Contour Method Research Articles

A robust hybrid active contour model based on pre-fitting bias field correction for fast image segmentation

An array of existing active contour models is prone to suffering from the deficiencies of poor anti-noise ability, initialization sensitivity, and slow convergence. In order to handle these problems, a robust hybrid active contour method based on bias correction is proposed in this research paper The energy functional is formulated through incorporating the adaptive edge indicator function and level set formulation driven by bias field correction. The adaptive edge indicator function, which is formulated based on image gradient information, is utilized to detect object boundaries and accelerate the segmentation in the homogeneous region. The level set formulation is constructed based on an improved criterion function, in which bias field information is considered. Specifically, the bias field distribution is approximated through the local mean gray value algorithm as a prior. Moreover, a new regularized function is proposed so as to maintain the stability of curve evolution. The segmentation process is implemented by the optimized energy function and the novel regularized term. Compared to previous active contour models, the modified active contour method can yield more precise, stable, and efficient segmentation results on some challenging images.

Automatic ladybird beetle detection using deep-learning models.

Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird beetles in random environment images as the first stage towards an automated classification system. First, an image processing module composed of a saliency map representation, simple linear iterative clustering superpixels segmentation, and active contour methods allowed us to generate bounding boxes with possible ladybird beetles locations within an image. Subsequently, a deep convolutional neural network-based classifier selects only the bounding boxes with ladybird beetles as the final output. This method was validated on a 2, 300 ladybird beetle image data set from Ecuador and Colombia obtained from the iNaturalist project. The proposed approach achieved an accuracy score of 92% and an area under the receiver operating characteristic curve of 0.977 for the bounding box generation and classification tasks. These successful results enable the proposed detector as a valuable tool for helping specialists in the ladybird beetle detection problem.

Determination of the mechanical parameters of the microstructure of rockfill materials in triaxial compression DEM simulation

An approach is devised to determine the mechanical parameters of the microstructure of Dalian limestone rockfill material (DLRM) in triaxial compression DEM simulation. The parameters of the rockfill materials include the crushing strength parameters of the particles and the mechanical contact model parameters (mesoscopic parameters). The crushing strength parameters of the particles in the DEM simulation are determined by a series of laboratory single-particle crushing tests. Weibull statistics are applied to describe the tensile strengths of the DLRM particles, and the particle size has only a slight influence on the Weibull modulus m. The size effect of the characteristic strength of the DLRM particles can be effectively described by an exponential function. The mesoscopic parameters are ascertained by the orthogonal test design and contour method. The orthogonal test design can reduce the ranges of values of the mesoscopic parameters and analyze the sensitivity of the mesoscopic parameters. The main mesoscopic parameters that affect each macroscopic response are captured by sensitivity analysis, and the mesoscopic parameters are quickly calibrated by taking advantage of the contours. The numerical simulation results obtained using the determined parameters agree with the results of the laboratory triaxial compression tests.

An Auto-Contouring Method for Kidney based on SVM

In adaptive radiotherapy planning, the contour map of the treatment target area is still the most difficult problem. Usually this work is done by a professional radiologist oncologist, which is very time-consuming and labor-intensive. In order to solve this problem, this paper proposes an automatic contour method based on support vector machine. Experiments were conducted on the lower abdomen MR data set of eight patients. In the experiment, the simulated data was only used to train the classifier, and the treatment day images were used to evaluate the performance of the classifier. DSI was used to compare the manual contour and automatic contour of the kidney. The experiment showed that, The automatic contour method based on support vector machine has better classification performance than most classification algorithms. Among the eight sets of results, the DSI value of the six sets of results is 1, and the smallest DSI value is also greater than 9.423.

A method of 3D-3D multi-stage non-rigid registration of the spine based on binocular structured light.

Intraoperative deformation and radiation are common problems in spinal surgery. A three-dimensional multi-stage dynamic iterative non-rigid registration method of the spine based on binocular structured light is proposed in this paper to overcome these problems. The problem of intraoperative radiation in traditional X-ray and CT is overcome by using binocular structured light. A three-dimensional spinal mask based on binary code is designed to reduce the influence of non-interested regions on the operation. Principal component analysis (PCA) algorithm is used to complete the rough registration between the preoperative CT model of the spine and the reconstructed surface of the intraoperative structured light. A new framework of multi-stage dynamic iterative non-rigid registration of the spine is proposed. The Iterative Closest Point (ICP) algorithm based on bidirectional selection is proposed to complete the single-stage registration of the spine. Then the multi-stage dynamic iterative registration of the spine is completed to solve the problem of large registration error caused by the deformation of the spine. The method proposed in this paper is compared with traditional registration methods, and its application is verified experimentally. The results show that the registration accuracy and time of the proposed method are mm and s, respectively. The accuracy of the method is 81.5% and 78.2% higher than that of the contour method and the method of marker points, respectively. The method can effectively avoid intraoperative radiation, reduce the registration error caused by the deformation of the spine, and has a high practicability.

