Geodesic Active Contour Method Research Articles

Jawbone Segmentation with Trabecular Bone Preservation from Cone Beam CT Images

To segment jaw structures in both open and closed mouth states from cone beam CT images and to preserve the true structures of trabecular bones. Segmentation algorithms of the mandible and maxilla were designed based on their different structures. We detected edges in volume and segment edges of the mandible and maxilla whether the mouth of a patient was open or closed. The internal structures of the mandible and maxilla were preserved by a morphological method with different parameters, respectively. An axial plane corresponding to the bottom of the hard palate was identified so that the bone structures of the maxilla above this plane were removed. Finally, the mandibular surface was smoothed by a simple thresholding method, and the maxillary surface was optimized by a geodesic active contours method. The 3D jaw model was segmented automatically by our proposed procedure with high accuracy. The average dice coefficients of the mandible and maxilla were equal to 0.9709 and 0.9420, respectively. The proposed jaw segmentation algorithm is automatic and knowledge-driven. The segmented jaws truly demonstrate the cortical and trabecular bone structures. It may potentially assist doctors in diagnosis and surgical planning.

Alternate Level Set Evolutions With Controlled Switch for Tooth Segmentation

CBCT images have been widely used in digital orthodontics. In CBCT images, there are some tooth boundaries of blurriness and disappearance, and the teeth are of intensity inhomogeneity. In order to identify these boundaries and segment teeth, this paper develops an approach of alternate level set evolutions with controlled switch via slice-by-slice tooth segmentation: the user selects a voxel inside a tooth to initialize a small circle encircling the voxel, and the curve is automatically expanded until the tooth surface is formed. In each slice, the curve is expanded by two level set evolutions: the first level set evolution handles the intensity inhomogeneity and the second level set evolution solves the boundary blurriness and disappearance of the teeth. Experiments showed that the proposed method successfully segmented 12 CBCT datasets of 356 teeth and outperformed the geodesic active contour method and the popular method and the state-of-the-art method.

Stochastic segmentation on images with uncertain data

AbstractThe present work considers a stochastic segmentation method on images in the presence of noise within a PDE‐based image processing framework. Classical methods are not able to capture the error propagation of uncertain estimated input data and their impact on the final segmentation result, which can be of great importance for clinical decisions. Therefore, an intrusive generalized polynomial chaos (gPC) expansion for a stochastic level‐set based geodesic active contours method is proposed. Employing an operator splitting and a stochastic Galerkin projection a deterministic and symmetric non‐linear hyperbolic system can be obtained, which can be treated using common numerical methods.

Contour evolution method for precise boundary delineation of medical images

Image segmentation is an important precursor to boundary delineation of medical images. One of the major challenges in applying automatic image segmentation in medical images is the imperfection in the imaging process which can result in inconsistent contrast and brightness levels, and low image sharpness and vanishing boundaries. Although recent advances in deep learning produce vast improvements in the quality of image segmentation, the accuracy of segmentation around object boundaries still requires improvement. We developed a new approach to contour evolution that is more intuitive but shares some common principles with the active contour model method. The method uses two concepts, namely the boundary grid and sparse boundary representation, as an implicit and explicit representation of the boundary points. We tested our method using lumbar spine MRI images of 515 patients. The experiment results show that our method performs up to 10.2 times faster and more flexible than the geodesic active contours method. Using BF-score contour-based metric, we show that our method improves the boundary accuracy from 74% to 84% as opposed to 63% by the latter method.

Image Segmentation for the Treatment Planning of Magnetic Resonance-Guided High-Intensity Focused Ultrasound (MRgHIFU) Therapy: A Parametric Study

In the present research work, image segmentation methods were studied to find internal parameters that provide an efficient identification of the regions of interest in Magnetic Resonance (MR) images used for the therapy planning of High-Intensity Focused Ultrasound (HIFU), a minimally invasive therapeutic method used for selective ablation of tissue. The involved image segmentation methods were threshold, level set and watershed segmentation algorithm with markers (WSAM), and they were applied to transverse and sagittal MR images obtained from an experimental setup of a murine experiment. A parametric study, involving segmentation tests with different values for the internal parameters, was carried out. The F-measure results from the parametric study were analyzed by region using Welch’s ANOVA followed by post hoc Games-Howell test to determine the most appropriate method for region identification. In transverse images, the threshold method had the best performance for the air region with a F-measure median of 0.9802 (0.9743–0.9847, interquartile range IQR 0.0104), the WSAM for the tissue, gel-pad, transducer and water region with a F-measure median of 0.9224 (0.8718–0.9468, IQR 0.075), 0.9553 (0.9496–0.9606, IQR 0.011), 0.9416 (0.9330–0.9540, IQR 0.021) and 0.9769 (0.9741–0.9803, IQR 0.0062), respectively. In sagittal images, threshold method had the best performance for the air region with a F-measure median of 0.9680 (0.9589–0.9735, IQR 0.0146), the WSAM for the tissue and gel-pad regions with a F-measure median of 0.9241 (0.8870–0.9426, IQR 0.0556) and 0.9553 (0.9472–0.9625, IQR 0.0153), respectively, and the Geodesic Active Contours (GAC) method for the transducer and water regions with a F-measure median of 0.9323 (0.9221–0.9402, IQR 0.0181) and 0.9681 (0.9627–0.9715, IQR 0.0088), respectively. The present research work integrates preliminary results to generate more efficient procedures of image segmentation for treatment planning of the MRgHIFU therapy. Future work will address the search of an automatic segmentation process, regardless of the experimental setup.

