Genetic Algorithms in Biomedical Image Processing

We are combining statistical machine learning methods with genetic algorithms to learn from training examples to detect features in biomedical images. To date, we have focusing on detecting the prostate in computed tomography images. To accomplish this, it is necessary for our system to learn about and combine information about shape, texture, and spatial relationships between the prostate and other anatomical landmarks.

Publications from this Project:

1. Ghosh, P. and Mitchell, M. (2006). Medical image segmentation with genetic algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2006, pp. 1171-1178.
2. Ghosh, P. and Mitchell, M. (2008). Prostate segmentation on pelvic CT images using a genetic algorithm. In Proceedings of the International Society for Optical Engineering (SPIE), Conference on Medical Imaging, February, 2008. SPIE Press.