A framework for the merging of pre-existing and correspondenceless 3D statistical shape models

被引:9
|
作者
Pereanez, Marco [1 ]
Lekadir, Karim [1 ]
Butakoff, Constantine [2 ]
Hoogendoorn, Corne [1 ]
Frangi, Alejandro F. [3 ]
机构
[1] Univ Pompeu Fabra, Ctr Computat Imaging & Simulat Technol Biomed CIS, Barcelona, Spain
[2] Univ Pompeu Fabra, Sensing Physiol & Biomed PhySense, Barcelona, Spain
[3] Univ Sheffield, CISTIB, Sheffield, S Yorkshire, England
关键词
Statistical shape model; Point distribution model; Eigenspace fusion; Point correspondence; Image segmentation; PDM CONSTRUCTION; TRAINING SET; CT IMAGES; ARTIFICIAL ENLARGEMENT; DEFORMABLE MODELS; SEGMENTATION; HEART; APPEARANCE; GENERATION; FEATURES;
D O I
10.1016/j.media.2014.05.009
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The construction of statistical shape models (SSMs) that are rich, i.e., that represent well the natural and complex variability of anatomical structures, is an important research topic in medical imaging. To this end, existing works have addressed the limited availability of training data by decomposing the shape variability hierarchically or by combining statistical and synthetic models built using artificially created modes of variation. In this paper, we present instead a method that merges multiple statistical models of 3D shapes into a single integrated model, thus effectively encoding extra variability that is anatomically meaningful, without the need for the original or new real datasets. The proposed framework has great flexibility due to its ability to merge multiple statistical models with unknown point correspondences. The approach is beneficial in order to re-use and complement pre-existing SSMs when the original raw data cannot be exchanged due to ethical, legal, or practical reasons. To this end, this paper describes two main stages, i.e., (1) statistical model normalization and (2) statistical model integration. The normalization algorithm uses surface-based registration to bring the input models into a common shape parameterization with point correspondence established across eigenspaces. This allows the model fusion algorithm to be applied in a coherent manner across models, with the aim to obtain a single unified statistical model of shape with improved generalization ability. The framework is validated with statistical models of the left and right cardiac ventricles, the L1 vertebra, and the caudate nucleus, constructed at distinct research centers based on different imaging modalities (CT and MRI) and point correspondences. The results demonstrate that the model integration is statistically and anatomically meaningful, with potential value for merging pre-existing multi-modality statistical models of 3D shapes. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码:1044 / 1058
页数:15
相关论文
共 50 条
  • [1] Endoscopic skull base training using 3D printed models with pre-existing pathology
    Narayanan, Vairavan
    Narayanan, Prepageran
    Rajagopalan, Raman
    Karuppiah, Ravindran
    Rahman, Zainal Ariff Abdul
    Wormald, Peter-John
    Van Hasselt, Charles Andrew
    Waran, Vicknes
    EUROPEAN ARCHIVES OF OTO-RHINO-LARYNGOLOGY, 2015, 272 (03) : 753 - 757
  • [2] Endoscopic skull base training using 3D printed models with pre-existing pathology
    Vairavan Narayanan
    Prepageran Narayanan
    Raman Rajagopalan
    Ravindran Karuppiah
    Zainal Ariff Abdul Rahman
    Peter-John Wormald
    Charles Andrew Van Hasselt
    Vicknes Waran
    European Archives of Oto-Rhino-Laryngology, 2015, 272 : 753 - 757
  • [3] Fusing Correspondenceless 3D Point Distribution Models
    Pereanez, Marco
    Lekadir, Karim
    Butakoff, Constantine
    Hoogendoorn, Corne
    Frangi, Alejandro
    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION (MICCAI 2013), PT I, 2013, 8149 : 251 - 258
  • [4] Reparameterising 3D Statistical Shape Models
    Wang, Haoyang
    Zafeiriou, Stefanos
    2019 14TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2019), 2019, : 477 - 481
  • [5] Influence of pre-existing salt diapirs on 3D folding patterns
    Fernandez, Naiara
    Kaus, Boris J. P.
    TECTONOPHYSICS, 2014, 637 : 354 - 369
  • [6] Strength test of 3D printed artificial rock mass with pre-existing fracture
    Wang, Youyu
    Wang, Li
    Meng, Fanfei
    Chen, Kang
    UNDERGROUND SPACE, 2021, 6 (05) : 492 - 505
  • [7] Visualization of the variability of 3D statistical shape models by animation
    Lamecker, H
    Seebass, M
    Lange, T
    Hege, HC
    Deuflhard, P
    MEDICINE MEETS VIRTUAL REALITY 12: BUILDING A BETTER YOU: THE NEXT TOOLS FOR MEDICAL EDUCATION, DIAGNOSIS , AND CARE, 2004, 98 : 190 - 196
  • [8] Building 3D Statistical Shape Models of Horticultural Products
    Femke Danckaers
    Toon Huysmans
    Mattias Van Dael
    Pieter Verboven
    Bart Nicolaï
    Jan Sijbers
    Food and Bioprocess Technology, 2017, 10 : 2100 - 2112
  • [9] Building 3D Statistical Shape Models of Horticultural Products
    Danckaers, Femke
    Huysmans, Toon
    Van Dael, Mattias
    Verboven, Pieter
    Nicolai, Bart
    Sijbers, Jan
    FOOD AND BIOPROCESS TECHNOLOGY, 2017, 10 (11) : 2100 - 2112
  • [10] 3D statistical shape models of patella for sex classification
    Mahfouz, Mohamed
    Badawi, Ahmed
    Merkl, Brandon
    Fatah, Emam E. Abdel
    Pritchard, Emily
    Kesler, Katherine
    Moore, Megan
    Jantz, Richard
    2006 28TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-15, 2006, : 4981 - +