Region-based Active Contour Model Research Articles

Brain Tumor Prediction and Segmentation with Morphological Region-based Active Contour Model and Refinement using Boltzmann Monte Carlo Method in MRI Images

Objectives: The primary goal of the research work is to accurately detect the precise location of the brain tumor in the radiological Magnetic Resonance Imaging (MRI) images of human brain using segmentation method. Methods: In this research work, we introduce mainly the Morphological Region-based Active Contour model and Boltzmann Monte Carlo method (MACB model), involving a comprehensive three-step methodology for the segmentation of the brain, MRI images in order to detect brain tumor. The initial step involves pre-processing which includes Gaussian filtering for noise reduction and Contrast Limited Adaptive Histogram Equalization (CLAHE) technique to enhance image features. In the second step, we identify tumor-related clusters using morphological operations and delineate the tumor regions using Active Contour (Snake) model to get a segmented image. In the final step, the Boltzmann Monte Carlo method is used to refine the edges of the segmented image. To evaluate the effectiveness of this approach, the 2D brain tumor datasets, available in the public domain, are used. The first dataset is taken from Kaggle website and has 3064 MRI human brain images and its respective ground truth images which is used for segmentation. The second dataset is used for visualization of segmented tumor, available in the same Kaggle website. Findings: The Performance metrics for finding similarity between the segmented images generated using the proposed MACB model and the ground truth images, available in the first dataset, exhibit higher values. That is, the proposed method has achieved higher values of Dice Similarity Coefficient (DSC): 93.26%, Jaccard Co-efficient: 86.44%, Sensitivity: 97.27%, Specificity: 99.43% and Pixel accuracy: 98.95%. Novelty: In this research work, MACB model is proposed for the detection, segmentation, and refinement process of brain tumor by incorporating Boltzmann Monte Carlo method with Morphological Region-Based Active Contour model. This novel approach has resulted in enhanced precision and efficiency in the brain tumor segmentation process. Keywords: Brain Tumor Segmentation, Morphological Operation, Active Contour, Boltzmann Monte Carlo Method, Magnetic Resonance Imaging

Image Segmentation based on Energy Fitting Models – A Review

As a result of changes in imaging technology, segmenting the area of interest (ROI) from medical images is an extremely important yet challenging task. It is still difficult for the global energy-based active contour model (ACM) to properly extract the ROI from medical images, despite the fact that many techniques based on the local region-based active contour model have been proposed to deal with intensity inhomogeneity. This brief study aims to assess the performance of current techniques that have been published in the recent years and have been used to image segmentation. The methods under consideration include the various energy fitting models that have been created to drive the active contour are highlighted in this review study. Each model was examined against a medical image, an MRI brain image, and an image that was not taken by a medical professional. According to the results of the comparison study, it can be determined which technique is better appropriate for image segmentation even when there is intensity inhomogeneity in the images.

Saliency-based variational active contour model for image with intensity inhomogeneity

<span>Variational active contour model (ACM) is used to segment or subdivide an image into the desired object. This segmentation technique in region-based ACM can be divided into two classes: global segmentation and selective segmentation. Selective segmentation, in which only a particular desired object is segmented from an input image, is preferable to the global model because the selective segmentation model proves to be very useful, especially in medical image analysis. However, when it comes to segmenting an image with inhomogeneous intensity, these models seem to give unsatisfactory results. In this paper, we propose a new variational selective ACM mainly used for segmentation of images with inhomogeneous intensity, by incorporating saliency image map and local image fitting ideas. In addition, the euler-lagrange equation (EL) was provided to solve the proposed model. A total of thirty sets of medical images were used to test the model. Numerical results show that the suggested model outperforms other existing models, with the hausdorff distance of the proposed model being 47.78% less than the competing model, and the dice and jaccard values being around 17.54% and 33.65% higher, respectively, than the competing model.</span>

Bias field correction-based active contour model for region of interest extraction in digital image

