Automatic selection of localized region-based active contour models using image content analysis applied to brain tumor segmentation (original) (raw)
Related papers
Application of Active Contour Models in Medical Image Segmentation
2004
Recent developments on medical imaging techniques have brought a completely new research field on image processing. The principal aim is to improve medical diagnosis through segmented images. Techniques have been developed to help for identifying specific structures within a magnetic resonance image: MRI. The Active Contour methods, these methods are adaptable to the desired features in the image . In our work, we describe two classes of active contour models and discussing application aspects in medical imaging area.
MR Brain Image Segmentation Using Region Based Active Contour Model
2016
Various image segmentation methods are widely used for finding diseases and illness. Detection of any kind of brain tumors from magnetic resonance imaging (MRI) is very important for radiologists and image processing researchers. This paper described a segmentation method based on region based active contour model using level set approach to be useful for region of interest (ROI) based image compression system. The brain tumors (ROI) may be anywhere in MR brain images. The aim of this paper is to segment an image into non-intersecting regions, region of interest and other than region of interest and background for region based medical image compression system. In this system, the initial mask is firstly created. The initial curve can be anywhere in the images and interior contours are automatically detected. This method performs two main steps, curve evolution and segmenting process. Curve evolution is done by using level set method and active contour model segments the region. The ...
Adaptive Active Contour Model for Brain Tumor Segmentation
International Journal of Computer Vision and Image Processing
For accurately diagnosing the severity of brain tumors in MRI images, Glioma segmentation is a significant step. The Glioma segmentation is due to noise and weak edges of organs in medical images. The geodesic active contour model (GACM) is a standard method for the segmentation of complex organ structures based on edge maps. The GACM performs poorly due to this noise and weak edges. So, the authors propose a method that uses adaptive kernels instead of a constant kernel for creating strong edge maps for GACM. The kernels used in phase congruency are Log Gabor kernels, which resemble similar anisotropic properties like Gabor kernels. They have replaced these with adaptive kernels. This adaptive kernel-based phase congruency provides a robust edge map to be used in GACM. Experimentation shows that when compared with state-of-the-art edge detection techniques, adaptive kernels enhance the weak as well as strong edges and improve the overall performance. Moreover, the proposed methodol...
Integrating machine learning with region-based active contour models in medical image segmentation
Journal of Visual Communication and Image Representation, 2017
Region-based active contour models are effective in segmenting images with poorly defined boundaries but often fail when applied to images containing intensity inhomogeneity. The traditional models utilize pixel intensity and are very sensitive to parameter tuning. On the other hand, machine learning algorithms are highly effective in handling inhomogeneities but often result in noise from misclassified pixels. In addition, there is no objective function. We propose a framework which integrates machine learning with a region-based active contour model. Classification probability scores from machine learning algorithm, which are regularized using a non-linear function, are used to replace the pixel intensity values during energy minimization. In our experiments, we integrate the k-nearest neighbours and the support vector machine with the Chan-Vese method and compare the results obtained with the traditional methods of Chan-Vese and Li et al. The proposed framework gives better accuracy and less sensitive to parameter tuning.
Multiphase Region-based Active Contours for Semi-automatic Segmentation of Brain MRI Images
Proceedings of the 10th International Conference on Computer Vision Theory and Applications, 2015
Segmenting brain magnetic resonance (MRI) images of the brain into white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) is an important problem in medical image analysis. The study of these regions can be useful for determining different brain disorders, assisting brain surgery, post-surgical analysis, saliency detection and for studying regions of interest. This paper presents a segmentation method that partitions a given brain MRI image into WM, GM and CSF regions through a multiphase region-based active contour method followed by a pixel correction thresholding stage. The proposed region-based active contour method is applied in order to partition the input image into four different regions. Three of those regions within the brain area are then chosen by intersecting a hand-drawn binary mask with the computed contours. Finally, an efficient thresholding-based pixel correction method is applied to the computed WM, GM and CSF regions to increase their accuracy. The segmentation results are compared with ground truths to show the performance of the proposed method.
