Translator Disclaimer
29 April 2005 Semiautomatic segmentation of the heart from CT images based on intensity and morphological features
Author Affiliations +
The incidence of certain types of cardiac arrhythmias is increasing. Effective, minimally invasive treatment has remained elusive. Pharmacologic treatment has been limited by drug intolerance and recurrence of disease. Catheter based ablation has been moderately successful in treating certain types of cardiac arrhythmias, including typical atrial flutter and fibrillation, but there remains a relatively high rate of recurrence. Additional side effects associated with cardiac ablation procedures include stroke, perivascular lung damage, and skin burns caused by x-ray fluoroscopy. Access to patient specific 3-D cardiac images has potential to significantly improve the process of cardiac ablation by providing the physician with a volume visualization of the heart. This would facilitate more effective guidance of the catheter, increase the accuracy of the ablative process, and eliminate or minimize the damage to surrounding tissue. In this study, a semiautomatic method for faithful cardiac segmentation was investigated using Analyze - a comprehensive processing software package developed at the Biomedical Imaging Resource, Mayo Clinic. This method included use of interactive segmentation based on math morphology and separation of the chambers based on morphological connections. The external surfaces of the hearts were readily segmented, while accurate separation of individual chambers was a challenge. Nonetheless, a skilled operator could manage the task in a few minutes. Useful improvements suggested in this paper would give this method a promising future.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Abena B. Redwood, Jon J. Camp, and Richard A. Robb "Semiautomatic segmentation of the heart from CT images based on intensity and morphological features", Proc. SPIE 5747, Medical Imaging 2005: Image Processing, (29 April 2005);

Back to Top