Anatomical medial surfaces with efficient resolution of branches singularities

详细信息    查看全文

• 作者：Debora Gil¹ ; ^a ; ^{debora@cvc.uab.es" class="auth_mail" title="E-mail the corresponding author} ; Sergio Vera^b ; Agné ; s Borrà ; s^a ; ^{agnesba@cvc.uab.es" class="auth_mail" title="E-mail the corresponding author} ; Albert Andaluz^a ; Miguel A. Gonzá ; lez Ballester^c ; ^d
• 关键词：Medial representations ; Shape recognition ; Medial branching stability ; Singular points
• 刊名：Medical Image Analysis
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：35
• 期：Complete
• 页码：390-402
• 全文大小：4511 K

文摘

Medial surfaces are powerful tools for shape description, but their use has been limited due to the sensibility of existing methods to branching artifacts. Medial branching artifacts are associated to perturbations of the object boundary rather than to geometric features. Such instability is a main obstacle for a confident application in shape recognition and description. Medial branches correspond to singularities of the medial surface and, thus, they are problematic for existing morphological and energy-based algorithms. In this paper, we use algebraic geometry concepts in an energy-based approach to compute a medial surface presenting a stable branching topology. We also present an efficient GPU-CPU implementation using standard image processing tools. We show the method computational efficiency and quality on a custom made synthetic database. Finally, we present some results on a medical imaging application for localization of abdominal pathologies.