The region-based Active Contour Model (ACM) is a widely known variational segmentation model for extracting or segmenting a digital image into numerous sections for further analysis. Distinguishing between global and specific segmentation models within this paradigm is possible. The global segmentation model is incapable of selectively segmenting the region of interest (ROI) from the input image, which leads to an over-segmented problem. A variety of models have been devised to address the task of selective segmentation, which involves the extraction of the boundary of a particular region of interest (ROI) inside a digital image. The Primal Dual Selective Segmentation (PDSS) model has been recently introduced and exhibits significant potential in terms of accuracy. Nevertheless, the presence of intensity inhomogeneity in digital images disrupts the precision and localisation of target regions of segmentation. Therefore, it is important to take into account bias field adjustment, also known as correction for intensity inhomogeneity. So, this study came up with a new selective segmentation model called the Selective Segmentation with Bias Field Correction (SSBF) model by combining the idea of the existing PDSS model with the level set-based bias field correction technique. To solve the proposed SSBF model, we first derived the Euler-Lagrange (EL) equation and solved it in MATLAB software. The Intersection over Union (IOU) coefficient, also known as the Dice (DSC) and Jaccard (JSC) similarity metrics, evaluated the proposed model's accuracy. Experimental results demonstrate that the JSC and DSC values of the proposed model were 13.4% and 7.2% higher, respectively, than the competing model.

An overview of intelligent image segmentation using active contour models

The active contour model (ACM) approach in image segmentation is regarded as a research hotspot in the area of computer vision, which is widely applied in different kinds of applications in practice, such as medical image processing. The essence of ACM is to make use ofuse an enclosed and smooth curve to signify the target boundary, which is usually accomplished by minimizing the associated energy function by means ofthrough the standard descent method. This paper presents an overview of ACMs for handling image segmentation problems in various fields. It begins with an introduction briefly reviewing different ACMs with their pros and cons. Then, some basic knowledge in of the theory of ACMs is explained, and several popular ACMs in terms of three categories, including region-based ACMs, edge-based ACMs, and hybrid ACMs, are detailedly reviewed with their advantages and disadvantages. After that, twelve ACMs are chosen from the literature to conduct three sets of segmentation experiments to segment different kinds of images, and compare the segmentation efficiency and accuracy with different methods. Next, two deep learning-based algorithms are implemented to segment different types of images to compare segmentation results with several ACMs. Experimental results confirm some useful conclusions about their sharing strengths and weaknesses. Lastly, this paper points out some promising research directions that need to be further studied in the future.

Malignant melanoma diagnosis applying a machine learning method based on the combination of nonlinear and texture features

Skin cancer affects people of all skin tones, including those with darker complexions. Melanomas are known as malignant tumors of skin cancer, resulting in an adverse prognosis, responsible for most deaths relating to skin cancer. Early diagnosis and treatment of skin cancer from dermoscopic images can significantly reduce mortality and save lives. In this paper, Computer-Aided Diagnosis (CAD) system based on machine learning algorithms is provided to classify various skin cancer types. The proposed method uses the Online Region-based Active Contour Model (ORACM) with a new binary level set equation and regularization operation to extract skin lesions' Region of Interest (ROI). Additionally, various combinations of different textures and nonlinear features are extracted for the ROI to show the multiple aspects of skin lesions. Several metaheuristic optimization algorithms are used to remove redundant or irrelevant features and reduce the feature space dimension. These are applied to the combination of the extracted features in which, the Non-dominated Sorting Genetic Algorithm (NSGA II) as a multi-objective optimization algorithm has the best performance. Furthermore, various machine learning algorithms including K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Fitting neural network (Fit net), Feed-Forward neural network (FF net), and Pattern recognition network (Pat net) are employed for the classification. In this paper, the best-obtained evaluation parameters based on fivefold cross-validation belong to the combination of selected nonlinear indices, texture, and GLCM features with an accuracy: 92.24 %, specificity: 100 %, and sensitivity: 100 %, resulting through NSGA II and applying the pattern net classifier. Besides, the comparison between this paper's experimental results and other similar works demonstrates the proposed method's efficiency.

