Deformable Contour Model Research Articles

An energy efficient approach of deep learning based soft sensor for air quality management

Monitoring environmental pollution is emerging as a recent study area especially in urban and highly polluted industrial areas. This field deploys many chemical analysis models and data driven models through soft sensors. But bio indicators are a more feasible, cost effective and precise monitoring model, which are rarely explored. This paper is based on growth monitoring of Cryptogams, a bio indicator which is capable of directly reflecting the pollution levels in the region of growth. A novel enhanced and energy efficient deformable active contour model is introduced to trace the development of transplanted Cryptogams at various sites with diverse pollution levels. The vegetative development of Cryptogams is monitored for duration of two weeks. The proposed energy efficient contour tracing model proves its superiority in precise tracing of the Cryptogam development, thus aiding in accurate pollution monitoring. The VGG 16 architecture built using deep convolutional neural network by constructing stacks of filters. VGG 16 architecture showed high performance when compared with other existing models. The accuracy is compared with the Ant colony optimization using GVF.

Research on contour feature extraction method of multiple sports images based on nonlinear mechanics

Abstract This article solves the issue of long extraction time and low extraction accuracy in traditional moving image contour feature extraction methods. Here authors have explored deformable active contour model to research the image processing technology in scientific research and the application of multiple sports and the method. A B-spline active contour model based on dynamic programming method is proposed in this article. This article proposes a method of using it to face image processing and extracting computed tomography (CT) image data to establish a three-dimensional model. The Lyapunov exponent, correlation dimension and approximate entropy of the nonlinear dynamics algorithm were used to extract the features of eight types of motor imagination electroencephalogram (EEG) signals. The results show that the success rate of pose reconstruction is more than 97% when the contour extraction quality is relatively ideal. The method is also robust to image noise, and the success rate of pose reconstruction can reach 94% when the video image has large noise. The execution efficiency is sub-linear, which can basically meet the requirements of real-time processing in video-based human posture reconstruction. The proposed method has a low error rate in the calculation of curvature features, effectively reduces the time for extracting contour features of moving images, and improves the accuracy of feature information extraction.

Segmentation of ultrasound image sequences by combing a novel deep siamese network with a deformable contour model

Segmentation of ultrasound image sequences by combing a novel deep siamese network with a deformable contour model

Automated 3D geometry segmentation of the healthy and diseased carotid artery in free-hand, probe tracked ultrasound images.

PurposeRupture of an arterosclerotic plaque in the carotid artery is a major cause of stroke. Biomechanical analysis of plaques is under development aiming to aid the clinician in the assessment of plaque vulnerability. Patient‐specific three‐dimensional (3D) geometry assessment of the carotid artery, including the bifurcation, is required as input for these biomechanical models. This requires a high‐resolution, 3D, noninvasive imaging modality such as ultrasound (US). In this study, a high‐resolution two‐dimensional (2D) linear array in combination with a magnetic probe tracking device and automatic segmentation method was used to assess the geometry of the carotid artery. The advantages of using this system over a 3D ultrasound probe are its higher resolution (spatial and temporal) and its larger field of view.MethodsA slow sweep (v = ± 5 mm/s) was made over the subject’s neck so that the full geometry of the bifurcated geometry of the carotid artery is captured. An automated segmentation pipeline was developed. First, the Star‐Kalman method was used to approximate the center and size of the vessels for every frame. Images were filtered with a Gaussian high‐pass filter before conversion into the 2D monogenic signals, and multiscale asymmetry features were extracted from these data, enhancing low lateral wall‐lumen contrast. These images, in combination with the initial ellipse contours, were used for an active deformable contour model to segment the vessel lumen. To segment the lumen–plaque boundary, Otsu’s automatic thresholding method was used. Distension of the wall due to the change in blood pressure was removed using a filter approach. Finally, the contours were converted into a 3D hexahedral mesh for a patient‐specific solid mechanics model of the complete arterial wall.ResultsThe method was tested on 19 healthy volunteers and on 3 patients. The results were compared to manual segmentation performed by three experienced observers. Results showed an average Hausdorff distance of 0.86 mm and an average similarity index of 0.91 for the common carotid artery (CCA) and 0.88 for the internal and external carotid artery. For the total algorithm, the success rate was 89%, in 4 out of 38 datasets the ICA and ECA were not sufficient visible in the US images. Accurate 3D hexahedral meshes were successfully generated from the segmented images .ConclusionsWith this method, a subject‐specific biomechanical model can be constructed directly from a hand‐held 2D US measurement, within 10 min, with a minimal user input. The performance of the proposed segmentation algorithm is comparable to or better than algorithms previously described in literature. Moreover, the algorithm is able to segment the CCA, ICA, and ECA including the carotid bifurcation in transverse B‐mode images in both healthy and diseased arteries.

