A4 Article in conference proceedings
Multi-resolution Statistical Shape Models for Multi-organ Shape Modelling (2020)
Chen, Z., Ristaniemi, T., Cong, F., & Wang, H. (2020). Multi-resolution Statistical Shape Models for Multi-organ Shape Modelling. In M. Han, S. Qin, & N. Zhang (Eds.), ISNN 2020 : Advances in Neural Networks : 17th International Symposium on Neural Networks, Proceedings (pp. 74-84). Springer. Lecture Notes in Computer Science, 12557. https://doi.org/10.1007/978-3-030-64221-1_7
JYU authors or editors
Publication details
All authors or editors: Chen, Zhonghua; Ristaniemi, Tapani; Cong, Fengyu; Wang, Hongkai
Parent publication: ISNN 2020 : Advances in Neural Networks : 17th International Symposium on Neural Networks, Proceedings
Parent publication editors: Han, Min; Qin, Sitian; Zhang, Nian
Place and date of conference: Cairo, Egypt, 4.-6.12.2020
ISBN: 978-3-030-64220-4
eISBN: 978-3-030-64221-1
Journal or series: Lecture Notes in Computer Science
ISSN: 0302-9743
eISSN: 1611-3349
Publication year: 2020
Number in series: 12557
Pages range: 74-84
Publisher: Springer
Place of Publication: Cham
Publication country: Switzerland
Publication language: English
DOI: https://doi.org/10.1007/978-3-030-64221-1_7
Publication open access: Not open
Publication channel open access:
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/93664
Abstract
Statistical shape models (SSMs) are widely used in medical image segmentation. However, traditional SSM methods suffer from the High-Dimension-Low-Sample-Size (HDLSS) problem in modelling. In this work, we extend the state-of-the-art multi-resolution SSM approach from two dimension (2D) to three dimension (3D) and from single organ to multiple organs. Then we proposed a multi-resolution multi-organ 3D SSM method that uses a downsampling-and-interpolation strategy to overcome HDLSS problem. We also use an inter-surface-point distance thresholding scheme to achieve multi-resolution modelling effect. Our method is tested on the modelling of multiple mouse abdominal organs from mouse micro-CT images in three different resolution levels, including global level, single organ level and local organ level. The minimum specificity error and generalization error of this method are less than 0.3 mm, which are close to the pixel resolution of mouse micro-CT images (0.2 mm) and better than the modelling results of traditional principal component analysis (PCA) method.
Keywords: computed tomography; internal organs; Three-dimensional imaging; statistical models
Free keywords: multi-resolution multi-organ SSM; PCA; HDLSS; mouse micro-CT image
Contributing organizations
Ministry reporting: Yes
Reporting Year: 2020
JUFO rating: 1