Using Deformable Image Registration for Adaptive Prostate Cancer Treatment

A study aimed to assess and compare the capabilities of two commercially available deformable image registration algorithms—Raystation 9A (A1) and Velocity AI (A2)—for possible use in adaptive prostate radiotherapy based on computed tomography (CT) images to cone-beam CT (CBCT) images. The results were published in Zeitschrift für medizinische Physik.

In this study, 10 patients treated for localized prostate cancer were retrospectively selected and analyzed. The propagation of rectum contours was assessed from a set of CT-CBCT pairs. Two independent observers carried out qualitative analysis using the two-level descriptive scale of either “meet” or “fail.”

The analysis showed that 83.7% of the rectum contours were scored identically (meet or fail) for both algorithms, from which 53.5% and 55.8% are failed results for A1 and A2, respectively, the investigators noted. Regarding rectum size, differences between referenced and deformation-based values were 5.5 and 5.8mm, and for the rectum wall, the prostate marker distance (WMD parameter) was 4.5 and 5.5mm for A1 and A2, respectively. The researchers added that between-group differences in prostate marker distance were statistically significant (P = 0.007).

“In both tested algorithms, neither effectiveness nor measured uncertainties in the propagation of rectum contour process in prostate patient cases were satisfactory,” the researchers concluded. “Careful selection of input images followed by case/set-based verification of every deformable registration is a substantial step to avoid inappropriate results.”