Medial axis segmentation of cranial nerves using shape statistics-aware discrete deformable models.

We propose a segmentation methodology for brainstem cranial nerves using statistical shape model (SSM)-based deformable 3D contours from T2 MR images. We create shape models for ten pairs of cranial nerves. High-resolution T2 MR images are segmented for nerve centerline using a 1-Simplex discrete deformable 3D contour model. These segmented centerlines comprise training datasets for the shape model. Point correspondence for the training dataset is performed using an entropy-based energy minimization framework applied to particles located on the centerline curve. The shape information is incorporated into the 1-Simplex model by introducing a shape-based internal force, making the deformation stable against low resolution and image artifacts. The proposed method is validated through extensive experiments using both synthetic and patient MRI data. The robustness and stability of the proposed method are experimented using synthetic datasets. SSMs are constructed independently for ten pairs (CNIII-CNXII) of brainstem cranial nerves using ten non-pathological image datasets of the brainstem. The constructed ten SSMs are assessed in terms of compactness, specificity and generality. In order to quantify the error distances between segmented results and ground truths, two metrics are used: mean absolute shape distance (MASD) and Hausdorff distance (HD). MASD error using the proposed shape model is 0.19 ± 0.13 (mean ± std. deviation) mm and HD is 0.21mm which are sub-voxel accuracy given the input image resolution. This paper described a probabilistic digital atlas of the ten brainstem-attached cranial nerve pairs by incorporating a statistical shape model with the 1-Simplex deformable contour. The integration of shape information as a priori knowledge results in robust and accurate centerline segmentations from even low-resolution MRI data, which is essential in neurosurgical planning and simulations for accurate and robust 3D patient-specific models of critical tissues including cranial nerves.

An approach to automated retinal layer segmentation in SDOCT images

The optical coherence tomography (OCT) imaging technique is a precise and well-known approach to the diagnosis of retinal layers. The pathological changes in the retina challenge the accuracy of computational segmentation approaches in the evaluation and identification of defects in the boundary layer. The layer segmentations and boundary detections are distorted by noise in the computation. In this work, we propose a fully automated segmentation algorithm using a denoising technique called the Boisterous Obscure Ratio (BOR) for human and mammal retina. First, the BOR is derived using noise detection, i.e., from the Robust Outlyingness Ratio (ROR). It is then applied to edge and layer detection using a gradient-based deformable contour model. Second, the image is vectorised. In this method, a cluster and column intensity grid is applied to identify and determine the unsegmented layers. Using the layer intensity and a region growth seed point algorithm, segmentation of the prominent layers is achieved. The automatic BOR method is an image segmentation process that determines the eight layers in retinal spectral domain optical coherence tomography images. The highlight of the BOR method is that the results produced are accurate, highly substantial, and effective, although time consuming.

MRI-Based Medial Axis Extraction and Boundary Segmentation of Cranial Nerves Through Discrete Deformable 3D Contour and Surface Models

This paper presents a segmentation technique to identify the medial axis and the boundary of cranial nerves. We utilize a 3-D deformable one-simplex discrete contour model to extract the medial axis of each cranial nerve. This contour model represents a collection of two-connected vertices linked by edges, where vertex position is determined by a Newtonian expression for vertex kinematics featuring internal and external forces, the latter of which include attractive forces toward the nerve medial axis. We exploit multiscale vesselness filtering and minimal path techniques in the medial axis extraction method, which also computes a radius estimate along the path. Once we have the medial axis and the radius function of a nerve, we identify the nerve surface using a two-simplex deformable model, which expands radially and can accommodate any nerve shape. As a result, the method proposed here combines the benefits of explicit contour and surface models, while also achieving a cornerstone for future work that will emphasize shape statistics, static collision with other critical structures, and tree-shape analysis.