A new fast morphological geodesic active contour method for lung CT image segmentation

This work proposes a new adaptive approach to lung segmentation based on a non-parametric adaptive active contour method (ACM) without previous training using the new Fuzzy Border Detector, called Fast Morphological Geodesic Active Contour (FGAC). Performance was evaluated with 72 lung images of volunteers that were with fibrosis, chronic obstructive pulmonary disease or were healthy. A manual segmentation by a medical specialist was considered the gold standard. The mean time of segmentation of seventy-two the two lungs was 1.98 s. This was the best average time among all the other segmentation methods compared here: GVF (240 s), VFC(30 s), OPS Euclidean (5.86 s), SISDEP (4.90 s), and CRAD (2 s); thus showing its potential for real-time applications. The FGAC showed good results in all similarity metrics compared in this work like the Jaccard Index (92.73%), Dice coefficient (96.19%) and Matthew correlation coefficient (95.54%), and also achieved good results in sensitivity (99.21%), and accuracy (98.86%). The new approach showed quantitative indexes better than the traditional methods VFC, GVF, RHT mod, RHT multi. Moreover, we evaluated the proposed method against the supervised techniques OPS-Euclidean, SISDEP, CRISP and CRAD. Our approach achieved superior or equivalent results to these methods, however with a shorter convergence time. These results had good indexes suggesting that the proposed approach can be used to aid medical diagnosis in pulmonology.

A Novel Technique to Detect Caries Lesion Using Isophote Concepts

Background and ObjectivesDental caries is one of the most common painful and infectious oral diseases. Early detection of caries lesion prevents the spreading of infection. Generally, dentists use x-ray images to locate the lesion's position. Dental x-ray images have poor intensity which results difficulties in finding exact affected area at a glance. Due to scarcity of dentists at government hospital, it becomes very difficult for the dentists to treat large number of patients in a short span of time. The objective of this work is to design a system to assist dentists to detect caries lesion quickly and more accurately. Deep learning based method is not suitable for this application because there is not enough training set is available to prepare the pre-trained model properly for deep learning. Traditional handcrafted method is desirable for such situation. MethodsDental x-ray not only contains the image of teeth and bonny structure of the jaws but also the tissues within the gum regions. So normal texture based segmentation is not enough to detect the caries lesion. In x-ray, caries lesion looks like a catchment basin, in which the depth at the center is maximum. Isophote along with geodesic active contour method is suitable to model such property of caries lesion. But prior to that multistage background elimination is essential to locate the suspected caries region. Ramdomness calculation and rescaling of that value on the basis of a small training data set is the first part of this multi stage background elimination process. Initial background elimination is performed on the basis of modified k-means clustering upon the entropy value and gray scale values of the x-ray image. In this clustering technique the number of cluster is determined automatically based on analyzing the distribution of data points. The clustering technique is immune against over clustering. Most of the caries lesion lies within the teeth region. Hence this region is surrounded by teeth region. This property is also checked to detect the suspected caries lesion and eliminate the background. ResultTill now very limited dental x-ray databases with caries lesion is available online. ‘Digital dental periapical x-ray database for caries screening’ dataset is used to test the method. The proposed method achieved overall 94% of accuracy and average computational time is below 4.5 sec. DiscussionThis is an alternate solution to detect ROI when deep learning technique fails due to lack of exhaustive training set. This approach fails to generate correct result if resolution of the x-ray image is very low. Low resolution images make confusion between randomness and noise. In addition to that catchment basin properties are not identified properly. Due to this carries lesion are not properly identified.

