Background- Mediastinal staging is the rate-limiting step prior to initiation of lung cancer treatment and is essential in identifying the most appropriate treatment for the patient. However, this process is often complex and involves multiple imaging modalities including invasive and non-invasive methods for the assessment of lymph nodes in the mediastinum which are error prone. The use of Artificial Intelligence may be able to provide more accurate and precise measurements and eliminate error associated with medical imaging. Methods-This thesis was conducted in three parts. In Part 1, we synthesized and critically appraised the methodological quality of existing studies that use Artificial Intelligence to diagnosis and stage lung cancer from thoracic imaging based on lymph node features. In Part 2, we determined the inter-rater reliability of segmentation of the ultrasonographic lymph node features performed by an experienced endoscopist (manually) compared to NeuralSeg (automatically). In Part 3, we developed and validated a deep neural network through a clinical prediction model to determine if NeuralSeg could learn and identify ultrasonographic lymph node features from endobronchial ultrasound images in patients undergoing lung cancer staging. Results- In Part 1, there were few studies in the Artificial Intelligence literature that provided a complete and detailed description of the design, Artificial Intelligence architecture, validation strategies and performance measures. In Part 2, NeuralSeg and the experienced endosonographer possessed excellent inter-rater correlation (Intraclass Correlation Coefficient = 0.76, 95% CI= 0.70 – 0.80, p<0.0001). In Part 3, NeuralSeg’s algorithm had an accuracy of 73.78% (95% CI: 68.40% to 78.68%), a sensitivity of 18.37% (95% CI: 8.76% to 32.02%) and specificity of 84.34% (95% CI: 79.22% to 88.62%). Conclusions- Analysis of staging modalities for lung cancer using Artificial Intelligence may be useful for when results are inconclusive or uninterpretable by a human reader. NeuralSeg’s high specificity may inform decision-making regarding biopsy if results are benign. Prospective external validation of algorithms and direct comparisons through cut-off thresholds are required to determine their true predictive capability. Future work with a larger dataset will be required to improve and refine the algorithm prior to trials in clinical practice. / Thesis / Master of Science (MSc) / Before deciding on treatment for patients with lung cancer, a critical step in the investigation is finding out whether the lymph nodes in the chest contain cancer cells. This is accomplished through medical imaging of the lymph nodes or taking a biopsy of the lymph node tissue using a needle attached to a scope that is entered through the airway wall. The purpose of these tests is to ensure that lung cancer patients receive the optimal treatment option. However, imaging of the lymph nodes is heavily reliant on human interpretation, which can be error prone. We aimed to critically analyze and investigate the use of Artificial Intelligence to enhance clinician performance for image interpretation. We performed a search of the medical literature for the use of Artificial Intelligence to diagnosis lung cancer from medical imaging. We also taught a computer program, known as NeuralSeg, to learn and identify cancerous lymph nodes from ultrasound imaging. This thesis provides a significant contribution to the Artificial Intelligence literature and provides recommendations for future research.

Background: The standard of care for mediastinal staging during endobronchial ultrasound (EBUS) is Systematic Sampling (SS) where a minimum of 3 lymph node (LN) stations are biopsied, even if they appear normal on imaging. When LNs appear normal on PET and CT, the Canada Lymph Node Score can also identify if they appear normal on EBUS. For these Triple Normal LNs, the pretest probability of malignancy is < 6%, and routine biopsy may not be required. This preliminary study introduced Selective Targeted Sampling (STS), which omits biopsy of Triple Normal LNs and compared it firsthand to SS. Methods: A prospective, feasibility RCT was conducted to determine whether the progression of a definitive trial was warranted. Primary outcomes and their progression criterium were recruitment rate (70% acceptable minimum); procedure length (no overlap between sampling methods’ 95%CIs); and missed nodal metastasis (overlap between sampling methods’ diagnostic accuracy 95%CIs and crossing of the null for the percent difference in diagnosis). cN0-N1 NSCLC patients undergoing EBUS were randomized to the STS or SS arm. Patients in the STS arm were then crossed over to the SS arm to receive standard of care. Wilson’s CI method and McNemar’s test of paired proportions were used for statistical comparison. Surgical pathology was the reference standard. Results: Thirty-eight patients met the eligibility criteria, and all were recruited (100%; 95%CI: 90.82 to 100.00%). The median procedure lengths, in minutes, for STS and SS were 3.07 (95%CI: 2.33 to 5.52) and 19.07 (95%CI: 15.34 to 20.05) respectively. STS had a diagnostic accuracy of 100% (95%CI: 74.65% to 100.00%), whereas SS was 93.75% (95%CI: 67.71% to 99.67%) with the inclusion of inconclusive results. Percent difference in diagnosis between sampling method was 5.35% (95%CI: -0.54% to 11.25%). Conclusion: With the progression criteria successfully met, a subsequent multicentered, non-inferiority crossover trial comparing STS to SS is warranted. / Thesis / Master of Science (MSc) / Before deciding on treatment for patients with lung cancer, a critical step in the investigations is finding out whether the lymph nodes in the chest contain cancer. This is best done with a needle that biopsies those lymph nodes through the walls of the airway, known as endobronchial ultrasound transbronchial needle aspiration. Guidelines require that every lymph node in the chest be biopsied through a process called Systematic Sampling. However, new research has suggested that some lymph nodes may not need a biopsy. These lymph nodes are ones with a very low chance of cancer, based on their imaging tests. In this study, Selective Targeted Sampling was introduced whereby lymph nodes that appeared normal were not initially biopsied. The study followed a feasibility design, which proved sufficient patient interest, adequate safety and possible benefits in pursuing a larger trial comparing Selective Targeted Sampling to Systematic Sampling.