Ren Yuan Canada

Dr. Ren Yuan, MD, PhD, FRCPC is an oncologic radiologist at BC Cancer Vancouver and Clinical Professor of Radiology at the University of British Columbia. A clinician-scientist at the BC Cancer Research Institute, she leads the Cancer Medical Imaging Core Lab (CanMIC) and co-directs the Radiology/Radiomics Core of the PRO-Lung Program. Her work focuses on thoracic oncology, including lung cancer imaging, early detection, and imaging-based biomarkers to assist risk stratification and treatment monitoring. She contributed to establishing British Columbia’s provincial low-dose CT lung cancer screening program. Dr. Yuan’s research integrates advanced quantitative imaging and AI into clinical practice to advance precision oncology.
Job Title
Oncological Radiologist
Faculty / Department / Division
Medicine/Radiology
Institution / Organisation
University of British Columbia

20 November 2026, Friday

Time Session
11:00
12:00
David Lam Chi-Leung Chairperson Hong Kong
Ernest Mau Ern Poh Chairperson Malaysia
  • Ren Yuan Speaker Canada
    AI Radiomics for the Early Detection of Lung Cancer Background: Lung cancer remains the leading cause of cancer-related mortality in Canada. Low-dose computed tomography (LDCT) screening frequently detects small or ground-glass opacity nodules that are challenging to assess for malignancy. This study aimed to develop a radiomics-based machine-learning model to predict the future malignant behaviour of these difficult nodules. Materials and Methods: Small nodules were drawn from three lung cancer screening datasets: PanCan (n=2,085 participants; N=10,381 nodules), ILST (n=1,082 participants; N=2,389 nodules), and DLCS (n=1,373 participants; N=2,009 nodules). A self-attention deep-learning model was trained for nodule segmentation, and axial masks were reconstructed into three-dimensional core nodule masks. Radiomics features were extracted from four discrete regions: the nodule core and surrounding regions, including core-plus-edge, shell, and shell-without-blood-vessel masks. Machine-learning models were developed and compared with the Brock model. Results: At a low false-positive rate of 10%, the ML-radiomics models demonstrated superior sensitivity to the Brock model across all nodule types in the external validation set. Both approaches identified malignant nodules at baseline that would not have otherwise received interventional management and predicted malignancy up to 2 years before clinical confirmation. Conclusion: A pipeline integrating deep-learning segmentation with ML-radiomics can accurately classify subcentimetre nodules up to approximately 2 years before clinical confirmation of malignancy in lung cancer screening. Keywords: Lung Cancer, LDCT Screening, Radiomics, Machine Learning, Deep Learning
  • Chong Kin Liam Speaker Malaysia
    Lung cancer is a major health problem in the in the Asia-Pacific, with the region accounting for over 60% of global lung cancer diagnoses and deaths. Compared to Western counterparts, lung cancer in Asia exhibits distinct and unique characteristics. Key differences between lung cancer in Asia and outside Asia include a much higher prevalence in never-smokers, younger age of onset, and significantly higher rates of EGFR mutations (30-40% vs. 7-15% in the West). Over 30% of Asian lung cancer patients are never-smokers, with that number rising to over 50% in East Asian women. This is significantly higher than in Western countries. Asian patients have a much higher prevalence of EGFR mutations (30-40%) compared to Caucasian patients (7-15%). Conversely, KRAS mutations which are commonly smoking-related are less frequent in Asian patients (8-10%) than in Western populations (20-30%). While smoking is still a major cause, especially in men (half of the world's smokers live in Asia), never-smoker cases are highly driven by indoor air pollution (biomass fuel), ambient particulate matter (PM2.5), and passive smoking. Asian patients are generally diagnosed at a younger age, with early-onset lung cancer incidents rising, particularly in China, India, and Indonesia. Adenocarcinoma is the most common histological subtype in Asia, often appearing as ground-glass opacities. Asian patients tend to have a better prognosis. However, access to molecular diagnostics and newer, more effective treatments varies significantly between high-income countries (e.g., Japan, South Korea, Australia) and low-to-middle-income countries in the region.
  • Yuh-Min Chen Speaker Taiwan
    "Background Lung cancer is the leading cause of cancer-related mortality in the Asia Pacific (APAC) region, accounting for approximately 60% of global cases. The demographic of lung cancer in this region is shifting, with increasing incidence among younger individuals, non-smokers, and women. Driven by diverse risk factors including air pollution, occupational hazards, genetic predisposition, and household cooking fumes, there is a pressing need for personalized approaches to screening, diagnosis, and treatment. Early Detection & Screening Low-dose computed tomography (LDCT) screening has been instrumental in shifting detection toward early-stage disease. While global trials primarily focus on heavy smokers, regional data indicates that genetic factors play a critical role. A nationwide screening program in Taiwan demonstrated that individuals with a family history of lung cancer have a higher detection rate of early-stage disease (89.6%) compared to heavy smokers (66.1%). This targeted screening approach has led to a significant stage shift and a projected 53% reduction in lung cancer mortality. Targeted Therapy & Immunotherapy Recent phase III trials evaluating targeted therapies (such as osimertinib, amivantamab plus lazertinib, and lorlatinib) and immunotherapies (including pembrolizumab and neoadjuvant nivolumab) show that clinical efficacy and toxicity profiles in Asian cohorts are highly consistent with global populations. Subgroup analyses from landmark trials, including FLAURA2, MARIPOSA, KEYNOTE-189, and CheckMate 816, confirm that APAC patients derive comparable progression-free survival (PFS), overall survival (OS), and pathological complete response (pCR) benefits from these advanced treatment modalities. Conclusions & Future Challenges Despite the biological efficacy of advanced treatments mirroring global outcomes, the APAC region faces unique, systemic challenges. Wide regional variations in healthcare infrastructure, drug pricing, and reimbursement criteria—along with underrepresentation in global clinical trials—create significant disparities in early diagnosis and treatment access. Overcoming these socio-economic barriers and optimizing management strategies in resource-limited settings remain the primary challenges for improving lung cancer survival rates across the Asia Pacific region. "
  • Q&A
Ballroom 3, Lower Ground Floor