Medical Decision-Making
Continuous Dose Delivery for Stereotactic Radiation Therapy
Stereotactic radiation therapy is conventionally delivered in a step-and-shoot manner, i.e., a shot is delivered when the target volume is stationary, and no radiation is delivered when the patient position is moved. We explore the possibility of delivering radiation therapy as the patient is moved to treat various locations of the tumor. A continuous dose delivery can result in reduced treatment time and increased homogeneity while sparing the surrounding healthy organs.
In radiation therapy with continuous dose delivery for Gamma Knife® Perfexion™, the dose is delivered while the radiation machine is in movement, as oppose to the conventional step-and-shoot approach which requires the unit to stop before any radiation is delivered. Continuous delivery can increase dose homogeneity and decrease treatment time. To design inverse plans, we first find a path inside the tumor volume, along which the radiation is delivered, and then find the beam durations and shapes using a mixed-integer programming optimization (MIP) model. The MIP model considers various machine-constraints as well as clinical guidelines and constraints.
Radiation Therapy Treatment Planning for Brain Cancer
Radiation therapy treatment planning is a complex and high-dimensional problem, and yet, it is often solved manually by clinicians. In these projects, we explore various models that use optimization and automated methods to find a good treatment plan that is approved by the oncologist and meets clinical criteria.
Radiation therapy is frequently used in diagnosing patients with cancer. Currently, the planning of such treatments is typically done manually which is time-consuming and prone to human error. The new advancements in computational powers and treating units now allow for designing treatment plans automatically.
To design a high-quality treatment, we select the beams sizes, positions, and shapes using optimization models and approximation algorithms. The optimization models are designed to deliver an appropriate amount of dose to the tumor volume while simultaneously avoiding sensitive healthy tissues. In this project, we work on finding the best beam positions for the radiation focal points for Gamma Knife® Perfexion™, using quadratic programming and algorithms such as grassfire and sphere-packing.
Machine Learning in The Prediction of Children’s Diseases
Early risk assessment of Autism can be studied based on prenatal factors, perinatal factors, maternal factors, and metal exposures to the mother. This is accomplished through machine learning approaches such as multiplayer perceptron and Bayesian kernel machine regression. Practical meanings of the findings can then be explored with medical experts. The methods adopted in this research can easily be generalized and transferred to explore other topics.
