Cognitive planning based on Genetic Algorithm in computer-assisted interventions

Minimally invasive and computer-assisted interventions and surgeries are getting widely accepted by patients and clinicians due to improved clinical outcomes. The new paradigm involves more advanced medical instruments, among which Radiofrequency Ablation (RFA) is one type of intervention to kill tumor tissues using a needle-like electrode. In this paper, a computational optimization algorithm to plan optimal ablation delivery is proposed, and potentially allows cognitive planning in surgical robotics. Genetic Algorithm (GA) was used as it can be designed to consider the multi-objective nature of a tumor ablation planning system. A mathematical protocol was also proposed to provide a reference for the viability of the algorithm. The feasibility of GA was tested on simulated and real data; and was found to be able to generate acceptable solution set for the tumor ablation planning problems.