A novel active contour model for medical image segmentation
Journal of Shanghai Jiaotong University (Science), 2010
A novel segmentation method for medical image with intensity inhomogeneity is introduced. In the proposed active contour model, both region and gradient information are taken into consideration. The former, i.e., region-based fitting energy, draws upon the region information and guarantees the accurate extraction of inhomogeneous image's local information. The latter, i.e., an edge indicator, weights the length penalizing term to consider the gradient constrain. Moreover, signed distance penalizing term is also added to ensure accurate computation and avoid the time-consuming re-initialization of evolving level set function. Experiments for synthetic and real images demonstrate the feasibility and superiority of the proposed model.
Journal of Physics: Conference Series, 2016
Gliomas are tumours arising from the interstitial tissue of the brain which are heterogeneous, infiltrative and possess ill-defined borders. Tumour subregions (e.g. solid enhancing part, edema and necrosis) are often used for tumour characterisation. Tumour demarcation into substructures facilitates glioma staging and provides essential information. Manual segmentation had several drawbacks that include laborious, time consuming, subjected to intra and inter-rater variability and hindered by diversity in the appearance of tumour tissues. In this work, active contour model (ACM) was used to segment the solid enhancing subregion of the tumour. 2D brain image acquisition data using 3T MRI fast spoiled gradient echo sequence in post gadolinium of four histologically proven high-grade glioma patients were obtained. Preprocessing of the images which includes subtraction and skull stripping were performed and then followed by ACM segmentation. The results of the automatic segmentation method were compared against the manual delineation of the tumour by a trainee radiologist. Both results were further validated by an experienced neuroradiologist and a brief quantitative evaluations (pixel area and difference ratio) were performed. Preliminary results of the clinical data showed the potential of ACM model in the application of fast and large scale tumour segmentation in medical imaging.
Active Contour Model for Brain MR Tumor Segmentation and Volume Estimation
International Journal of Engineering and Advanced Technology
Brain MR tumor segmentation and estimation of volume is a critical task in medical applications. Brain tumors are analyzed by the common test method known as magnetic resonance imaging (MRI) which provides a detail image of brain. The proposed work involves detection of tumor in brain using deep learning based active contour model. Segmentation is the main objective of the proposed work for achieving detailed information about the tumor and accurate volume estimation to detect the size of the tumor. The Euclidean similarity factor (ESF) is used for considering the spatial distances and intensity differences of the region there by preserving all the fine details of the image. 3D convolutional neural network (3DCNN) is used for extracting the features and segmentation to identify the tumor location in the brain. Finally, shoelace method is used to estimate the volume of the tumor, and it provides treatment planning, surgical methods, estimation of dose, etc. The simulation results in ...
Performance metrics for active contour models in image segmentation
Image segmentation is one of the significant techniques in image processing to distinguish desired parts from its background for further analysis. It provides visual means for inspection of anatomical structure of human body, identification of disease, tracking of its development and input for surgical planning and simulation. Active contour models are regarded as promising and vigorously research model-based approach to computer assisted medical image analysis.
Segmentation of brain MRI using active contour model
International Journal of Imaging Systems and Technology
Alzheimer disease is a neurodegenerative disorder that impairs memory, cognitive function, and gradually leads to dementia, physical deterioration, loss of independence, and death of the affected individual. In this context, segmentation of medical images is a very important technique in the field of image analysis and Computer-Assisted Diagnosis. In this article, we introduce a new automatic method of brain images' segmentation based on the Active Contour (AC) model to extract the Hippocampus and the Corpus Callosum (CC). Our contribution is to combine the geometric method with the statistical method of the AC. We used the Caselle Level Set and added a learning phase to build an average shape and to make the initialization task automatic. For the step of contour evolution, we used the principle of Level set and we added to it the a priori knowledge. Experimental results are very promising. V