Noise-insensitive contour method for residual stress measurement in laser butt welding

The residual stress distribution of laser welding greatly affects the overall mechanical response of the welded structure. In this study, a new residual stress measurement method is proposed, using the finite element method (FEM) to optimize and modify the contour method. The distribution of the welding residual stress is simulated via B-spline interpolation and by solving an unconstrained weighted least-square problem in parallel, using the Levenberg–Marquardt algorithm. The control points of the B-spline are obtained to determine the residual stress distribution. For numerical verification, the residual stress dataset is generated by simulating the laser welding process, and the calculation efficiency of the FE-modified contour method is tested on this prior dataset. It is verified that the proposed method does not depend on the initial value of the residual stress distribution. This residual stress measurement method is an improvement over the traditional contour method and can achieve satisfactory accuracy, even under the influence of Gaussian noise and signal-to-noise ratio noise. In the experiments, the contour data of the laser welding seam cutting surface are obtained by employing electrical discharge cutting and three-dimensional displacement scanning technology. The traditional and FE-modified contour methods are used to identify the residual stress in the welding direction. The results show that the proposed method can adapt to contour measurement data under actual complex working conditions.

Internal stresses in a clad pressure vessel steel during post weld heat treatment and their relevance to underclad cracking

A potential connection between the residual stresses generated by a cladding operation, the thermal stresses generated during post weld heat treatment (PWHT), and the propensity for underclad cracking was investigated. As-deposited residual stresses were measured at ambient temperature, using the contour method and neutron diffraction. Measurements were performed in 20mm thick steel substrates that were partially clad with AISI grade 309 (layer 1) and grade 308 (layer 2) stainless steels, using the submerged-arc welding process. Neutron diffraction measurements were also performed after heating the clad samples to 200 and 325°C. The mechanical properties in each region within the steel heat affected zone (HAZ) were determined, at those same temperatures, by subjecting coupons to simulated cladding thermal cycles and then to tension tests. Substantial tensile residual stresses in the HAZ were measured after cladding. These persisted during subsequent heating to 325°C: a temperature that is approximately at the mid-point of the heating ramp in a typical PWHT cycle. The tensile results, however, indicated that each microstructural zone within the HAZ is likely to retain sufficient ductility to prevent fracture, and that underclad cracking is unlikely to occur during the early stages of the PWHT ramp.

Bioreactance and fourth-generation pulse contour methods in monitoring cardiac index during off-pump coronary artery bypass surgery

The pulmonary artery catheter (PAC) is considered the gold standard for cardiac index monitoring. Recently new and less invasive methods to assess cardiac performance have been developed. The aim of our study was to assess the reliability of a non-invasive monitor utilizing bioreactance (Starling SV) and a non-calibrated mini-invasive pulse contour device (FloTrac/EV1000, fourth-generation software) compared to bolus thermodilution technique with PAC (TDCO) during off-pump coronary artery bypass surgery (OPCAB). In this prospective study, 579 simultaneous intra- and postoperative cardiac index measurements obtained with Starling SV, FloTrac/EV1000 and TDCO were compared in 20 patients undergoing OPCAB. The agreement of data was investigated by Bland–Altman plots, while trending ability was assessed by four-quadrant plots with error grids. In comparison with TDCO, Starling SV was associated with a bias of 0.13 L min−1 m−2 (95% confidence interval, 95% CI, 0.07 to 0.18), wide limits of agreement (LOA, − 1.23 to 1.51 L min−1 m−2), a percentage error (PE) of 60.7%, and poor trending ability. In comparison with TDCO, FloTrac was associated with a bias of 0.01 L min−1 m−2 (95% CI − 0.05 to 0.06), wide LOA (− 1.27 to 1.29 L min−1 m−2), a PE of 56.8% and poor trending ability. Both Starling SV and fourth-generation FloTrac showed acceptable mean bias but imprecision due to wide LOA and high PE, and poor trending ability. These findings indicate limited reliability in monitoring cardiac index in patients undergoing OPCAB.