Application of centerline detection and deformable contours algorithms to segmenting the carotid lumen

The main contribution of this article is to evaluate the utility of different state-of-the-art deformable contour models for segmenting carotid lumen walls from computed tomography angiography images. We have also proposed and tested a new tracking-based lumen segmentation method based on our evaluation results. The deformable contour algorithm (snake) is used to detect the outer wall of the vessel. We have examined four different snakes: with a balloon, distance, and a gradient vector flow force and the method of active contours without edges. The algorithms were evaluated on a set of 32 artery lumens—16 from the common carotid artery (CCA)-the internal carotid artery section and 16 from the CCA-the external carotid artery section—in order to find the optimum deformable contour model for this task. Later, we evaluated different values of energy terms in the method of active contours without edges, which turned out to be the best for our dataset, in order to find the optimal values for this particular segmentation task. The choice of particular weights in the energy term was evaluated statistically. The final Dice’s coefficient at the level of 0.939±0.049 puts our algorithm among the best state-of-the-art methods for these solutions.

Deformable Contour-Based Maneuvering Flying Vehicle Tracking in Color Video Sequences

This paper presents a new method for the tracking of maneuvering flying vehicles using a deformable contour model in color video sequences. The proposed approach concentrates on targets with maneuvering motion in sky, which involves fundamental aspect change stemmed from 3D rotation of the target or video camera. In order to segment and track the aircraft in a video, at first, the target contour is initialized manually in a key frame, and then it is matched and tracked automatically in the subsequent frames. Generally active contour models employ a set of energy functions based on edge, texture, color, and shape features. Afterwards, objective function is minimized iteratively to track the target contour. In the proposed algorithm, we employ game of life cellular automaton to manage snake pixels’ (snaxels’) deformation in each epoch of minimization procedure. Furthermore, to cope with the large aspect change of aircraft, a Gaussian model has been taken into account to represent the target color in RGB space. To compensate for changes in luminance and chrominance ingredients of the target, the prior distribution function is dynamically updated during tracking. The proposed algorithm is evaluated using the collected dataset, and the expected probability of tracking error is calculated. Experimental results show positive results for the proposed algorithm.

A New Snake Model for Pupil Localization Using Orthogonal Polynomials Transform

 Abstract—In this paper a new approach for representing and evolving deformable contour or snake model to accurately detect pupil boundary for improving the performance of iris recognition systems is proposed. The proposed model extracts the boundary with computationally efficient Laplacian of Guassian (LoG) mask. The LoG mask is obtained from the set of polynomial basis operators derived from Orthogonal Polynomials Transform. Two types of controlling force models, introduced as internal and external forces are designed to properly activate the contour and locate it over the pupil boundary. The internal forces are designed to smooth the contour as well as to keep it close to a boundary by pushing the contour vertices towards the boundary of interest. The external forces are responsible for pulling the contour vertices towards the pupil boundary and the contour is deformed into a new shape in response to the effective force. A revised contour estimate of the selected boundary based on the execution of the contour tracing algorithm is generated. The results are highly encouraging to capture the contour of non-circular shaped pupil of iris. Experimental results on the CASIA v1.0 iris database demonstrate that the proposed snake model outperforms in both accuracy and speed.

Harris function based active contour external force for image segmentation

Deformable active contour (snake) models are efficient tools for object boundary detection. Existing alterations of the traditional gradient vector flow (GVF) model have reduced sensitivity to noise, parameters and initial location, but high curvatures and noisy, weakly contrasted boundaries cause difficulties for them.This paper introduces two Harris based parametric snake models, Harris based gradient vector flow (HGVF) and Harris based vector field convolution (HVFC), which use the curvature-sensitive Harris matrix to achieve a balanced, twin-functionality (corner and edge) feature map. To avoid initial location sensitivity, starting contour is defined as the convex hull of the most attractive points of the map. In the experimental part we compared our methods to the traditional external energy-inspired state-of-the-art GVF and VFC; the recently published parametric decoupled active contour (DAC) and the non-parametric Chan–Vese (ACWE) techniques. Results show that our methods outperform the classical approaches, when tested on images with high curvature, noisy boundaries.

