Quantitative Assessment of Heart Function: A Hybrid Mechanism for Left Ventricle Segmentation from Cine MRI Sequences

详细信息    查看全文

• 关键词：Gradient vector flow ; Left ventricle ; Segmentation ; Cine MRI sequences
• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10142
• 期：1
• 页码：169-179
• 丛书名：Artificial Life and Computational Intelligence
• ISBN：978-3-319-51691-2
• 卷排序：10142

文摘

In this paper, we propose a hybrid approach for segmenting the left ventricle out of magnetic resonance sequences and apply results of the segmentation for heart quantification. The hybrid approach uses a thresholding-based region growing algorithm coupled with gradient vector flow (GVF). Results of the segmentation steps were used for the quantification process and yielded values of 175.4 ± 51.52 (ml), 66 ± 38.97 (ml), and 61.60 ± 12.79 (%) for end diastolic volume (EDV), end systolic volume (ESV), and ejection fraction (EF), respectively.