Incorporation of Preprocedural PET into CT-Guided Radiofrequency Ablation of Hepatic Metastases: a Nonrigid Image Registration Validation Study

Abstract

This study evaluates the accuracy of augmenting initial intraprocedural computed tomography (CT) during radiofrequency ablation (RFA) of hepatic metastases with preprocedural positron emission tomography (PET) through a hardware-accelerated implementation of an automatic nonrigid PET-CT registration algorithm. The feasibility of augmenting intraprocedural CT with preprocedural PET to improve localization of CT-invisible but PET-positive tumors with images from actual RFA was explored. Preprocedural PET and intraprocedural CT images from 18 cases of hepatic RFA were included. All PET images in the study originated from a hybrid PET/CT scanner, and PET-CT registration was performed in two ways: (1) direct registration of preprocedural PET with intraprocedural CT and (2) indirect registration of preprocedural CT (i.e., the CT of hybrid PET/CT scan) with intraprocedural CT. A hardware-accelerated registration took approximately 2 min. Calculated registration errors were 7.0 and 8.4 mm for the direct and indirect methods, respectively. Overall, the direct registration was found to be statistically not distinct from that performed by a group of clinical experts. The accuracy, execution speed, and compactness of our implementation of nonrigid image registration suggest that existing PET can be overlaid on intraprocedural CT, promising a novel, technically feasible, and clinically viable approach for PET augmentation of CT guidance of RFA.

Software-based PET-MR image coregistration: combined PET-MRI for the rest of us!

“…Because experts’ views differ slightly, it is reasonable to contrast any disagreement in landmark correspondence between the algorithm and expert results with the interexpert variability as an additional accuracy metric and to judge whether the algorithm’s performance is comparable to that of a typical expert [12, 16]. To this end, the 4 PET points per test landmark (1 from the algorithm and the rest provided by 3 experts) were allocated to 4 separate groups of 3 each, as illustrated in Fig.…”

“…Comparable median values obtained for all 4 groups is an indication of good agreement between the algorithm-determined and the 3 expert-determined point correspondences. As in a similar registration validation study [16], a sign test, suitable for studies with small sample size, was performed to assess if the median distance for each group of groups 1–3 was equal to the median distance for the reference group. For this test, a p -value <0.05 was used as the criterion to reject the null hypothesis and to indicate a statistically significant difference.…”

Accuracy assessment of an automatic image-based PET/CT registration for ultrasound-guided biopsies and ablations

“…To compensate for different respiratory changes or physiological discrepancies between the multimodal images, non-rigid deformation methods using parameterized cubic B-splines [3] or with a nonlinear automated warping method using thin-plate splines [4] were recently proposed for this application, thus improving the quality of PET/CT alignment. Lei et al assessed the feasibility of fusing PET with intra-procedural CTs for hepatic RF ablation using a non-rigid registration between PET and unenhanced CT [5]. In the work presented by Shekhar et al [6], normalized mutual information-based was used with a 3D elastic image registration technique to align whole-body PET and CT images acquired on stand-alone scanners.…”

Real-time tracking of liver motion and deformation using a flexible needle

“…An emerging trend of augmenting intraprocedural CT with preprocedural images (e.g., contrast CT, contrast magnetic resonance [MR] imaging, and positron emission tomography [PET]) improves intraprocedural visualization and targeting of the tumor [7–11]; however, the additional computation needed for 3D image registration (often nonrigid) further delays the availability of images for intraprocedural image guidance. Registration of intraprocedural 3D CT with preprocedural contrast-enhanced MR images of the liver has been reported to take 28–52 min [12,13]) because of the computationally intensive task of modeling and recovering complex nonrigid deformation of the liver.…”

“…Registration of intraprocedural 3D CT with preprocedural contrast-enhanced MR images of the liver has been reported to take 28–52 min [12,13]) because of the computationally intensive task of modeling and recovering complex nonrigid deformation of the liver. Fast 3D nonrigid medical image registration implementations [14–16], including our team’s hardware-accelerated solution [7], which take 1–4 min, depending on image size, similarity metric, deformation model, and optimization algorithm, shorten long computation times, but are not instantaneous. Thus, the latency problem persists.…”