Reproducibility of Deriving Parameters of AAA Rupture Risk From Patient-Specific 3D Finite Element Models

To assess the reproducibility of estimating biomechanical parameters of abdominal aortic aneurysms (AAA) based on finite element (FE) computations derived from a commercially available, semiautomatic vascular analyzer that reconstructs computed tomographic angiography (CTA) data into FE models. The CTA data from 10 consecutive male patients (mean age 74 years, range 63-87) with a fusiform infrarenal AAA >5 cm in diameter were used for this study, along with the CTA scans from 4 individuals without aortic disease. Three different observers used semiautomatic reconstruction software to create deformable contour models from axial CT scans. These 3-dimensional FE models captured the aortic wall and thrombus tissue using isotropic finite strain constitutive modeling. Geometric (maximum diameter and volume measurements based on an anatomical centerline) and biomechanical determinants [aneurysm peak wall stress (PWS) and the peak wall rupture risk (PWRR) index] were then calculated from the FE models. The determinations were made 5 times for each anonymized dataset presented for analysis in random order (5-fold measurements for 14 datasets produced 210 measurements from the 3 observers). Inter- and intraobserver variability were assessed by calculating the coefficient of variation of these repeated measures. The methodological variations were expressed with the intraclass correlation coefficient (ICC) and Bland-Altman plots. The median segmentation time was < 1 hour (mean 39.2 minutes, range 25-48) for datasets from the AAA patients; for the healthy individuals, segmentation times were considerably shorter (median 8.7 minutes, range 4-15). Intraobserver reproducibility was high, as represented by a CV <3% for the diameter measurement and < 5.5% for volume, PWS, and the PWRR index. The ICC was 0.97 (range 0.95-0.98) for diameter and 0.98 (range 0.97-0.99) for volume; for PWS and the PWRR index, the ICCs were equal at 0.98 (range 0.97-0.99). The reproducibility of volume and maximum diameter measurements in infrarenal AAAs with FE analysis is high. With the model used in this semiautomatic reconstruction software, wall stress analysis can be achieved with high agreement among observers and in serial measurements by a single observer.

Automatic Delineation of the Diaphragm in Computed Tomographic Images

Segmentation of the internal organs in medical images is a difficult task. By incorporating a priori information regarding specific organs of interest, results of segmentation may be improved. Landmarking (i.e., identifying stable structures to aid in gaining more knowledge concerning contiguous structures) is a promising segmentation method. Specifically, segmentation of the diaphragm may help in limiting the scope of segmentation methods to the abdominal cavity; the diaphragm may also serve as a stable landmark for identifying internal organs, such as the liver, the spleen, and the heart. A method to delineate the diaphragm is proposed in the present work. The method is based upon segmentation of the lungs, identification of the lower surface of the lungs as an initial representation of the diaphragm, and the application of least-squares modeling and deformable contour models to obtain the final segmentation of the diaphragm. The proposed procedure was applied to nine X-ray computed tomographic (CT) exams of four pediatric patients with neuroblastoma. The results were evaluated against the boundaries of the diaphragm as identified independently by a radiologist. Good agreement was observed between the results of segmentation and the reference contours drawn by the radiologist, with an average mean distance to the closest point of 5.85 mm over a total of 73 CT slices including the diaphragm.

A Novel Clustering Method for Quick Partial Volume Estimation in MR Brain Images

Automated brain MR image segmentation is a challenging pattern recognition problem that received significant attention lately. The most popular solutions involve fuzzy c-means (FCM) or similar clustering mechanisms. Several improvements have been made to the standard FCM algorithm, in order to reduce its sensitivity to Gaussian, impulse, and intensity non-uniformity noises. This paper presents a modified FCM-based method that targets accurate and fast segmentation in case of mixed noises. The proposed method extracts a scalar feature value from the neighbourhood of each pixel, using a context dependent filtering technique that deals with both spatial and grey level distances. These features are clustered afterwards by the histogram-based approach of the enhanced FCM algorithm. Results were evaluated based on synthetic phantoms and real MR images. Test experiments revealed that the proposed method provides better results compared to other reported FCM-based techniques. The time complexity of the proposed method is situated well below the traditional FCM algorithm. The achieved segmentation and the obtained fuzzy membership values represent excellent support for deformable contour model based cortical surface reconstruction methods.

Visualising complex morphology of fatigue cracks in voxel based 3D datasets

Fatigue cracks are usually characterised by surface sensitive techniques after specimen failure. High resolution micro computed tomography (μCT) based on synchrotron radiation allows the non-destructive visualisation of crack morphology and evaluation of fatigue crack formation/propagation before specimen failure. The visualisation of the complex fracture morphology with characteristic features out of the acquired set of slices is, however, challenging. To obtain a reasonable estimate, two approaches are generally used: the determination of mass centre points in the hollow space and the minimum intensity search in parallel projections. The more sophisticated approach using the elastically deformable contour model, the physical analogy of a rubber band, termed snakes, gives rise to crack morphologies with much less artefacts. The approach was used in the present study for the characterisation of fatigue cracks in poly(methylmethacrylate) (PMMA) and a dental ceramic. The search for the appropriate snake parameters works much better for homogeneous materials, here PMMA, than for inhomogeneous materials, here a dental ceramic. For the ceramic, the regions where the snakes approach provided reasonable results were restricted. Combining μCT with sophisticated computer vision techniques enables the unique characterisation of cracks at the micrometre scale.

