Registration of physical space to laparoscopic image space for use in minimally invasive hepatic surgery

• Published in: 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002 p. 12 pp.
• Main Authors: Stefansic, J.D., Herline, A.J., Shyr, Y., Chapman, W.C., Fitzpatrick, J.M., Dawant, B.M., Galloway, R.L.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2002
• Subjects: Filters; Image analysis; Image registration; Imaging phantoms; Laparoscopes; Liver neoplasms; Merging; Minimally invasive surgery; Plastics; Robust control
• ISBN: 0780375076; 9780780375079
• DOI: 10.1109/SSBI.2002.1233999

While laparoscopes are used for numerous minimally invasive (MI) procedures, MI liver resection and ablative surgery is infrequently performed. The paucity of cases is due to the restriction of the field of view by the laparoscope and the difficulty in determining tumor location and margins under video guidance. By merging MI surgery with interactive, image-guided surgery (ITGS), we hope to overcome localization difficulties present in laparoscopic liver procedures. One key component of any DGS system is the development of accurate registration techniques to map image space to physical or patient space. This manuscript focuses on the accuracy and analysis of the direct linear transformation (DLT) method to register physical space with laparoscopic image space on both distorted and distortion-corrected video images. Experiments were conducted on a liver-sized plastic phantom affixed with 20 markers at various depths. After localizing the points in both physical and laparoscopic image space, registration accuracy was assessed for different combinations and numbers of control points (n) to determine the quantity necessary to develop a robust registration matrix. For n = 11, average target registration error (TRE) was 0.70 /spl plusmn/ 0.20 mm. We also studied the effects of distortion correction on registration accuracy. For the particular distortion correction method and laparoscope used in our experiments, there was no statistical significance between physical to image registration error for distorted and corrected images. In cases where a minimum number of control points (n = 6) are acquired, the DLT is often not stable and the mathematical process can lead to high TRE values. Mathematical filters developed through the analysis of the DLT were used to prospectively eliminate outlier cases where the TRE was high. For n = 6, prefilter average TRE was 17.4 /spl plusmn/ 153 mm for all trials; when the filters were applied, average TRE decreased to 1.64 /spl plusmn/ 1.10 mm for the remaining trials.