2011 年 49 巻 1 号 p. 25-33
Recently, there are various studies to recognize and trace the shape of the left ventricle in the echogram. Especially speckle-tracking method is very useful to evaluate heart motion. However, most of these techniques require initial settings to indicate initial region or point of interest of the examiner. Additionally, real-time recognition of left ventricle has not been considered by the conventional researches. In this study, we propose an automatic recognition algorithm of left ventricular cavity using successive echocardiograms, which is not required any initial settings by examiner. This system plots a point in a left ventricular cavity, and then depicts the cavity automatically. We have applied this algorithm to 10 normal hearts and 60 diseased hearts. As the result, the proposed method correctly recognized 82% of left ventricular cavities throughout all of the recorded frames, which was judged by professional sonographers. Furthermore, this software was applied to real-time visualization of the cavity through analog video signal, where automatic calculation of ejection fraction was agreed with the results of conventional method by a sonographer.