Comparison of segmentation using fast marching and geodesic active contours methods for bone

Image processing is important in diagnosing diseases or damages of human organs. One of the important stages of image processing is segmentation process. Segmentation is a separation process of the image into regions of certain similar characteristics. It is used to simplify the image to make an analysis easier. The case raised in this study is image segmentation of bones. Bone's image segmentation is a way to get bone dimensions, which is needed in order to make prosthesis that is used to treat broken or cracked bones. Segmentation methods chosen in this study are fast marching and geodesic active contours. This study uses ITK (Insight Segmentation and Registration Toolkit) software. The success of the segmentation was then determined by calculating its accuracy, sensitivity, and specificity. Based on the results, the Active Contours method has slightly higher accuracy and sensitivity values than the fast marching method. As for the value of specificity, fast marching has produced three image results that have higher specificity values compared to those of geodesic active contour's. The result also indicates that both methods have succeeded in performing bone's image segmentation. Overall, geodesic active contours method is quite better than fast marching in segmenting bone images.

Automated Segmentation and Analysis of Corpus Callosum in Autistic MR Brain Images Using Fuzzy-c-Means-Based Level Set Method

In this work, the segmentation and analysis of the corpus callosum (CC) in autistic MR brain images is carried out using a fuzzy c-means (FCM)-based level set method. Initially, the images are skull-stripped using the geodesic active contour method. The CC is extracted from the skull-stripped images using the FCM-based level set method. FCM clustering forms the initial contour. The evolution of the curve is then regularized using a distance function in the level sets. The segmented CC is divided into five segments, whose areas are measured. The subjective results show that the proposed method is able to extract the CC from skull-stripped images. It is demonstrated that the level set with the FCM as the initial contour gives better results than those obtained with a manual initial contour. It is found that the autistic subjects have a reduced CC area compared to that of control subjects. The total CC area of autistic subjects gives a correlation of R = 0.39 with the verbal intelligence quotient (IQ) values. Further analysis shows that the anterior third region of the CC gives significant discrimination of the control and autistic subjects compared to the other segments. Its correlation (R) with verbal IQ is found to be 0.27 in autistic subjects. The feature area extracted from the CC and its segments are significant, hence the results may be clinically helpful in the mass screening of autistic subjects.

An Efficient Liver-Segmentation System Based on a Level-Set Method and Consequent Processes

This paper presents an efficient liver-segmentation system developed by combining three ideas under the operations of a level-set method and consequent processes. First, an effective initial process creates mask and seed regions. The mask regions assist in prevention of leakage regions due to an overlap of gray-intensities between liver and another soft-tissue around ribs and verte-brae. The seed regions are allocated inside the liver to measure statistical values of its gray-intensities. Second, we introduce liver-corrective images to represent statistical regions of the liver and preserve edge information. These images help a geodesic active contour (GAC) to move without obstruction from high level of image noises. Lastly, the computation time in a level-set based on reaction-diffusion evolution and the GAC method is reduced by using a concept of multi-resolution. We applied the proposed system to 40 sets of 3D CT-liver data, which were acquired from four patients (10 different sets per patient) by a 4D-CT imaging system. The segmentation results showed 86.38% ± 4.26% (DSC: 91.38% ± 2.99%) of similarities to outlines of manual delineation provided by a radiologist. Meanwhile, the results of liver segmentation only using edge images presented 79.17% ± 5.15% or statistical regions showed 74.04% ± 9.77% of similarities.

A Fast Geodesic Active Contour Model for Medical Image Segmentation Using Prior Analysis and Wavelets

The deformable geodesic active contour (GAC) method is one of the most popular techniques used in object boundary detection in images. In this work, we improve the automatic GAC technique by incorporating prior information extracted from the image region of interest. In addition, we propose a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. The results show both an improvement of more than 40 % in convergence speed together with an excellent accuracy when compared with the previous work.

Segmentation of the thrombus of giant intracranial aneurysms from CT angiography scans with lattice Boltzmann method

Computed Tomography Angiography (CTA) plays an essential role in the diagnosis, treatment evaluation, and monitoring of cerebral aneurysms. Segmentation of CTA medical images of giant intracranial aneurysms (GIA) provides quantitative measurements of thrombus and aneurysms geometrical characteristics allowing 3D reconstruction. In fact, GIA demonstrated neuroradiological features and propensity of partial or total spontaneous intra-aneurysmal thrombosis generating a thrombus. Despite intensive researches on medical image segmentation, aneurysm (Lumen, Thrombus, and Parent Blood Vessels) segmentation remains as a difficult problem that has not been yet resolved. In this paper, we proposed a Lattice Boltzmann Geodesic Active Contour Method (LBGM) for aneurysm segmentation in CTA images in order to estimate both the volumes of the thrombus and the aneurysm. Although the noise in the CTA images is very strong and the edges of the thrombus are not so different than the surrounding tissues, the aneurysms are segmented effectively. Based on these results, a method using a dome-neck aspect ratio (AR) parameter for the evaluation of the Spontaneous Thrombosis (ST) phenomena demonstrates the promising potentiality of this LBGM for clinical applications.

