Authors: Yasuyuki Ueda Junji Morishita Shohei Kudomi Katsuhiko Ueda
Publish Date: 2015/09/04
Volume: 54, Issue: 9, Pages: 1341-1351
Abstract
The purpose of our study is to investigate the feasibility of automated patient verification using multiplanar reconstruction MPR images generated from threedimensional magnetic resonance MR imaging of the brain Several anatomyrelated MPR images generated from threedimensional fast scout scan of each MR examination were used as biological fingerprint images in this study The database of this study consisted of 730 temporal pairs of MR examination of the brain We calculated the correlation value between current and prior biological fingerprint images of the same patient and also all combinations of two images for different patients to evaluate the effectiveness of our method for patient verification The best performance of our system were as follows a halftotal error rate of 159 with a false acceptance rate of 0023 and a false rejection rate of 315 an equal error rate of 137 and a rankone identification rate of 986 Our method makes it possible to verify the identity of the patient using only some existing medical images without the addition of incidental equipment Also our method will contribute to patient misidentification error management caused by human errors
Keywords: