Volume 28, Issue 3
Computational Software: NeuronSeg_BACH: Automated Neuron Segmentation Using B-Spline Based Active Contour and Hyperelastic Regularization

Commun. Comput. Phys., 28 (2020), pp. 1219-1244.

Published online: 2020-07

Preview Purchase PDF 46 2534
Export citation

Cited by

• Abstract

The vast diversity in neuron cell morphology has led to an increase in automated algorithms which can accurately reconstruct neurons from microscopy images. The poor quality of brightfield and fluorescence microscopy images and the thin branch-like fibrous structure of neurons make the process of manual segmentation challenging. We propose a novel automatic neuron segmentation framework using a B-spline based active contour deformation model with hyperelastic regularization, and develop a MATLAB software tool named "NeuronSeg_BACH". In NeuronSeg_BACH, initialization of the contour is done automatically by detecting cell body and neurites separately. This boundary-extraction based algorithm utilizes cubic B-splines to deform active contours to match the neuron cell surface accurately. Using adaptive local refinement, finer level deformation of the active contour is captured using truncated hierarchical B-splines in a multiresolution manner. By introducing hyperelastic regularization, we allow large nonlinear deformations of the active contours. Unlike other existing methods which represent boundaries as piecewise constant functions, we provide a more accurate and smooth representation of the neuron geometry. In the level set segmentation framework, the implicit level set function is defined using $C^2$ continuous B-splines. Improved segmentation results are shown for 2D and 3D synthetic and microscopy images as compared to other methods.

• Keywords

Neuron morphology, image segmentation, active contour models, hyperelastic regularization, truncated hierarchical B-splines.

68U10

• BibTex
• RIS
• TXT
@Article{CiCP-28-1219, author = {Pawar , Aishwarya and Jessica Zhang , Yongjie}, title = {Computational Software: NeuronSeg_BACH: Automated Neuron Segmentation Using B-Spline Based Active Contour and Hyperelastic Regularization}, journal = {Communications in Computational Physics}, year = {2020}, volume = {28}, number = {3}, pages = {1219--1244}, abstract = {

The vast diversity in neuron cell morphology has led to an increase in automated algorithms which can accurately reconstruct neurons from microscopy images. The poor quality of brightfield and fluorescence microscopy images and the thin branch-like fibrous structure of neurons make the process of manual segmentation challenging. We propose a novel automatic neuron segmentation framework using a B-spline based active contour deformation model with hyperelastic regularization, and develop a MATLAB software tool named "NeuronSeg_BACH". In NeuronSeg_BACH, initialization of the contour is done automatically by detecting cell body and neurites separately. This boundary-extraction based algorithm utilizes cubic B-splines to deform active contours to match the neuron cell surface accurately. Using adaptive local refinement, finer level deformation of the active contour is captured using truncated hierarchical B-splines in a multiresolution manner. By introducing hyperelastic regularization, we allow large nonlinear deformations of the active contours. Unlike other existing methods which represent boundaries as piecewise constant functions, we provide a more accurate and smooth representation of the neuron geometry. In the level set segmentation framework, the implicit level set function is defined using $C^2$ continuous B-splines. Improved segmentation results are shown for 2D and 3D synthetic and microscopy images as compared to other methods.

}, issn = {1991-7120}, doi = {https://doi.org/10.4208/cicp.OA-2020-0025}, url = {http://global-sci.org/intro/article_detail/cicp/17692.html} }
TY - JOUR T1 - Computational Software: NeuronSeg_BACH: Automated Neuron Segmentation Using B-Spline Based Active Contour and Hyperelastic Regularization AU - Pawar , Aishwarya AU - Jessica Zhang , Yongjie JO - Communications in Computational Physics VL - 3 SP - 1219 EP - 1244 PY - 2020 DA - 2020/07 SN - 28 DO - http://doi.org/10.4208/cicp.OA-2020-0025 UR - https://global-sci.org/intro/article_detail/cicp/17692.html KW - Neuron morphology, image segmentation, active contour models, hyperelastic regularization, truncated hierarchical B-splines. AB -

The vast diversity in neuron cell morphology has led to an increase in automated algorithms which can accurately reconstruct neurons from microscopy images. The poor quality of brightfield and fluorescence microscopy images and the thin branch-like fibrous structure of neurons make the process of manual segmentation challenging. We propose a novel automatic neuron segmentation framework using a B-spline based active contour deformation model with hyperelastic regularization, and develop a MATLAB software tool named "NeuronSeg_BACH". In NeuronSeg_BACH, initialization of the contour is done automatically by detecting cell body and neurites separately. This boundary-extraction based algorithm utilizes cubic B-splines to deform active contours to match the neuron cell surface accurately. Using adaptive local refinement, finer level deformation of the active contour is captured using truncated hierarchical B-splines in a multiresolution manner. By introducing hyperelastic regularization, we allow large nonlinear deformations of the active contours. Unlike other existing methods which represent boundaries as piecewise constant functions, we provide a more accurate and smooth representation of the neuron geometry. In the level set segmentation framework, the implicit level set function is defined using $C^2$ continuous B-splines. Improved segmentation results are shown for 2D and 3D synthetic and microscopy images as compared to other methods.

Aishwarya Pawar & Yongjie Jessica Zhang. (2020). Computational Software: NeuronSeg_BACH: Automated Neuron Segmentation Using B-Spline Based Active Contour and Hyperelastic Regularization. Communications in Computational Physics. 28 (3). 1219-1244. doi:10.4208/cicp.OA-2020-0025
Copy to clipboard
The citation has been copied to your clipboard