Complete fully automatic detection, segmentation and 3D reconstruction of tumor volume for non-small cell lung cancer using YOLOv4 and region-based active contour model

We aim to develop a fully automatic system that will detect, segment and accurately reconstruct non-small cell lung cancer tumors into space using YOLOv4 and region-based active contour model. The system consists of two main sections which are detection and volumetric rendering. The detection section is composed of image enhancement, augmentation, labeling and localization while the volumetric rendering is mainly image filtering, tumor extraction, region-based active contour and 3D reconstruction. In this method the images are enhanced to eliminate noise before augmentation which is intended to multiply and diversify the image data. Labeling was then carried out in order to create a solid learning foundation for the localization model. Images with localized tumors were passed through smoothing filters and then clustered to extract tumor masks. Lastly contour information was obtained to render the volumetric tumor. The designed system displays a strong detection performance with a precision of 96.57%, sensitivity and F 1 score of 97.02% and 96.79% respectively at a detection speed of 34 fps, prediction time per image of 21.38 ms. The system segmentation validation achieved a dice score coefficient of 92.19 % on tumor extraction. A 99.74 % accuracy was obtained during the verification of the method’s volumetric rendering using a 3D printed image of the rendered tumor. The rendering of the volumetric tumor was obtained at an average time of 11 s. This system shows a strong performance and reliability due to its ability to detect, segment and reconstruct a volumetric tumor into space with high confidence.

Driver drowsiness detection system based on infinite feature selection algorithm and support vector machine

In recent times, driver drowsiness is one of the major reasons for road accidents that leads to severe physical injuries, deaths and significant economic losses. Hence, the existing driver drowsiness detection systems require a countermeasure device for the prevention of sleepiness related accident. This research paper aims to perform drowsiness detection with the help of driver’s eye state, head pose, and mouth state information. Initially, the input data were collected from the public drowsy driver database. Then, the Camera Response Model (CRM) was applied to improve the quality of collected data. Also, viola-jones, and Kanade-Lucas-Tomasi (KLT) approaches were used to detect and track the driver’s face, eye, and mouth regions from the input video. In this research study, Online Region-Based Active Contour Model (ORACM) algorithm was used to segment the driver’s mouth region in order to obtain the threshold value. Successively, feature extraction; Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) was applied to extract the features from the detected eye region. The extracted features of the eye region were combined with the threshold value of mouth region and head pose angle. After extracting the feature vectors, infinite approach was utilized to choose the relevant feature vectors. Finally, the selected features were classified using Support Vector Machine (SVM) for classifying the stages of drowsiness detection. Simulation outcome illustrated that the proposed system increased the classification accuracy up to 5.52% as related to hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM).

Robust region-based active contour models via local statistical similarity and local similarity factor for intensity inhomogeneity and high noise image segmentation

<p style='text-indent:20px;'>In this paper, we design a novel variational segmentation method for two types of segmentation problems, namely, global segmentation (all objects /features in a given image are aimed to be segmented) and selective/ interactive segmentation (an objects /feature of interest in a given image is aimed to be segmented) for inhomogeneous and severe additive noisy images. The proposed segmentation models implement a local denoising constraint, capable to tackle efficiently noise/outliers and coping with intensity inhomogeneity issues, combined with local similarity factor based on spatial distances and intensity differences in the local region that guides accurately the level set function to distinguish between outliers and minute important details. Furthermore, to exhibit the accuracy of the proposed models, an experimental comparison is inducted and shown comparisons with state-of-art models on synthetic images, outdoor images, and medical images.</p>

Segmentation of male pelvic organs on computed tomography with a deep neural network fine-tuned by a level-set method

