Minimizing clip artifacts in multi CT angiography of clipped patients

Abstract

Purpose: To optimize the multi CTA (MSCTA) protocol, the influence of pitch, kilovoltage peak (kVp), reconstruction algorithm, type, and orientation of the clip on clip-induced artifacts was investigated in a phantom study. Also, the influence of kVp, concentration of contrast material, and clip orientation in clipped patients was studied.

Methods: A phantom containing a clip was scanned with varying parameters. Artifact was quantified with 3D volumetry. Artifact volumes were compared for the different parameters. In addition, the number of artifact streaks was presented as a function of the pitch. Five clipped patients were scanned with 90 kVp and 120 kVp and 5 with 120 kVp and 140 kVp. The artifact area was compared. The visualization at the clip site was evaluated for different clip orientations in 50 patients, and for 140 kVp with 370 mg iodine/mL contrast (I/mL) compared with 120 kVp/300 mg I/mL in 7 patients.

Results: Up to a pitch of 0.6, there was hardly an increase in artifact. Higher kVp and linear interpolation resulted in fewer artifacts. Alloy clips containing cobalt produced more artifact than did titanium clips. Clips positioned perpendicular to the scan plane led to significantly less artifact. In patients with clips, scanning with 140 kVp/370 mgI/mL led to a decrease of artifact area and a better visualization of the clip site. The visualization at the clip site was also better for clips perpendicular to the scan plane.

Conclusions: If clip artifacts are to be minimized, we suggest scanning with a pitch of 0.6, by using 140 kVp and 370 mgI/mL contrast.

Fig 1.

Phantom. A cylindrical PMMA phantom (A) with a cylinder containing a clip (B).

Fig 2.

Metal artifact of Cobalt clips scanned at pitch 1 positioned in the scanplance (A–C) and perpendicular to the scan plane (D). The metal artifact consists of a black-and-white component. The aspect of the artifact changes with decreasing window width: widest width (A); window width as used in clinical practice (B); and binary picture (C). The artifact volume largely depends on the position of the clip to the scan plane, with much less artifact for a clip perpendicular to the scan plane (D) compared to a clip in the scan plane (B).

Fig 3.

Artifact quantification in patients: quantification of the black-and-white component of the artifact in patients in CTA source images. A, Clip artifact in clinical window setting, with background of 32 HU and an SD of 21. B, Area of the black component of the artifact enclosing all pixels with HU < 31 (±3 SD). C, Area of the white component of the artifact enclosing all pixels with HU > 95 (±3 SD).

Fig 4.

Artifact volume of the Cobalt containing alloly and titanium clip at increasing pitch. Volume of clip artifact at increasing pitch for cobalt-containing alloy (upper, black lines) and titanium (lower, white lines) clip. Both clips were scanned in the high mode (superscript H, open symbols) up to pitch 1, and standard mode (superscript S, closed symbols) up to pitch 1.5 at 90 (triangles), 120 (squares), and 140 (circles) kVp.

Fig 5.

Number of white streaks for the cobalt-containing alloy (upper, black lines) and titanium clips (lower, white lines) scanned in high mode (H) (open symbols, up to P 1) and standard mode (S) (closed symbols, up to P 1.5).

Fig 6.

Aspect of a cobalt clip artifact, positioned in the scanplane, at increasing pitch. The numbers of white streaks increase with increasing pitch.