Fa. Cosio et Bl. Davies, Automated prostate recognition: a key process for clinically effective robotic prostatectomy, MED BIO E C, 37(2), 1999, pp. 236-243
Clinical trials of PROBOT, a robotic system for prostate surgery, have show
n that robotic surgery of soft tissue can be successful. Monitoring of the
progress of the resection has shown to be a necessary feature of an effecti
ve robotic system for prostate surgery. It should provide the surgeon with
a reliable method of assessing the cavity during resection. An automatic sy
stem for intraoperative monitoring of the progress of the resection during
robotic prostatectomy consists of two subsystems: real-time intraoperative
imaging of the prostate and automatic identification of the contour of the
gland on each image. The development of a fully automatic scheme for prosta
te recognition on transurethral ultrasound scans is reported. A genetic alg
orithm has been developed to automatically adjust a model of the prostate b
oundary until an optimum fit to the prostate in a given image is obtained.
An analysis of ifs performance on 22 different ultrasound images showed an
average error of 6.21 mm. Use of a genetic algorithm and a constrained pros
tate model have shown to be a robust way to automatically identify the pros
tate in ultrasound images. The scheme is able to produce approximate prosta
te boundaries, without any human intervention, on ultrasound scans of varyi
ng quality. In addition to soft tissue robotic surgery, the generic algorit
hm technique is also applicable to a wide range of computer assisted surgic
al techniques.