Computed Tomography (CT) imaging is used in Radiation Therapy planning, where the treatment is carefully tailored to each patient in order to maximize radiation dose to the target while decreasing adverse effects to nearby healthy tissues. A crucial step in this process is manual organ contouring, which if performed automatically could considerably decrease the time to starting treatment and improve outcomes. Computerized segmentation of male pelvic organs has been studied for decades and deep learning models have brought considerable advances to the field, but improvements are still demanded. A two-step framework for automatic segmentation of the prostate, bladder and rectum is presented: a convolutional neural network enhanced with attention gates performs an initial segmentation, followed by a region-based active contour model to fine-tune the segmentations to each patient's specific anatomy. The framework was evaluated on a large collection of planning CTs of patients who had Radiation Therapy for prostate cancer.The Surface Dice Coefficient improved from 79.41 to 81.00% on segmentation of the prostate, 94.03–95.36% on the bladder and 82.17–83.68% on the rectum, comparing the proposed framework with the baseline convolutional neural network. This study shows that traditional image segmentation algorithms can help improve the immense gains that deep learning models have brought to the medical imaging segmentation field.

Superpixel-based active contour model via a local similarity factor and saliency

The region-based active contour models could present difficulties because of undesired initial contour, noise distribution and image weak edges. In order to overcome the above problems, this paper proposes a superpixel-based via a local similarity factor and saliency (SLSFS). Firstly, the initial contour is generated by combining super-pixel and fuzzy c-means clustering. Secondly, the difference between local space and local intensity is used to improve the segmentation accuracy under noise. Finally, the weak edge information is protected by improved saliency detection. In addition, a gradient similarity constraint is used to remove the redundant regions. SLSFS model can generate adaptive initial contour around the target, and protect the weak edge information of the target on the premise of ensuring certain noise robustness. Experiments show that the average dice of SLSFS is 14% higher than that of the optimal comparison model and 19% on gray images.

Morphological active contour model for automatic brain tumor extraction from multimodal magnetic resonance images

BackgroundBrain tumor extraction from magnetic resonance (MR) images is challenging due to variations in the location, shape, size and intensity of tumors. Manual delineation of brain tumors from MR images is time-consuming and prone to human errors. MethodIn this paper, we present a method for automatic tumor extraction from multimodal MR images. Brain tumors are first detected using k-means clustering. A morphological region-based active contour model is then used for tumor extraction using an initial contour defined based on the boundary of the detected brain tumor regions. The contour evolution for tumor extraction was performed using successive application of morphological operators. In our model, a Gaussian distribution was used to model local image intensities. The spatial correlation between neighboring voxels was also modeled using Markov random field. ResultsThe proposed method was evaluated on BraTS 2013 dataset including patients with high-grade and low-grade tumors. In comparison with other active contour based methods, the proposed method yielded better performance on tumor segmentation with mean Dice similarity coefficients of 0.9179 ( ± 0.025) and 0.8910 ( ± 0.042) obtained on high-grade and low-grade tumors, respectively. ConclusionThe proposed method achieved higher accuracies for brain tumor extraction in comparison to other contour-based methods.

Computer-Aided Diagnosis System for Diagnosis of Cavitary and Miliary Tuberculosis Using Improved Artificial Bee Colony Optimization

A framework for Computer-Aided Diagnosis (CAD) to diagnose Cavitary TB and Miliary TB from chest Computed Tomography (CT) slices has been designed and implemented. The lung tissues from the CT slices are segmented using region-based Active Contour Model (ACM) and the Region of Interests (ROIs) labelled by an expert radiologist are extracted. Features based on shape and texture are extracted from each ROI. A wrapper-based Improved Artificial Bee Colony Optimization (I-ABCO) algorithm with the accuracy of the Support Vector Machine (SVM) classifier as the fitness function is used to select the optimal subset of features. The search process of I-ABCO is improved using two evaluation functions, namely, rough dependency measure (RDM) and mutual information (MI), to promote better exploitation of the search space. The selected features are used to train the Radial Basis Function Neural Network (RBFNN) classifier, using ten-fold cross validation and the performance is evaluated. Experimentation has been performed on CT slices using two datasets: Tuberculosis dataset and Lung Image Database Consortium-Image Database Resource Initiative (LIDC-IDRI) dataset. The accuracy of the CAD systems using I-ABCO with MI and I-ABCO with RDM for both datasets are (88.34%, 92.63%) and (87.32%, 90.17%), respectively. The CAD system using the basic Artificial Bee Colony Optimization (ABCO) algorithm for feature selection is also experimented with the same datasets and an accuracy of (85.68%, 88%) is achieved. The performance of the proposed algorithms outperforms the ABCO algorithm in diagnostic accuracy, which ensures that selecting the optimal feature subset efficiently has an impact on the classification accuracy.

