the prescribed radiation treatment. As a result, approximately 25% of patients will require a replan (a new radiation plan). Treatment replanning ensures patients do not receive too much radiation to the healthy tissue. It would be beneficial to identify, prior to the start of treatment, which patients will likely require a replan during treatment. This research involved analyzing medical images of patients with OPC to predict which ones will require a replan. Tumors were outlined on the images and computer software extracted information that aimed to describe tumor characteristics, such as shape and texture. Next, algorithms that rely on self-learning looked for patterns within the data to identify which information best predicts which patients will require a replan. Furthermore, we compared this algorithm’s performance to multiple doctors’ performances and found that our algorithm performed with higher accuracy compared to doctors. This algorithm will aid doctors in identifying high-risk patients who could benefit from a replan, reducing treatment delays and limiting radiation to healthy tissue. Apart from weight loss, patients with oropharyngeal cancer will also experience many harmful side effects from their radiation treatment. Doctors are investigating the possibility of prescribing lower radiation doses while still managing to cure patients, but there is limited data to identify which patients will have more severe side effects. This research involved finding relationships between the doses received by sensitive organs during radiation and the severity of side effects experienced. This information will help doctors to keep side effects as low as possible while they prescribe radiation treatments. The tools created in this work will aid doctors in reducing side effects and improving quality of life for patients with OPC.
Recommended Citation
Chinnery, Tricia A., "Predicting Radiation Replanning and Toxicity Outcomes to Support Personalized Treatment in Oropharyngeal Cancer" (2024). Electronic Thesis and Dissertation Repository. 10092.
https://ir.lib.uwo.ca/etd/10092
Creative Commons License
This work is licensed under a Creative Commons Attribution-No Derivative Works 4.0 License.