A Retrospective Analysis of Prostate Cone Beam Computed Tomography (CBCT) Image Registration: A Tale of Two...

To determine the feasibility of the gray-value registration technique as a correction method for prostate image-guided radiotherapy.

The current practice at this institution involves a two-step process beginning with an automated bone registration, followed by a manual therapist manipulated registration.

This process is susceptible to subjective judgement and inter-observer variability, which introduces inconsistencies in image registrations and subsequent treatment delivery. Variation in the time required to complete image registrations may increase the chance for prostate intra-fractional movement, which may increase treatment inaccuracies.

A retrospective image review was completed for 20 patients. Translational shifts and duration data for therapist registrations were retrieved for 15 scans for each patient, totaling 300 scans. Gray-value registrations were completed on the same 300 scans to recalculate shift values and the time to complete this technique was recorded. The analysis of variance test was used to analyze the extent of variance between the two registration techniques.

No difference between the two registration techniques in the lateral (right-left) direction (P = .364) and superoinferior directions (P = .455) were found. Gray-value registrations took significantly less time to complete and were more consistent than the two-step therapist registrations (P < .001). A statistically significant difference in z shifts exists (P = .003) between the two techniques.

Gray-value registration can minimize and standardize the image registration durations and produce x and y shifts similar to those produced by therapists. Lacking the ability to preferentially match to the prostate-rectum interface, therapists still need to perform a simple inspection in the z (anteroposterior) plane to ensure an adequate registration to the interface.