A fast region-based active contour for non-rigid object tracking and its shape retrieval.

Conventional tracking approaches track objects using a rectangle bounding box. Gait, gesture and many medical analyses require non-rigid shape extraction. A non-rigid object tracking is more difficult because it needs more accurate object shape and background separation in contrast to rigid bounding boxes. Active contour plays a vital role in the retrieval of image shape. However, the large computation time involved in contour tracing makes its use challenging in video processing. This paper proposes a new formation of the region-based active contour model (ACM) using a mean-shift tracker for video object tracking and its shape retrieval. The removal of re-initialization and fast deformation of the contour is proposed to retrieve the shape of the desired object. A contour model is further modified using a mean-shift tracker to track and retrieve shape simultaneously. The experimental results and their comparative analysis concludes that the proposed contour-based tracking succeed to track and retrieve the shape of the object with 71.86% accuracy. The contour-based mean-shift tracker resolves the scale-orientation selection problem in non-rigid object tracking, and resolves the weakness of the erroneous localization of the object in the frame by the tracker.

Active contour model with adaptive weighted function for robust image segmentation under biased conditions

The segmentation of images under biased conditions such as low contrast, high-intensity inhomogeneity, and noise is a challenge for any image segmentation model. The ideal image segmentation model must be capable of segmenting images with maximum accuracy and a minimum false-positive rate under biased conditions. In this paper, we propose a region-based active contour model (ACM), called global signed pressure and K-means clustering based on local correntropy with the exponential family (GSLCE), to address segmentation challenges under biased conditions. An adaptive weighted function is formulated based on the global and local image differences such that a single weighted function can drive both the global and local intensities. Further, the Riemannian steepest descent method is used for convergence of the proposed GSLCE energy function, and a Gaussian kernel is applied for spatial smoothing to obviate the computationally expensive level-set re-initialization. The experimental results show that, compared with state-of-the-art ACMs, the proposed GSLCE model obtained the best visual image segmentation results for synthetic and real images under biased conditions. Further, the qualitative and quantitative experimental results validate that the proposed model outperforms the state-of-the-art ACMs by yielding higher values of performance metrics. Moreover, the proposed GSLCE model requires substantially less processing time compared to the state-of-the-art ACMs.

Localised edge‐region‐based active contour for medical image segmentation

Segmenting the region of interest (ROI) from medical images is a fundamental but challenging task due to the illumination change and imaging devices. Although many models based on the local region-based active contour model (LR-ACM) are proposed to deal with intensity inhomogeneity, it is still difficult for the global energy-based ACM with local image information to accurately extract the ROI from medical images. To solve this problem, this study proposes a novel localised ACM by constructing the gradient information based on the probability scores from the fuzzy k-nearest neighbour classifier. Different from the traditional LR-ACMs, our model is based on local rather than global image statistics, where a probability score-based edge detector is directly used for gradient information. The energy functional consists of localised region energy and an edge energy. By introducing a local characteristics function, the localised region energy with the probability-score-based edge information is formulated, which can make the evolution curve stop on the exact boundaries of ROI. The edge energy including the regularisation and the penalty terms is used to avoid the reinitialisation process and smooth the evolution curve during evolution. To maintain the signed distance property of the evolution curve, a novel potential function in the penalty term is designed, which can consistently control the diffusion direction of the evolution curve. Experiments on the medical images including the cardiac magnetic resonance imaging and the 3DIRCADb databases demonstrate that the proposed model is more robust and accurate to extract the ROI than the popular localised and region-based ACMs. The code is available at: https://github.com/HuaxiangLiu/Localized_ERAC/.

