Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance
详细信息 查看全文
- 作者：Tuan Anh Ngo1 ; aAuthor Vitae ; Zhi Lu1 ; bAuthor Vitae ; Gustavo Carneiro ; c ; gustavo.carneiro@adelaide.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Deep learning ; Level set method ; Segmentation of the left ventricle of the heart ; Cardiac cine magnetic resonance
- 刊名：Medical Image Analysis
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：35
- 期：Complete
- 页码：159-171
- 全文大小：2175 K
文摘
- •
Using cardiac cine magnetic resonance, we introduce a new structured output model for the region of interest (ROI) detection of the left ventricle of the heart using a deep belief network (DBN).
- •
We also propose a new structured output model for the delineation of the endocardial and epicardial borders using another DBN.
- •
Finally, we extend a common level set method that takes: a) the ROI detection above to initialise the optimisation process, and b) the delineation of the endocardial and epicardial borders above to constrain the level set evolution.