Left ventricle segmentation using graph searching on intensity and gradient and a priori knowledge (lvGIGA) for short-axis cardiac magnetic resonance imaging.
Academic Article
Overview
abstract
PURPOSE: To develop and evaluate an automated left ventricle (LV) segmentation algorithm using Graph searching based on Intensity and Gradient information and A priori knowledge (lvGIGA). MATERIALS AND METHODS: The lvGIGA algorithm was implemented with coil sensitivity correction and polar coordinate transformation. Graph searching and expansion were applied for extracting myocardial endocardial and epicardial borders. LV blood and myocardium intensities were estimated for accurate partial volume calculation of blood volume and myocardial mass. Cardiac cine SSFP images were acquired from 38 patients. The lvGIGA algorithm was used to measure blood volume, myocardial mass, and ejection fraction, and compared with clinical manual tracing and the commercial MASS software. RESULTS: The success rate for segmenting both endocardial and epicardial borders was 95.6% slices for lvGIGA and 37.8% for MASS (excluding basal slices that required manual enclosure of ventricle blood). The lvGIGA segmentation result agreed well with manual tracing, within -2.9 +/- 4.4 mL, 2.1 +/- 2.2%, and -9.6 +/- 13.0 g, for blood volume, ejection fraction, and myocardial mass, respectively. CONCLUSION: The lvGIGA algorithm substantially improves the robustness of LV segmentation automation over the commercial MASS software, agrees well with clinical manual tracing, and may be a useful tool for clinical practice.
