Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article


Doctor of Philosophy


Medical Biophysics


Mattonen, Sarah A.


Surgery is the primary treatment option for patients with early-stage non-small cell lung cancer (NSCLC). However, it is difficult for clinicians to determine which patients are at a high risk of recurrence after surgery and who would benefit from adjuvant therapies. Computed tomography (CT) and positron emission tomography (PET) images are used to determine the cancer staging, which is the gold standard for predicting recurrence. Previous studies have shown that these images may hold prognostic information and can augment clinical data. Machine learning models (MLMs) built utilizing quantitative imaging information, which can outperform current clinical prognostic markers, would therefore aid in decision-making for NSCLC patients. The objective of this work was to develop, validate, and evaluate a clinical decision-support system (CDSS) integrating multi-modality MLMs utilizing imaging and clinical information for the risk stratification of NSCLC patients after surgery. A semi-automatic segmentation algorithm was developed to delineate the tumour on CT. The algorithm provided reproducible segmentations regardless of experience level and was packaged in an efficient and user-friendly interface. CT and PET radiomic features were then extracted from the tumour and peri-tumoural regions, along with vertebral bodies L3-L5 to assess bone marrow uptake on PET. AMLM using these radiomic features and clinical features achieved a concordance of 0.76 and outperformed stage when stratifying patients into high and low risks of recurrence. Subsequently, a deep learning model (DLM) was developed, trained, and externally validated using CT, PET, clinical, surgical, and pathological information from 500 NSCLC patients across two institutions. The DLM outperformed stage achieving an area-under-the-receiver-operating-curve (AUC) of 0.78 and 0.66 in the testing and external validation cohorts, respectively. The validated DLM was integrated into a CDSS, and a user-study was conducted to compare the performance of the DLM to clinicians and evaluate how the CDSS would be best adopted into clinical practice. The CDSS was able to augment the performance of clinicians when predicting post-surgical recurrence and improved their decision confidence. In conclusion, these contributions have the potential to lead to more personalized treatment decisions and improve outcomes for patients with NSCLC.

Summary for Lay Audience

Non-small cell lung cancer (NSCLC) is the most common type of lung cancer. When caught early, the best treatment is surgery as it provides the best chance of getting rid of the cancer while minimizing side-effects. However, after surgery, the decision on who to provide additional treatment to is difficult, and many patients who would benefit from added therapies to prevent the cancer from returning are missed. Medical images currently used in the clinical workflow may hold information to help better identify these patients. Therefore, this thesis looked to develop a prediction model using medical images combined with clinical information to identify how a patient will do after surgery and improve the personalization of NSCLC treatment. We used features that clinicians cannot see with their eyes from the medical images to build a model to predict which patients are more likely to have their cancer return after surgery. We then developed a deep learning model, where the computer can automatically find patterns in the medical images. The model was able to better identify patient outcomes when compared to the current gold standard for predicting prognosis, the cancer stage of the patient. The deep learning model was then integrated into a computer system for clinicians to use. A user-study showed that the system improved the performance of clinicians when identifying high-risk patients. These results demonstrate that a predictive model using imaging and clinical information helps clinicians better identify NSCLC patients at a higher risk of recurrence who need additional treatment. This could lead to improved treatment outcomes for NSCLC patients.

Creative Commons License

Creative Commons Attribution-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-No Derivative Works 4.0 License.

Available for download on Monday, December 01, 2025