Analysis of ventricle regions in Alzheimer's brain MR images using level set based methods

In this work, an attempt has been made to analyse ventricle region of the T1 weighted coronal Magnetic Resonance (MR) brain images and study the progression of severity in Alzheimer’s Disease (AD) conditions. Two level set methods namely Distance Regularised Level Set Evolution (DRLSE) and geodesic active contour are used to extract the desired region of interest. Eighty geometric features are derived from the segmented ventricle region. The most significant parameters are found using principal component analysis. Results demonstrate that the DRLSE shows better performance in extraction of the boundary of the ventricle region than geodesic active contour method. The geometrical feature, area is found to have a high correlation with brain to ventricle index for all subjects. Further, it is observed that this feature gives a distinct separation between normal and abnormal AD subjects (p value = 0.00012). It also provides high correlation for normal (.97) and abnormal AD subjects (<0.9). Hence, this analysis could be a useful supplement to physicians in diagnosis and treatment of Alzheimer’s and other neurodegenerative disorders.

Coupling edge and region-based information for boundary finding in biomedical imagery

We propose in this paper a boundary finding scheme for biomedical imagery which integrates a region-based method and an edge-based technique. We show that more accurate and robust results may be obtained through seeking a joint solution to the traditional approach of curve evolution. The approach incorporates an energy model based on prior distribution and likelihood into the curve evolution of the geodesic active contour (GAC) method. During curve evolution, we use a decision function to adjust relevant parameters in the model automatically so that the curve can easily avoid ‘clutter’. For termination of curve evolution, a stability index is proposed which examines curve evolution convergence to ensure that the curve arrives at the boundary robustly and accurately. The experimental results demonstrate that advantages can be achieved using our approach compared to several classical methods. ► Propose a boundary finding scheme for biomedical imagery by integrating a region-based method and an edge-based technique. ► Incorporate an energy model based on prior distribution into the curve evolution. ► Propose a stability index for examining the convergence of curve evolution.

Delineating lakes and enclosed islands in satellite imagery by geodesic active contour model

The objective of the present paper is to develop a new method for delineating lakes and enclosed islands from shuttle radar topography mission (SRTM) digital elevation model (DEM). The Thousand‐Island Lake in China is chosen as the study site. DEM may have missing values or be inaccurate over water bodies. Thus, it is not trivial to delineate the shorelines of lake directly from DEM. We achieve this objective by overlaying the boundary derived from the Landsat image of the same area. Unlike traditional water body delineation techniques, e.g. the band ratio method, which make use of physical quantities, we only use the colour information from Landsat ETM+ band 7, 4 and 2. The main reason is that the colour information is the only resource available for most publicly available satellite data such as the maps from Google Earth. Thus, it is necessary to develop a method depending on only colour information. In the Landsat image, a discrimination function to determine whether a pixel belongs to the lake area is obtained by studying sample pixels chosen from the lake area. The delineation of shorelines is an evolutionary process. The evolution equation is derived according to the active contour model and the discrimination function. The initial contour is inside the lake and expands according to the evolution equation. The evolving curve converges to the boundaries of the lake efficiently with a satisfactory result. Finally, the shorelines are overlaid on the DEM according to latitude and longitude. Our geodesic active contour method is a general one, and could be used to delineate objects of interest such as oil slicks and burn scars in satellite images.

Color Image Segmentation for Objects of Interest with Modified Geodesic Active Contour Method

In this paper, we propose a novel variational method for color image segmentation using modified geodesic active contour method. Our goal is to detect Object(s) of Interest (OOI) from a given color image, regardless of other objects. The main novelty of our method is that we modify the stopping function in the functional of usual geodesic active contour method so that the new stopping function is coupled by a discrimination function of OOI. By minimizing the functional, the OOI is segmented. Firstly, we study the pixel properties of the OOI by sample pixels visually chosen from OOI. From these sample pixels, by the principal component analysis and interval estimation, the discrimination function of whether a pixel is in the OOI is obtained probabilistically. Then we propose the energy functional for the segmentation of OOI with new stopping function. Unlike usual stopping functions defined by the image gradient, our improved stopping function depends on not only the image gradient but also the discrimination function derived from the color information of OOI. As a result, better than usual active contour methods which detect all objects in the image, our modified active contour method can detect OOI but without unwanted objects. Experiments are conducted in both synthetic and natural images. The result shows that our algorithm is very efficient for detecting OOI even the background is complicated.

Quantitative Evaluation of Contour Segmentation of Three Dimensional Image Using Level Set Method

Quantitative evaluation of level set contour segmentation method applied to three dimensional images detecting image edge based on threshold is discussed. The integration of two popular level set methods, i.e., reinitialization method and geodesic active contour method, leads to success in development of robust, with high accuracy, level set based segmentation method. The applications of this method to both synthetic and clinical medical images are shown. Accuracy of the propose method, in the view of both averaged contour location and standard deviation of curvature in the vicinity of contour, calculated using obtained level set function is discussed.