UC.PT

• Path
• › UC.PT
• › English Version
• › Organizations
• › INESC Coimbra
• › R&D Projects
• › Projects
• › IMRT Beam Angle Optimization Project
• › Introduction

Introduction

In this project we will address the problem of Beam Angle Optimisation (BAO)  in Intensity Modulated Radiation Therapy (IMRT).

(Image obtained using Software CERR)

• What is IMRT?

  • Radiation therapy consists in the treatment of cancerous tissues using radiation, having as goal the destruction of cancerous cells and the preservation of healthy tissues. The treatment plan is based on the patient CT images, where the radiation oncologist delineates the target volume and organs at risk. The medical physicist and/or the dosimetrist are then responsible for performing the plan aiming to deliver the prescribed dose to the tumor while minimizing the irradiation of the surrounding healthy organs and tissues. The achievement of optimal radiotherapy treatments is done through the optimization of all possible variables that can influence the dose distribution.With IMRT, the number of degrees of freedom to be optimized is so large that computation of mathematical algorithms is mandatory to achieve valuable solutions. The selection of appropriate radiation incidence directions may be decisive for the quality of the treatment.

• Why is this problem important?

  • In clinical practice, most of the time, beam directions continue to be manually selected or are optimized using gradient methods that are prone to converge to the nearest local minimum starting with the initial beam incidence directions.In this project we will work on computer-aided inverse planning applied to radiation therapy treatments focusing on the resolution of the beam angle optimization (BAO) problem. We aim at improving the quality of the treatments which may increase treatment outcome and quality of life while reducing treatment planning time.

• What do we propose to do?

  • We aim to develop and test new approaches for the resolution of the BAO problem, using both derivative-free optimization methods and evolutionary algorithms (EA) to tackle this highly non-convex optimization problem. See the full description for a more detailed description.

• Who are we?

  • This is an interdisciplinary project, with researchers having a solid background on computer science, optimization, medical physics and clinical practice. From the computer science and optimization side, the team has expertise in creating algorithms in multidisciplinary optimization including derivative-free algorithms and evolutionary computation. From the medical physics side, the team counts with specialized researchers, with a sound experience in treatment planning both from the research and from the clinical practice points of view. The synergies that will be possible to exploit set the grounds for a future quality research and contribute to the innovative character of our proposed work.

The development of this project will have academic impact by the development and application of derivative-free and EA to challenging real world problems. However, since this project is to be developed in straight collaboration with the Portuguese Institute of Oncology of Coimbra (IPOC), our main goal is to reflect the academic empirical achievements on the improvement of patient’s treatments.