Shiqin Su
Associate Member
Assistant Professor
The University of Texas MD Anderson Cancer Center at Houston
Department of Radiation Physics
- My research focuses on leveraging advanced machine learning techniques to enhance radiation therapy planning, with a particular emphasis on automated dose prediction and optimization of planning constraints. By integrating AI-driven models with clinical data, my work aims to streamline treatment plan generation, improving efficiency and consistency while maintaining high-quality outcomes. A key application of this approach is in online adaptive planning, where real-time adjustments are required to account for daily anatomical changes, ensuring precise dose delivery. This research lies at the intersection of radiation oncology, artificial intelligence, treatment planning optimization, and adaptive therapy, making it highly relevant to students interested in AI in healthcare and precision medicine.
- In addition to automated planning, my research explores the application of deep learning for predicting recurrence in gynecological cancers following radiotherapy. By analyzing patterns in post-treatment imaging and correlating them with clinical outcomes, we aim to develop predictive models that can identify patients at higher risk of recurrence. This approach leverages advancements in convolutional neural networks, radiomics, and clinical data integration to enhance personalized treatment strategies.
- Students can work on projects such as developing deep learning models for dose distribution prediction, creating optimization algorithms that integrate clinical constraints, and testing these methods in adaptive therapy scenarios using real-world datasets. Through hands-on experience, they will gain skills in machine learning, data analytics, medical imaging, and treatment plan evaluation. Additionally, students will have opportunities to collaborate with multidisciplinary teams, bridging technical expertise with clinical insights. These projects will equip students with cutting-edge tools to address challenges in modern radiation oncology and contribute to the development of innovative, patient-centered solutions, positioning them at the forefront of AI-driven oncology research.
Education & Training
PhD, University of British Columbia, 2020