Extracting neuronal activity signals from microscopy recordings of contractile tissue using B-spline Explicit Active Surfaces (BEAS) cell tracking

Ca2+ imaging is a widely used microscopy technique to simultaneously study cellular activity in multiple cells. The desired information consists of cell-specific time series of pixel intensity values, in which the fluorescence intensity represents cellular activity. For static scenes, cellular signal extraction is straightforward, however multiple analysis challenges are present in recordings of contractile tissues, like those of the enteric nervous system (ENS). This layer of critical neurons, embedded within the muscle layers of the gut wall, shows optical overlap between neighboring neurons, intensity changes due to cell activity, and constant movement. These challenges reduce the applicability of classical segmentation techniques and traditional stack alignment and regions-of-interest (ROIs) selection workflows. Therefore, a signal extraction method capable of dealing with moving cells and is insensitive to large intensity changes in consecutive frames is needed. Here we propose a b-spline active contour method to delineate and track neuronal cell bodies based on local and global energy terms. We develop both a single as well as a double-contour approach. The latter takes advantage of the appearance of GCaMP expressing cells, and tracks the nucleus’ boundaries together with the cytoplasmic contour, providing a stable delineation of neighboring, overlapping cells despite movement and intensity changes. The tracked contours can also serve as landmarks to relocate additional and manually-selected ROIs. This improves the total yield of efficacious cell tracking and allows signal extraction from other cell compartments like neuronal processes. Compared to manual delineation and other segmentation methods, the proposed method can track cells during large tissue deformations and high-intensity changes such as during neuronal firing events, while preserving the shape of the extracted Ca2+ signal. The analysis package represents a significant improvement to available Ca2+ imaging analysis workflows for ENS recordings and other systems where movement challenges traditional Ca2+ signal extraction workflows.

Segmentation with Active Contours

Active contours (also known as snakes) have shown their ability to introduce regularity on image segmentation. In contrast with level-set approaches, the active contours techniques based on a contour parameterization are able to maintain the initial topology of the area of interest. For this reason, it has been used in recent medical research for diaphragm segmentation. Most of the on-line codes for 2D/3D segmentation, as well as built-in Matlab toolboxes are based on level-set methods. Moreover, in the literature, the implementation details of active contours methods with meshes in three dimensions are tight, making tedious any reproduction of these techniques. In this paper, we give some details of the implementation of active contours in 2D/3D with meshes, especially about the choice of the use of a 2D/3D mesh and its refinement. We also explore the choice of the parameters with a quantitative study of their influence on the segmentation results. The 3D segmentation method has been applied to CT scan images of the lungs.

A Novel Method for Effective Cell Segmentation and Tracking in Phase Contrast Microscopic Images.

Cell migration plays an important role in the identification of various diseases and physiological phenomena in living organisms, such as cancer metastasis, nerve development, immune function, wound healing, and embryo formulation and development. The study of cell migration with a real-time microscope generally takes several hours and involves analysis of the movement characteristics by tracking the positions of cells at each time interval in the images of the observed cells. Morphological analysis considers the shapes of the cells, and a phase contrast microscope is used to observe the shape clearly. Therefore, we developed a segmentation and tracking method to perform a kinetic analysis by considering the morphological transformation of cells. The main features of the algorithm are noise reduction using a block-matching 3D filtering method, k-means clustering to mitigate the halo signal that interferes with cell segmentation, and the detection of cell boundaries via active contours, which is an excellent way to detect boundaries. The reliability of the algorithm developed in this study was verified using a comparison with the manual tracking results. In addition, the segmentation results were compared to our method with unsupervised state-of-the-art methods to verify the proposed segmentation process. As a result of the study, the proposed method had a lower error of less than 40% compared to the conventional active contour method.

Developing a Recognition System for Diagnosing Melanoma Skin Lesions Using Artificial Intelligence Algorithms.

In recent years, computerized biomedical imaging and analysis have become extremely promising, more interesting, and highly beneficial. They provide remarkable information in the diagnoses of skin lesions. There have been developments in modern diagnostic systems that can help detect melanoma in its early stages to save the lives of many people. There is also a significant growth in the design of computer-aided diagnosis (CAD) systems using advanced artificial intelligence. The purpose of the present research is to develop a system to diagnose skin cancer, one that will lead to a high level of detection of the skin cancer. The proposed system was developed using deep learning and traditional artificial intelligence machine learning algorithms. The dermoscopy images were collected from the PH2 and ISIC 2018 in order to examine the diagnose system. The developed system is divided into feature-based and deep leaning. The feature-based system was developed based on feature-extracting methods. In order to segment the lesion from dermoscopy images, the active contour method was proposed. These skin lesions were processed using hybrid feature extractions, namely, the Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) methods to extract the texture features. The obtained features were then processed using the artificial neural network (ANNs) algorithm. In the second system, the convolutional neural network (CNNs) algorithm was applied for the efficient classification of skin diseases; the CNNs were pretrained using large AlexNet and ResNet50 transfer learning models. The experimental results show that the proposed method outperformed the state-of-art methods for HP2 and ISIC 2018 datasets. Standard evaluation metrics like accuracy, specificity, sensitivity, precision, recall, and F-score were employed to evaluate the results of the two proposed systems. The ANN model achieved the highest accuracy for PH2 (97.50%) and ISIC 2018 (98.35%) compared with the CNN model. The evaluation and comparison, proposed systems for classification and detection of melanoma are presented.

