With leave-one-out tests, an average registration error of 2.0 mm was reported by Sadowsky et al. [28] but no information about computation time is described. This algorithm was recently accelerated with a GPU-
The algorithms ranked first and second in the Friedman test and SNE-SR ranking, achieving scores of 99.2877 (DQSMODE) and 93.0463 (QSMODE) out of 100, with statistically significant p-values in all Wilcoxon signed rank tests across 50 path-planning problems. Validation of QSMODE in practical ...
i.e. whether the predicted risks correspond to observed probabilities. In medical applications this is important because treatment decisions often rely on the estimated risk of disease. The aim of this paper is to present generic tools