Meeting Banner
Abstract #2328

Local Refinement for Automatic Probe Detection in 3T MRI

Xinyang Liu 1 , Kemal Tuncali 1 , William M Wells III 1 , and Gary P. Zientara 1

1 Radiology, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, United States

The purpose of this study is to develop an automatic approach to detect multiple 3D probes in 3T abdominal HASTE images obtained during MRI-guided cryoablation. The detected probes can be used to guide automatic iceball segmentation during the freeze cycles of the procedure. We introduced a novel template to model the probe artifact, and an extra local refinement process to improve accuracy of the detection. Retrospective experiments based on 13 MRI-guided cryoablation cases show that our automatic probe detection method with local refinement is accurate and robust, compared with results determined manually, and is feasible for clinical use.

This abstract and the presentation materials are available to members only; a login is required.

Join Here