A semi‐automated line tracing technique for monitoring ice margins in Antarctic images

The current shape and rate of change of the margins of the Antarctic ice sheet are poorly known. Since polar regions are inhospitable, remotely sensed images provide an invaluable data source for studying the ice margin. These images can be examined by a human expert or processed automatically by a computer. This paper describes the design and implementation of a semi‐automated technique to trace ice margins in Synthetic Aperture Radar images. The technique is based on a deformable contour model derived from the Kass et al. active contour model and Lobregt and Viergever's discrete dynamic contour. The contour is initialized by the user, to approximate the margin, and the deformation process causes the contour to accurately mould itself to the shape of the margin. The technique has been tested on a number of different images, with acceptable results in most cases.

A Deformable Contour Based Approach for Hand Image Segmentation

In this paper we address the issue of hand contour segmentation from digital images using deformable contour models (snakes). We present a novel variation of the traditional snake solution, where additional nodes are inserted and redundant nodes are deleted to better describe the complexity of the extracted line. Candidate locations for node insertion and deletion are based on an analysis of the energy terms in the snake solution. This allows us to use more closely spaced nodes along the high curvature segments of a hand outline. This dynamic manipulation of the node number and spacing within a single snake allows us to better capture the geometry of the hand and accommodate its radiometric behavior. Here we present our approach, and some experimental results demonstrating its performance as a tool for hand contour segmentation in biometrics, medical imaging, and pattern recognition.

Détection des troubles de contractilité myocardique par suivi pariétal et régional en échocardiographie

In this paper, a method for the detection of myocardium contractility defect from transthoracic echocardiography is proposed. Speckle phenomenon is considered here as useful functional information and not only as a multiplicative noise. Its distribution and frequential characteristics are used to derive boundary and regional energy terms in order to track myocardium walls with deformable contour models. Moreover, ultrasound density is also estimated from speckle moments to calculate myocardial displacement field from the solution of an inverse continuity equation problem. The clinical feasibility of local and global indices and a prospective study for the multisite stimulation are presented.

Automated markerless extraction of walking people using deformable contour models

AbstractWe develop a new automated markerless motion capture system for the analysis of walking people. We employ global evidence gathering techniques guided by biomechanical analysis to robustly extract articulated motion. This forms a basis for new deformable contour models, using local image cues to capture shape and motion at a more detailed level. We extend the greedy snake formulation to include temporal constraints and occlusion modelling, increasing the capability of this technique when dealing with cluttered and self‐occluding extraction targets.This approach is evaluated on a large database of indoor and outdoor video data, demonstrating fast and autonomous motion capture for walking people. Copyright © 2004 John Wiley &amp; Sons, Ltd.

Mutual information in coupled multi-shape model for medical image segmentation

This paper presents extensions which improve the performance of the shape-based deformable active contour model presented earlier in [IEEE Conf. Comput. Vision Pattern Recog. 1 (2001) 463] for medical image segmentation. In contrast to that previous work, the segmentation framework that we present in this paper allows multiple shapes to be segmented simultaneously in a seamless fashion. To achieve this, multiple signed distance functions are employed as the implicit representations of the multiple shape classes within the image. A parametric model for this new representation is derived by applying principal component analysis to the collection of these multiple signed distance functions. By deriving a parametric model in this manner, we obtain a coupling between the multiple shapes within the image and hence effectively capture the co-variations among the different shapes. The parameters of the multi-shape model are then calculated to minimize a single mutual information-based cost criterion for image segmentation. The use of a single cost criterion further enhances the coupling between the multiple shapes as the deformation of any given shape depends, at all times, upon every other shape, regardless of their proximity. We found that this resulting algorithm is able to effectively utilize the co-dependencies among the different shapes to aid in the segmentation process. It is able to capture a wide range of shape variability despite being a parametric shape-model. And finally, the algorithm is robust to large amounts of additive noise. We demonstrate the utility of this segmentation framework by applying it to a medical application: the segmentation of the prostate gland, the rectum, and the internal obturator muscles for MR-guided prostate brachytherapy.