Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation

Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation Publisher Pubmed

Alimohamadi Gilakjan S^{1, 2} ; Hasani Bidgoli J³ ; Aghaizadeh Zorofi R³ ; Ahmadian A^{1, 2}

Show Affiliations

1. Department of Biomedical Systems & Medical Physics, Tehran University of Medical Sciences, Tehran, Iran
2. Research Center for Biomedical Technologies and Robotics, Imam Khomeini Hospital Complex, Keshavarz Blvd, Tehran, Iran
3. Control & Intelligent Processing, Center of Excellence, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran

Source: Australasian Physical and Engineering Sciences in Medicine Published:2019

Abstract

The construction of a powerful statistical shape model (SSM) requires a rich training dataset that includes the large variety of complex anatomical topologies. The lack of real data causes most SSMs unable to generalize possible unseen instances. Artificial enrichment of training data is one of the methods proposed to address this issue. In this paper, we introduce a novel technique called constrained cage-based deformation (CCBD), which has the ability to produce unlimited artificial data that promises to enrich variability within the training dataset. The proposed method is a two-step algorithm: in the first step, it moves a few handles together, and in the second step transfers the displacements of these handles to the base mesh vertices to generate a real new instance. The evaluation of statistical characteristics of the CCBD confirms that our proposed technique outperforms notable data-generating methods quantitatively, in terms of the generalization ability, and with respect to specificity. © 2019, Australasian College of Physical Scientists and Engineers in Medicine.

Style	Citing Format
MLA	Alimohamadi Gilakjan S, et al.. "Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation." Australasian Physical and Engineering Sciences in Medicine, vol. 42, no. 2, 2019, pp. 573-584.
APA	Alimohamadi Gilakjan S, Hasani Bidgoli J, Aghaizadeh Zorofi R, Ahmadian A (2019). Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation. Australasian Physical and Engineering Sciences in Medicine, 42(2), 573-584.
Chicago	Alimohamadi Gilakjan S, Hasani Bidgoli J, Aghaizadeh Zorofi R, Ahmadian A. "Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation." Australasian Physical and Engineering Sciences in Medicine 42, no. 2 (2019): 573-584.
Harvard	Alimohamadi Gilakjan S et al. (2019) 'Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation', Australasian Physical and Engineering Sciences in Medicine, 42(2), pp. 573-584.
Vancouver	Alimohamadi Gilakjan S, Hasani Bidgoli J, Aghaizadeh Zorofi R, Ahmadian A. Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation. Australasian Physical and Engineering Sciences in Medicine. 2019;42(2):573-584.
BibTex	@article{ author = {Alimohamadi Gilakjan S and Hasani Bidgoli J and Aghaizadeh Zorofi R and Ahmadian A}, title = {Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation}, journal = {Australasian Physical and Engineering Sciences in Medicine}, volume = {42}, number = {2}, pages = {573-584}, year = {2019} }
RIS	TY - JOUR AU - Alimohamadi Gilakjan S AU - Hasani Bidgoli J AU - Aghaizadeh Zorofi R AU - Ahmadian A TI - Artificially Enriching the Training Dataset of Statistical Shape Models Via Constrained Cage-Based Deformation JO - Australasian Physical and Engineering Sciences in Medicine VL - 42 IS - 2 SP - 573 EP - 584 PY - 2019 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract