Technologies

At UC San Diego, we have developed a major advancein knowledge-based treatment planning: full3Ddosedistribution prediction . Similar to existing art1our method relies on learning from a plurality of previously treatedplans, but our method moves far beyondcurrent technology to synthesize past experience into voxel-by-voxel predictions for expected dose distributions for newpatients. Our currentembodiment already meets or exceedsthe accuracy of existing technology in DVH prediction, with the invaluable addition of identifying (a) precisely where the dose is expectedto be depositedin the patient and (b) the degreeof confidence in that voxel-by-voxel prediction.

1SeeinparticularUS20120310615(onwhichDr.KevinMoorewastheleadinventor)andUS20120014507.

A painting is not the amountof blue, yellow,and red paint on a canvas; it is their arrangement that makes it art.

The advent of knowledge-based planning(KBP) represents a critical step forward in clinical radiotherapy, comfortably mentioned in the company of the other major advances in treatment planning(2Dàà3D-conformalààIMRT/RapidArcààKBP). While incredibly powerful, current knowledge-based methods result in dose-volume histogram(DVH) predictions that are ultimately limited by the inherent loss in spatial information of a DVH. In current incarnations of KBP (e.g.Varian’s RapidPlanTM), these predictions must be converted into DVH-based optimization parametersto enact automated planning, and when treatment planDVHsdiffer from their knowledge-based DVH predictions it requires significant expertise to discern the origin of the deviation. Troublingly, the investigation and resolution of these discrepancies necessarily falls into the hands of the same human treatment plannersthat knowledge-based planningpurports to outperform.