Respiratory Motion Compensation Using Diaphragm Tracking for Cone-Beam C-Arm CT: A Simulation and a Phantom Study

Abstract

Long acquisition times lead to image artifacts in thoracic C-arm CT. Motion blur caused by respiratory motion leads to decreased image quality in many clinical applications. We introduce an image-based method to estimate and compensate respiratory motion in C-arm CT based on diaphragm motion. In order to estimate respiratory motion, we track the contour of the diaphragm in the projection image sequence. Using a motion corrected triangulation approach on the diaphragm vertex, we are able to estimate a motion signal. The estimated motion signal is used to compensate for respiratory motion in the target region, for example, heart or lungs. First, we evaluated our approach in a simulation study using XCAT. As ground truth data was available, a quantitative evaluation was performed. We observed an improvement of about 14% using the structural similarity index. In a real phantom study, using the artiCHEST phantom, we investigated the visibility of bronchial tubes in a porcine lung. Compared to an uncompensated scan, the visibility of bronchial structures is improved drastically. Preliminary results indicate that this kind of motion compensation can deliver a first step in reconstruction image quality improvement. Compared to ground truth data, image quality is still considerably reduced.

Figure 1

Diaphragm tracking on simulated XCAT data. Images (a)–(d) show projection images acquired from different angles.

Figure 2

Comparison of the extracted diaphragm motion signal and the actual respiration signal of the simulated XCAT phantom. The amplitude of the signal cannot be estimated accurately, as the projections of the diaphragm top do not coincide with the 2D contour.

Figure 3

Structural similarity index of the heart volume for xy- and xz-slices. The uncompensated reconstruction shows better results in the beginning and the end, as the heart is only of small size in these slices.

Figure 4

Comparison of xy-slice 70 of compensated and uncompensated volumes (cf. Figure 3(a)). Simulated high-contrast heart lesions further illustrate the improved image quality. Line profiles were taken at the position of the red lines.

Figure 5

Comparison of xz-slice 60 of compensated and uncompensated volumes (cf. Figure 3(b)). Line profiles were taken at the position of the red lines.

Figure 6

Line profiles of xy-slice 70 of compensated and uncompensated volumes (cf. Figure 3(a)). Line profiles were taken at the position of the red lines in Figure 4.

Figure 7

Line profiles of xz-slice 60 of compensated and uncompensated volumes (cf. Figure 3(b)). Line profiles were taken at the position of the red lines in Figure 5.

Figure 8

Illustration of the artiCHEST lung phantom. The box contains a porcine lung mounted on an artificial diaphragm and is filled with water.

Figure 9

Zoomed in view of the diaphragm and the tracked function in a projection image.

Figure 10

A slice of a static reconstruction of the artiCHEST phantom. At the bottom there is a porcine heart; the white circle is a plastic tube representing the spine. The red bounding box shows the region of interest for further evaluation.

Figure 11

Detailed view of compensated and not compensated slices of a 20s scan with 2 respiration cycles of only 50% respiratory amplitude.

Figure 12

Detailed view of compensated and not compensated slices of a 20s scan with 2 full respiration cycles.

Algorithm 1

Motion compensated reconstruction. Respiratory motion is compensated in lines (9)–(11).