Segmentation of medical images using adaptive region growing (original) (raw)

Segmentation of medical images using adaptive region growing

Proc. SPIE Medical Imaging, 2001

Interaction increases flexibility of segmentation but it leads to undesirable behavior of an algorithm if knowledge being requested is inappropriate. In region growing, this is the case for defining the homogeneity criterion, as its specification depends also on image formation properties that are not known to the user. We developed a region growing algorithm that learns its homogeneity criterion automatically from characteristics of the region to be segmented. The method is based on a model that describes homogeneity and simple shape properties of the region. Parameters of the homogeneity criterion are estimated from sample locations in the region. These locations are selected sequentially in a random walk starting at the seed point, and the homogeneity criterion is updated continuously. This approach was extended to a fully automatic and complete segmentation method by using the pixels with the smallest gradient length in the not yet segmented image region as a seed point. The methods were tested for segmentation on test images and of structures in CT and MR images. We found the methods to work reliable if the model assumption on homogeneity and region characteristics are true. Furthermore, the model is simple but robust, thus allowing for a certain degree of deviation from model constraints and still delivering the expected segmentation result.

A Hybrid Region Growing Algorithm for Medical Image Segmentation

International Journal of Computer Science and Information Technology, 2012

In this paper, we have made improvements in region growing image segmentation. The First one is seeds select method, we use Harris corner detect theory to auto find growing seeds. Through this method, we can improve the segmentation speed. In this method, we use the Improved Harris corner detect theory for maintaining the distance vector between the seed pixel and maintain minimum distance between the seed pixels. The homogeneity criterion usually depends on image formation properties that are not known to the user. We induced a new uncertainty theory called Cloud Model Computing (CMC) to realize automatic and adaptive segmentation threshold selecting, which considers the uncertainty of image and extracts concepts from characteristics of the region to be segmented like human being. Next to region growing operation, we use canny edge detector to enhance the border of the regions. The method was tested for segmentation on X-rays, CT scan and MR images. We found the method works reliab...

3-D Medical Image Region-Growing based Segmentation Techniques, Challenges and Open Issues

Environment and Water Resource Management / 813: Modelling and Simulation / 814: Power and Energy Systems / 815: Health Informatics, 2014

Volumetric medical imaging acquisition technologies such as Computed Tomography (CT), Magnetic Resonance Tomography (MRT) and Positron Emission Tomography (PET) provide an effective means for noninvasive mapping of the anatomy of a subject. With these technologies being used every day there are enormous number of medical images, this has necessitated the use of computers in processing and analysis of these images. A significant task in medical image analysis is segmentation, whose goal is to partition a volumetric medical image into separate regions, usually anatomic structure (tissue type) that are meaningful for a specific task. In this paper region growing based segmentation techniques are discussed and the generic algorithms are given. The challenges and open issues in the medical field of this type of techniques are also highlighted. A recommendation of how the techniques can be used in the medical field is proposed.

Performance Evaluation of Region-Growing Based Segmentation Algorithms for Segmenting the Aorta

Jurnal Teknologi, 2016

Region-growing based image segmentation techniques, available for medical images, are reviewed in this paper. In digital image processing, segmentation of humans' organs from medical images is a very challenging task. A number of medical image segmentation techniques have been proposed, but there is no standard automatic algorithm that can generally be used to segment a real 3D image obtained in daily routine by the clinicians. Our criteria for the evaluation of different region-growing based segmentation algorithms are: ease of use, noise vulnerability, effectiveness, need of manual initialization, efficiency, computational complexity, need of training, information used, and noise vulnerability. We test the common region-growing algorithms on a set of abdominal MRI scans for the aorta segmentation. The evaluation results of the segmentation algorithms show that region-growing techniques can be a better choice for segmenting an object of interest from medical images.

Semi-Automatic Seeded Region Growing for Object Extracted in MRI

2016

this research characterizes a semi-automatic way to segemt objects found in medical images by using seeded region growing method, which increasingly became a popular method because of its ability to involve high-level knowledge of anatomical structures in seed selection process. Region based segmentation of the medical images is widely used in various clinical applications such as bone and tumor detection, visualization, and unsupervised image retrieval in clinical databases. Because of fuzziness of medical images in nature; segmenting regions depending on intensity is a very challenging task. In this paper, the popular seeded region grow methodology, which is used to segment anatomical structures in computed topography angiography images, is discussed. Homogeneity criteria used to control the region grow process during segmenting images is proposed.

REGION BASED SEGMENTATION FOR MEDICAL IMAGES

Image segmentation plays a vital role in many medical imaging applications by automatically locating the regions of interest. Image segmentation is the most crucial functions in image analysis and processing. Also segmentation results affect all the subsequent processes of image analysis. Manual segmentation of medical image by the radiologist is not only a tedious and time consuming process but also not very accurate. Hence it is necessary to develop medical image segmentation algorithms that are accurate and efficient. In this work, we propose a Region based technique. The proposed method has been tested and evaluated on several medical images. In this work, the medical image is lineated and extracted out so that it can be viewed individually. The results demonstrate that the proposed Region based Segmentation algorithm is highly efficient over Threshold based segmentation. This is validated using the performance measures such as completeness and correctness.

Medical Image Segmentation By Region Evolutionary Approach

In this paper, we propose a segmentation method based on region growing and evolutionary algorithms. The proposed approach is validated on synthetic and medical images. The results obtained show the good performance of this approach.

A new minimum variance region growing algorithm for image segmentation

Pattern Recognition Letters, 1997

Region growing is a very useful technique for image segmentation. Its efficiency mainly depends on its aggregation criterion. In the present paper, a new algorithm is proposed with a homogeneity criterion based on an adequate tuning between spatial neighbourhood and histogram neighbourhood. It differs from other techniques by reconsidering the pixel (or voxel) assignments on each step by a process which minimizes variance through special dilations. Thus, the region created by an initial seed can be non-connected and possibly does not contain this seed. Examples are given in dental surgery for 2D X-Ray images (and their associated 3D block) and for 3D images acquired by the Morphometre, the new 3D scanner constructed by GEMSE (General Electric Medical Systems). © 1997 Published by Elsevier Science B.V.

Novel Seed Selection and Conceptual Region Growing Framework for Medical Image Segmentation

2019

The objective of the paper is to propose a novel idea to improve initial conditions of seeded region growing (SRG) algorithm. We also propose a conceptual region growing framework to contribute to its progress in medical imaging. Our scheme is based on the simple observation that nature seems random but it repeats itself. Medical images are a kind of natural images and hence they must have a tendency of behaving like fractals. Our non-parametric Polygonal Seed Selection method does not need density estimation as before and shows clear Improvement to handle over segmentation problem. Qualitative results have been demonstrated on Axial Slices of Brain using traditional SRG, K-Means and Watershed segmentation.

Gradient Based Seeded Region Grow method for CT Angiographic Image Segmentation

2010

Segmentation of medical images using seeded region growing technique is increasingly becoming a popular method because of its ability to involve high-level knowledge of anatomical structures in seed selection process. Region based segmentation of medical images are widely used in varied clinical applications like visualization, bone detection, tumor detection and unsupervised image retrieval in clinical databases. As medical images are mostly fuzzy in nature, segmenting regions based intensity is the most challenging task. In this paper, we discuss about popular seeded region grow methodology used for segmenting anatomical structures in CT Angiography images. We have proposed a gradient based homogeneity criteria to control the region grow process while segmenting CTA images.