An integer linear programming model is proposed as a framework for optimizing seed placement and dose distribution in brachytherapy treatment planning. The basic model involves using 0/1 indicator variables to describe the placement or non-placement of seeds in a prespecified three-dimensional grid of potential locations. The dose delivered to each point in a discretized representation of the diseased organ and neighbouring healthy tissue can then be modelled as a linear combination of the indicator variables. A system of linear constraints is imposed to attempt to keep the dose level at each point to within specified target bounds. Since it is physically impossible to satisfy all constraints simultaneously, each constraint uses a variable to either record when the target dose level is achieved, or to record the deviation from the desired level. These additional variables are embedded into an objective function to be optimized. Variations on this model are discussed and two computational approaches--a branch-and-bound algorithm and a genetic algorithm--for finding 'optimal' seed placements are described. Results of computational experiments on a collection of prostate cancer cases are reported. The results indicate that both optimization algorithms are capable of producing good solutions within 5 to 15 min, and that small variations in model parameters can have a measurable effect on the dose distribution of the resulting plans.
A linear-programming model is proposed for deriving discriminant rules that allow allocation of entities to a reserved-judgment region. The size of the reserved-judgment region, which can be controlled by varying parameters within the model, dictates the level of aggressiveness (cautiousness) of allocating (misallocating) entities to groups. Results of simulation experiments for various configurations of normal and contaminated normal three-group populations are reported for a variety of parameter selections. Results of cross-validation experiments using real data sets are also reported. Both the simulation and cross-validation experiments include comparison with other discriminant analysis techniques. The results demonstrate that the proposed model is useful for deriving discriminant rules that reduce the chances of misclassification, while maintaining a reasonable level of correct classification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.