作者: Antonio Bravo , Miguel Vera , Mireille Garreau , Rubén Medina
DOI: 10.1007/978-3-642-21984-9_25
关键词: Ground truth 、 Computer vision 、 Segmentation 、 Artificial intelligence 、 Multi slice 、 Heart.chambers 、 Mathematical morphology 、 Region growing 、 Computer science 、 Hybrid approach 、 Tomography
摘要: This research is focused on segmentation of the heart ventricles from volumes Multi Slice Computerized Tomography (MSCT) image sequences. The performed in three–dimensional (3–D) space aiming at recovering topological features cavities. enhancement scheme based mathematical morphology operators and hybrid–linkage region growing technique are integrated into approach. Several clinical MSCT four dimensional (3–D + t) human used to test proposed For validating results, a comparison between shapes obtained using method ground truth manually traced by cardiologist performed. Results 3–D real data show capabilities approach for extracting ventricular cavities with necessary accuracy.