3D coronary artery elastic registration based on differential invariant signatures

ABSTRACT

In this paper, a point-set similarity model (PSM) is introduced, which provides a new elastic point set registration frame by using similarity invariant signature curves. According to the potential correspondences obtained by PSM, the similarity transformations between the point sets could be estimated. Experiments on synthetic data and real data of coronary artery show that our method offers certain advantages comparing with typical methods.

KEYWORDS:

• Registration
• similarity transformation
• differential invariant
• signature curve
• segmentation matching

Disclosure statement

No potential conflict of interest was reported by the author.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [No. 61773110], and the National Key Research and Development Program of China [No. 2017YFC1307600].

Notes on contributors

Mengxiao Wang

M.W. proposed the conception of this research and drafted this article. M.W. focused on the collection, analysis and interpretation of data. And M.W. revised the whole content of this manuscript.