Strong-column–weak-beam criterion for reinforced concrete frames subjected to biaxial seismic excitation

In several earthquakes, numerous reinforced concrete (RC) frames subjected to seismic excitation exhibit a collapse pattern characterised by column hinges, although these frames are designed according to the strong-column–weak-beam (S-C–W-B) criterion. The effect of biaxial seismic excitation on the disparity between the design and the actual performance of RC frames is investigated in this study. First, a modified load contour method was proposed to derive a closed-form equation of the biaxial bending moment strength, which was verified based on numerical and experimental results. Subsequently, a group of time-history analyses of a simple frame modelled using fibre beam-column elements subjected to biaxial seismic excitation were conducted to verify that the current S-C–W-B criterion is inadequate for preventing the occurrence of column hinges. A biaxial overstrength factor was developed based on the proposed equation, and the reinforcement of columns was appropriately amplified using this factor to prevent the occurrence of column hinges under biaxial excitation; this approach was proved to be effective through another group of time-history analyses. Thus, the findings of this study can serve as a basis for improving the seismic design of RC frames, which will enable the construction of safer engineering structures.

Nested sampling with normalizing flows for gravitational-wave inference

We present a novel method for sampling iso-likelihood contours in nested sampling using a type of machine learning algorithm known as normalising flows and incorporate it into our sampler nessai. Nessai is designed for problems where computing the likelihood is computationally expensive and therefore the cost of training a normalising flow is offset by the overall reduction in the number of likelihood evaluations. We validate our sampler on 128 simulated gravitational wave signals from compact binary coalescence and show that it produces unbiased estimates of the system parameters. Subsequently, we compare our results to those obtained with dynesty and find good agreement between the computed log-evidences whilst requiring 2.07 times fewer likelihood evaluations. We also highlight how the likelihood evaluation can be parallelised in nessai without any modifications to the algorithm. Finally, we outline diagnostics included in nessai and how these can be used to tune the sampler's settings.

Characterisation of short-length scale residual stress variations within an electron beam welded P91 Ferritic–Martensitic steel plate

In this research, an electron beam (EB) butt-welded P91 steel plate (~9 mm thick) is selected to measure longitudinal residual stresses (acting in the welding direction) using a promising residual stress measurement technique - the contour method. The EB weld causes short length scale residual stresses within the narrow width of the fusion zone with steep stress gradients lateral to the weld line, which presents a new challenge for the residual stress measurements. The special measures were taken for all main steps of the technique to improve its the spatial resolution, thereby the short length scale residual stresses were captured. The success of the measurement is assessed by comparing the contour method result to the neutron diffraction result, and a good agreement were found in the results of both the techniques. These results also shows that the contour measurement results successfully captured the steep stress gradient on both sides of the weld centre-line (0 mm) with tensile stress peaks situated just 2.8 mm apart. It is one of the best resolutions in residual stress length-scale in this component achieved in contour measurements.

Seasonal Variation of the Antarctic Slope Front Occurrence and Position Estimated from an Interpolated Hydrographic Climatology

AbstractThe Antarctic Slope Front (ASF) is a fundamental feature of the subpolar Southern Ocean that is still poorly observed. In this study we build a statistical climatology of the temperature and salinity fields of the upper 380 m of the Antarctic margin. We use a comprehensive compilation of observational datasets including the profiles gathered by instrumented marine mammals. The mapping method consists first of a decomposition in vertical modes of the combined temperature and salinity profiles. Then the resulting principal components are optimally interpolated on a regular grid and the monthly climatological profiles are reconstructed, providing a physically plausible representation of the ocean. The ASF is located with a contour method and a gradient method applied on the temperature field, two complementary approaches that provide a complete view of the ASF structure. The front extends from the Amundsen Sea to the eastern Weddell Sea and closely tracks the continental shelf break. It is associated with a sharp temperature gradient that is stronger in winter and weaker in summer. The emergence of the front in the Amundsen and Bellingshausen sectors appears to be seasonally variable (slightly more westward in winter than in summer). Investigation of the density gradients across the shelf break indicates a winter slowdown of the baroclinic component of the Antarctic Slope Current at the near surface, in contrast with the seasonal variability of the temperature gradient.

