Heuristic Initialization for Active Contour Models in CT/MRI Image Processing

2015 ◽  
Vol 15 (03) ◽  
pp. 1550010
Author(s):  
Hao Liu ◽  
Hongbo Qian ◽  
Ning Dai ◽  
Jianning Zhao
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Heuristic Method ◽  
Initial Contour ◽  
Active Contour Models ◽  
Contour Model ◽  
Segmentation Approach ◽  
Edge Points ◽  
Contour Models ◽  
Level Set Evolution

It is an important segmentation approach of CT/MRI images to automatically extract contours in every slice using active contour models. The key point of the segmentation approach is to automatically construct initial contours for active contour models because any active contour model is sensitive to its initial contour. This paper presents an algorithm to construct such initial contours using a heuristic method. Assume that the contour in previous slice (previous contour) is accurate. The contour in the current slice (current contour) is constructed according to the previous contour using the way: Recognition and link of edge points of tissues according to the previous contour. The contour linking edge points is used as the initial contour of the distance regularized level set evolution (DRLSE) method and then an accurate contour can be extracted in the current slice.

scholarly journals Active Contour Model Using Fast Fourier Transformation for Salient Object Detection

Electronics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 192
Author(s):  
Umer Sadiq Khan ◽  
Xingjun Zhang ◽  
Yuanqi Su
Keyword(s):  
Object Detection ◽  
Fourier Transformation ◽  
Active Contour ◽  
Active Contour Model ◽  
Salient Object Detection ◽  
Fast Fourier Transformation ◽  
Salient Object ◽  
Active Contour Models ◽  
Contour Model ◽  
Contour Models

The active contour model is a comprehensive research technique used for salient object detection. Most active contour models of saliency detection are developed in the context of natural scenes, and their role with synthetic and medical images is not well investigated. Existing active contour models perform efficiently in many complexities but facing challenges on synthetic and medical images due to the limited time like, precise automatic fitted contour and expensive initialization computational cost. Our intention is detecting automatic boundary of the object without re-initialization which further in evolution drive to extract salient object. For this, we propose a simple novel derivative of a numerical solution scheme, using fast Fourier transformation (FFT) in active contour (Snake) differential equations that has two major enhancements, namely it completely avoids the approximation of expansive spatial derivatives finite differences, and the regularization scheme can be generally extended more. Second, FFT is significantly faster compared to the traditional solution in spatial domain. Finally, this model practiced Fourier-force function to fit curves naturally and extract salient objects from the background. Compared with the state-of-the-art methods, the proposed method achieves at least a 3% increase of accuracy on three diverse set of images. Moreover, it runs very fast, and the average running time of the proposed methods is about one twelfth of the baseline.

SEGMENTATION OF ABDOMEN DISEASES USING ACTIVE CONTOUR MODELS IN CT IMAGES

2015 ◽  
Vol 27 (05) ◽  
pp. 1550047 ◽  
Author(s):  
Gaurav Sethi ◽  
B. S. Saini
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Active Contour Model ◽  
Diagnostic System ◽  
Ct Images ◽  
Active Contour Models ◽  
Segmentation Methods ◽  
Contour Models ◽  
Edge Based ◽  
Level Set Evolution

Precise segmentation of abdomen diseases like tumor, cyst and stone are crucial in the design of a computer aided diagnostic system. The complexity of shapes and similarity of texture of disease with the surrounding tissues makes the segmentation of abdomen related diseases much more challenging. Thus, this paper is devoted to the segmentation of abdomen diseases using active contour models. The active contour models are formulated using the level-set method. Edge-based Distance Regularized Level Set Evolution (DRLSE) and region based Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) are used for segmentation of various abdomen diseases. These segmentation methods are applied on 60 CT images (20 images each of tumor, cyst and stone). Comparative analysis shows that edge-based active contour models are able to segment abdomen disease more accurately than region-based level set active contour model.

Automatic segmentation of medical images using a novel Harris Hawk optimization method and an active contour model

2021 ◽  
pp. 1-19
Author(s):  
Maria Tamoor ◽  
Irfan Younas
Keyword(s):  
Image Segmentation ◽  
Active Contour ◽  
Medical Image ◽  
Active Contour Model ◽  
Heart Diseases ◽  
Medical Image Segmentation ◽  
Gaussian Kernel ◽  
Initial Contour ◽  
Automated Method ◽  
Contour Model

Medical image segmentation is a key step to assist diagnosis of several diseases, and accuracy of a segmentation method is important for further treatments of different diseases. Different medical imaging modalities have different challenges such as intensity inhomogeneity, noise, low contrast, and ill-defined boundaries, which make automated segmentation a difficult task. To handle these issues, we propose a new fully automated method for medical image segmentation, which utilizes the advantages of thresholding and an active contour model. In this study, a Harris Hawks optimizer is applied to determine the optimal thresholding value, which is used to obtain the initial contour for segmentation. The obtained contour is further refined by using a spatially varying Gaussian kernel in the active contour model. The proposed method is then validated using a standard skin dataset (ISBI 2016), which consists of variable-sized lesions and different challenging artifacts, and a standard cardiac magnetic resonance dataset (ACDC, MICCAI 2017) with a wide spectrum of normal hearts, congenital heart diseases, and cardiac dysfunction. Experimental results show that the proposed method can effectively segment the region of interest and produce superior segmentation results for skin (overall Dice Score 0.90) and cardiac dataset (overall Dice Score 0.93), as compared to other state-of-the-art algorithms.