Robust pixel-wise concrete crack segmentation and properties retrieval using image patches

Crack identification is an essential task in periodic inspection and maintenance of buildings. The application of deep learning based computer vision techniques is increasingly popular, but suffer from challenges of insufficient performance on highly diverse field inspection scenarios as well as a requirement for large amounts of labeled training data. To address these limitations, this paper proposes a robust crack segmentation approach using image patches to detect and support further accurate retrieval of crack properties for integrity assessment. In the proposed approach, a local region-based active contour model is integrated with a convolution neural network and several post-processing morphological operations to derive a segmented crack map. Experimental validation shows significant improvement in terms of accuracy and robustness over previous work. Data labeling requirement is also comparatively lower. This paper enhances the current concrete inspection process, and lays the foundation for more data efficient methods of crack segmentation to be explored.

A Hybrid Segmentation Approach of Brain Magnetic Resonance Imaging Using Region-Based Active Contour with a Similarity Factor and Multi-Population Genetic Algorithm

The performance of medical image segmentation is generally affected by the parameters of the adopted method and noise. To overcome these issues we introduce in this paper a novel segmentation approach of brain MRI using a region based-active contour model and evolutionary algorithm and without performing any pre-processing step. Our main objective is to accurately extract edges, resolve the intensity inhomogeneity problem and overcome manifestations of noise. Chan and Vese model was adopted by introducing a local similarity factor based on Bilateral filter principle (LSFB). The adjustment of our functional energy parameters was achieved using a multi-population genetic algorithm (MPGA) which can display better search performance than serial single population models, in terms of the quality of the solution found, effort and processing time. We selected Brain MRI from Oasis and Brainweb data base with different noise type. The initialization of the active contour was totally random. A comparison of segmentation results with Chan and Vese model and active contour model with a locally computed signed pressure force (SPF) of Akram and his team reveals a clear efficiency of our proposed approach.

A hybrid active contour model for ultrasound image segmentation

Abundant noise, low contrast, intensity heterogeneity, shadows, and blurry boundaries exist in most medical images, especially for 2D ultrasound (US) image. In this paper, we propose a semiautomatic hybrid active contour model for 2D US image segmentation. The proposed method mainly uses a local bias correction function and probability score. It is well known that most region-based active contour models are based on the assumption of intensity homogeneity. It is very difficult to define a region descriptor for US images with intensity heterogeneity. Here, a bias field can account for the intensity heterogeneity of the US image. Therefore, the proposed local bias correction function is considered to integrate with respect to the neighborhood center of the US image. Besides, to segment complex ultrasound images more accurately, a probability score is constructed from the edge-based operator. Based on the estimation of the bias field and an interleaved process of probability score, minimization of the proposed energy functional is achieved. The proposed method is validated on synthetic images and real US images, with satisfactory performance in the presence of noise, intensity heterogeneity, and blurry boundaries.

Saliency-Driven Active Contour Model for Image Segmentation

Active contour models have achieved prominent success in the area of image segmentation, allowing complex objects to be segmented from the background for further analysis. Existing models can be divided into region-based active contour models and edge-based active contour models. However, both models use direct image data to achieve segmentation and face many challenging problems in terms of the initial contour position, noise sensitivity, local minima and inefficiency owing to the in-homogeneity of image intensities. The saliency map of an image changes the image representation, making it more visual and meaningful. In this study, we propose a novel model that uses the advantages of a saliency map with local image information (LIF) and overcomes the drawbacks of previous models. The proposed model is driven by a saliency map of an image and the local image information to enhance the progress of the active contour models. In this model, the saliency map of an image is first computed to find the saliency driven local fitting energy. Then, the saliency-driven local fitting energy is combined with the LIF model, resulting in a final novel energy functional. This final energy functional is formulated through a level set formulation, and regulation terms are added to evolve the contour more precisely across the object boundaries. The quality of the proposed method was verified on different synthetic images, real images and publicly available datasets, including medical images. The image segmentation results, and quantitative comparisons confirmed the contour initialization independence, noise insensitivity, and superior segmentation accuracy of the proposed model in comparison to the other segmentation models.