Simulation of a cylindrical-conical gear train on parallel axes with an adjustable side clearance

The geometrical synthesis of a cylindrical-conical transmission on parallel axes with external gearing is considered on the basis of the blocking contour method, which makes it possible to determine solutions for the right and left ends of the wheel. The use of the calcula-tion for cylindrical-conical wheels is described. We used our own algorithm for constructing the blocking contour and engagement in the Math CAD program, and a 3D model of the trans-mission in the KISSsoft program. For a better example, the contour and engagement in the 3D model are given.

A Novel Multi-Orientation Kernel for Retina Vessel Detection

Retina is a thinnest tissue comprises of millions of blood vessels. It plays a vital role in the human eye that carries the visual signals to the brain for the interpretation. Any damage to the blood vessels in the retina causes serious issues related to the vision and it leads to the chronicle eye diseases like glaucoma, macular degeneration, diabetic retinopathy etc. Diabetic Retinopathy (DR) is a threatening disease among the diabetic patients in the recent years. Damage to the blood vessels causes DR. As the number of diabetic patients are comparatively high these days, it has become mandatory for the development of accurate system for segmenting the blood vessels in the retina which will reduce the work load of ophthalmologists to a greater extent. In this work we propose a novel technique named Multi-Orientation Kernel (MOK) for blood vessel detection. We also propose a framework for segmentation of retina blood vessels which follows the sequence of steps such as preprocessing, blood vessel extraction using proposed kernel (MOK) and refinement usingActive Contour method. This proposed method is tested on DRIVE and CHASE_DB1 dataset. The proposed algorithm produced 95% of accuracy on DRIVE datasetand 96% of accuracy on CHASE_DB1 dataset respectively. The performance of proposed approach is compared with few existing techniques.

Application of a nonlinear kinematic-isotropic material model for the prediction of residual stress relaxation under a cyclic load

The effect of residual stress in the fatigue analysis of a formed products must be considered with great care. The relaxation of residual stress under a cyclic load is a transient phenomenon that is described in this paper using classic plasticity theory by employing a combined, non-linear, kinematic and isotropic hardening material model. Results were compared with experimental observations by means of contour method and digital-image-correlation method on specimens made of S235JR steel, with focus on near surface state. This research showed reasonable prediction of initial residual stress state and an over-prediction of strain ratcheting as cyclic load progresses.

Enhanced Segmentation of Inflamed ROI to Improve the Accuracy of Identifying Benign and Malignant Cases in Breast Thermogram.

Effective analysis of breast thermography needs an accurate segmentation of the inflamed region in Infrared Breast Thermal Images (IBTI) which helps in the diagnosis of breast cancer. However, IBTI suffers from intensity inhomogeneity, overlapping regions of interest, poor contrast, and low signal-to-noise ratio (SNR) due to the imperfect image acquisition process. To mitigate this, this work proposes an enhanced segmentation of the inflamed Region of Interest (ROI) using an active contour method driven by the multiscale local and global fitted image (MLGFI) model. The first phase proposes a bilateral histogram difference-based thresholding (BHDT) method for locating the inflamed ROI. This is then used for automatic initialization of active contours driven by MLGFI to segment the inflamed ROI from IBTI effectively. To prove the effectiveness of this segmentation method, its performance is compared with ground truth image and its accuracy is also evaluated with the state-of-the-art methods (Fuzzy C Means (FCM), Chan-Vese (CV-ACM), and K-means). From the analysis, it is found that the proposed method not only increases the precision and the segmentation accuracy but also reduces the oversegmentation and undersegmentation rate significantly. In the second phase, area-based feature (AF) and average intensity-based feature (AIF) along with the GLCM (gray level cooccurrence matrix) based second-order statistical features are extracted from the inflamed ROI. Based on these features, a system is developed to effectively classify the benign and malignant breast conditions. From the results, it is observed that the proposed model exhibits an improved accuracy of 91.5%, sensitivity of 91%, and specificity of 92% compared to the whole breast thermogram. Hence, it is concluded that the proposed method will improve the efficacy of thermal imaging in the diagnosis of breast cancer.