IMAGE COSEGMENTATION BASED ON LOCAL AND GLOBAL LEVEL SET METHODS

2012 ◽  
Vol 12 (03) ◽  
pp. 1250019 ◽  
Author(s):  
LIHE ZHANG ◽  
ZHENZHEN LIU
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Level Set Methods ◽  
Energy Functional ◽  
Image Statistics ◽  
Contour Model ◽  
Contour Models ◽  
Homogeneous Regions ◽  
The Given ◽  
Edge Indicator Function

In this paper, we propose a novel cosegmentation algorithm based on active contour model which utilizes local and global image statistics. Many localized region-based active contour models have been proposed to solve a challenging problem of the property (such as intensity, color, texture, etc.) inhomogeneities that often occurs in real images, but these models usually cannot reasonably evolve the curve in this situation that some center points along the curve are in homogeneous regions and their local regions are far away from the object. In order to overcome the difficulties we selectively enlarge the driven force of some points and introduce the edge indicator function to avoid the curve over-shrinking or over-expanding on the salient boundaries. In addition, we introduce global image statistics to better the curve evolution and try to avoid the given energy functional converging to a local minimum. Practical experiments show that our algorithm can obtain better segmentation results.

scholarly journals A novel myocardium segmentation approach based on neutrosophic active contour model

2017 ◽  
Vol 142 ◽  
pp. 109-116 ◽  
Author(s):  
Yanhui Guo ◽  
Guo-Qing Du ◽  
Jing-Yi Xue ◽  
Rong Xia ◽  
Yu-hang Wang
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Contour Model ◽  
Segmentation Approach

scholarly journals Active contour model for satellitale image combining local and global region based approach

2019 ◽  
Vol 15 (1) ◽  
pp. 247
Author(s):  
Mouri Hayat ◽  
Fizazi Hadria
Keyword(s):  
Active Contour ◽  
Active Contour Model ◽  
Initial Contour ◽  
Multiple Objects ◽  
Image Information ◽  
Contour Model ◽  
Global Image Information ◽  
Segmentation Of Images ◽  
Global And Local ◽  
Local Image

<p>Global and local image information is crucial for accurate segmentation of images with intensity inhomogeneity valuable minute details and multiple objects with various intensities. We propose a region-based active contour model which is able to utilize together local and global image information. The major contribution of this paper is to expand the LIF model which is includes only local image infofmation to a local and global model. The introduction of a new local and global signed pressure force function enables the extraction of accurate local and global image information and extracts multiple objects with several intensities. Several tests performed on some synthetic and real images indicate that our model is effective as well as less sensitivity to the initial contour location and less time compared with the related works. </p><p><em> </em></p>

scholarly journals Fused Second-Order MR Image Feature Framework for Region of Interest Delineation

2021 ◽  
Author(s):  
Shoaib Amin Banday ◽  
Samiya Khan ◽  
A. H. Mir
Keyword(s):  
Active Contour ◽  
Feature Fusion ◽  
Active Contour Model ◽  
Region Of Interest ◽  
Second Order ◽  
Image Feature ◽  
Feature Maps ◽  
Contour Model ◽  
Segmentation Approach ◽  
Critical Phases

Abstract Healthcare infrastructure relies on technology-driven solutions such as CAD systems for improving the overall efficiency of its procedures and processes. Image segmentation is one of the most critical phases for such systems in view of the fact that accuracy of this phase determines the efficacy of the later phases, to a large extent. Extensive research is underway to develop segmentation techniques that can achieve highest accuracy with some suggestions directed towards an information fusion based approach within the machine learning paradigm. This research paper proposes a fused second-order statistical image feature framework for Region of Interest delineation. It is a feature fusion-based segmentation approach (ACM-FT) that fuses texture driven feature maps from GLCM , GLRLM and Gabor filters. The proposed approach is then compared with Active Contour Model with classical edge detection method (ACM-ED) and Active Contour Model without edges (ACM-WE) using Overlap Index (OI) and Jackard’s Similarity Co-efficient (JSI). The proposed approach achieves an average accuracy of 92.17% and 93.19% for JSI and OI, respectively, demonstrating significant improvements.

Sign in / Sign up

Export Citation Format

Share Document