scholarly journals Unsupervised Cardiac Image Segmentation via Multiswarm Active Contours with a Shape Prior

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
I. Cruz-Aceves ◽  
J. G. Avina-Cervantes ◽  
J. M. Lopez-Hernandez ◽  
M. G. Garcia-Hernandez ◽  
M. A. Ibarra-Manzano
Keyword(s):  
Particle Swarm Optimization ◽  
Image Segmentation ◽  
Human Heart ◽  
Active Contours ◽  
Particle Swarm ◽  
Clinical Decision ◽  
Magnetic Resonance Images ◽  
Polar Coordinate System ◽  
Shape Prior ◽  
Swarm Optimization

This paper presents a new unsupervised image segmentation method based on particle swarm optimization and scaled active contours with shape prior. The proposed method uses particle swarm optimization over a polar coordinate system to perform the segmentation task, increasing the searching capability on medical images with respect to different interactive segmentation techniques. This method is used to segment the human heart and ventricular areas from datasets of computed tomography and magnetic resonance images, where the shape prior is acquired by cardiologists, and it is utilized as the initial active contour. Moreover, to assess the performance of the cardiac medical image segmentations obtained by the proposed method and by the interactive techniques regarding the regions delineated by experts, a set of validation metrics has been adopted. The experimental results are promising and suggest that the proposed method is capable of segmenting human heart and ventricular areas accurately, which can significantly help cardiologists in clinical decision support.

scholarly journals Multiple Active Contours Driven by Particle Swarm Optimization for Cardiac Medical Image Segmentation

2013 ◽  
Vol 2013 ◽  
pp. 1-13 ◽  
Author(s):  
I. Cruz-Aceves ◽  
J. G. Aviña-Cervantes ◽  
J. M. López-Hernández ◽  
S. E. González-Reyna
Keyword(s):  
Particle Swarm Optimization ◽  
Image Segmentation ◽  
Active Contour ◽  
Medical Image ◽  
Active Contours ◽  
Active Contour Model ◽  
Particle Swarm ◽  
Magnetic Resonance Images ◽  
Swarm Optimization ◽  
Contour Model

This paper presents a novel image segmentation method based on multiple active contours driven by particle swarm optimization (MACPSO). The proposed method uses particle swarm optimization over a polar coordinate system to increase the energy-minimizing capability with respect to the traditional active contour model. In the first stage, to evaluate the robustness of the proposed method, a set of synthetic images containing objects with several concavities and Gaussian noise is presented. Subsequently, MACPSO is used to segment the human heart and the human left ventricle from datasets of sequential computed tomography and magnetic resonance images, respectively. Finally, to assess the performance of the medical image segmentations with respect to regions outlined by experts and by the graph cut method objectively and quantifiably, a set of distance and similarity metrics has been adopted. The experimental results demonstrate that MACPSO outperforms the traditional active contour model in terms of segmentation accuracy and stability.

Brain MR Image Multilevel Thresholding by Using Particle Swarm Optimization, Otsu Method and Anisotropic Diffusion

2019 ◽  
Vol 10 (3) ◽  
pp. 91-106
Author(s):  
Abdul Kayom Md Khairuzzaman ◽  
Saurabh Chaudhury
Keyword(s):  
Particle Swarm Optimization ◽  
Image Segmentation ◽  
Anisotropic Diffusion ◽  
Particle Swarm ◽  
Structural Similarity ◽  
Multilevel Thresholding ◽  
Bacterial Foraging Optimization ◽  
Mr Image ◽  
Swarm Optimization ◽  
Mr Image Segmentation

Multilevel thresholding is widely used in brain magnetic resonance (MR) image segmentation. In this article, a multilevel thresholding-based brain MR image segmentation technique is proposed. The image is first filtered using anisotropic diffusion. Then multilevel thresholding based on particle swarm optimization (PSO) is performed on the filtered image to get the final segmented image. Otsu function is used to select the thresholds. The proposed technique is compared with standard PSO and bacterial foraging optimization (BFO) based multilevel thresholding techniques. The objective image quality metrics such as Peak Signal to Noise Ratio (PSNR) and Mean Structural SIMilarity (MSSIM) index are used to evaluate the quality of the segmented images. The experimental results suggest that the proposed technique gives significantly better-quality image segmentation compared to the other techniques when applied to T2-weitghted brain MR images.

Sign in / Sign up

Export Citation Format

Share Document