Chan-Vese Model Research Articles

An innovative approach for PCO morphology segmentation using a novel MOT-SF technique

Polycystic ovary syndrome (PCOS) is an endocrine disorder affecting women of reproductive age characterized by the presence of multiple follicles in the ovaries that are detectable via ultrasound imaging. Early diagnosis of PCOS morphology can be challenging due to low resolution and increased speckle noise, making it difficult to identify smaller follicle boundaries. This article introduces a novel methodology, multiscale gradient-weighted oriented Otsu thresholding with sum of product fusion (MOT-SF), to address these challenges. The MOT-SF technique precisely recognizes smaller region boundaries even at lower resolutions by employing a pyramidal structure for image computation at multiple scales. Otsu's thresholding is used to segment the image, optimizing the threshold by minimizing the interclass variance at each stage. Incorporating gradient weights (λ) within classes enhances smaller boundary regions and reduces noise. Additionally, the MOT-SF method integrates a sum of product fusion strategies, combining segmented images from various scales to produce a final image that preserves both small and large PCOS structures while mitigating noise. The experimental results show that MOT-SF outperforms traditional methods such as Otsu’s thresholding and Chan-Vese models, as well as deep learning approaches such as R-CNN, in terms of computational efficiency and robustness to variations in ultrasound image quality. The MOT-SF methodology achieves an accuracy of nearly 85% and a precision of 94%, highlighting its potential to improve the detection and characterization of follicles in ultrasound images and advancing diagnostic tools in reproductive health.Graphical

Fast and accurate phase processing in off-axis digital holography combining adaptive spatial filtering and an embedded GPU platform

Abstract Parallel-phase processing enables rapid phase extraction from off-axis digital holograms. To achieve fast and accurate results, the phase reconstruction processes were parallelized using improved filter algorithms and optimized programming strategies. First, an adaptive filtering method based on the Chan-Vese (CV) model which better suits parallelism was designed to extract the +1 term spectrum. We selected suitable computer unified device architecture (CUDA) libraries according to the characteristics of the key phase reconstruction steps. Acceleration technologies, such as virtual memory and shared memory, were used to improve the computational efficiency. Furthermore, we combined an improved 4f optical imaging system with an embedded graphic processing unit (GPU) platform to design a low-cost phase reconstruction system for off-axis digital holography. To verify the feasibility of our method, the reconstructed quality of the CV filtering method was estimated, and the run times of phase retrieval on the central processing unit (CPU) and embedded GPU were compared for off-axis holograms with different pixel sizes. Additionally, the dynamic fluctuation phase maps of water droplet evaporation were retrieved to demonstrate the real-time capability of the method.

Automated Ultrasound Object Segmentation Using Combinatorial Active Contour Method

Active Contour (AC) is an algorithm widely used in segmentation for developing Computer-Aided Diagnosis (CAD) systems in ultrasound imaging. Existing AC models still retain an interactive nature. This is due to the large number of parameters and coefficients that require manual tuning to achieve stability. Which can result in human error and various issues caused by the inhomogeneity of ultrasound images, such as leakage, false areas, and local minima. In this study, an automatic object segmentation method was developed to assist radiologists in an efficient diagnosis process. The proposed method is called Automatic Combinatorial Active Contour (ACAC), which combines the simplification of the global region-based CV (Chan-Vese) model and improved-GAC (Geodesic Active Contour) for local segmentation. The results of testing with 50 datasets showed an accuracy value of 98.83%, precision of 95.26%, sensitivity of 86.58%, specificity of 99.63%, similarity of 90.58%, and IoU (Intersection over Union) of 82.87%. These quantitative performance metrics demonstrate that the ACAC method is suitable for implementation in a more efficient and accurate CAD system.

Automatic classification and segmentation of blast cells using deep transfer learning and active contours.

Acute lymphoblastic leukemia (ALL) presents a formidable challenge in hematological malignancies, necessitating swift and precise diagnostic techniques for effective intervention. The conventional manual microscopy of blood smears, although widely practiced, suffers from significant limitations including labor-intensity and susceptibility to human error, particularly in distinguishing the subtle differences between normal and leukemic cells. To overcome these limitations, our research introduces the ALLDet classifier, an innovative tool employing deep transfer learning for the automated analysis and categorization of ALL from White Blood Cell (WBC) nuclei images. Our investigation encompassed the evaluation of nine state-of-the-art pre-trained convolutional neural network (CNN) models, namely VGG16, VGG19, ResNet50, ResNet101, DenseNet121, DenseNet201, Xception, MobileNet, and EfficientNetB3. We augmented this approach by incorporating a sophisticated contour-based segmentation technique, derived from the Chan-Vese model, aimed at the meticulous segmentation of blast cell nuclei in blood smear images, thereby enhancing the accuracy of our analysis. The empirical assessment of these methodologies underscored the superior performance of the EfficientNetB3 model, which demonstrated exceptional metrics: a recall specificity of 98.5%, precision of 95.86%, F1-score of 97.16%, and an overall accuracy rate of 97.13%. The Chan-Vese model's adaptability to the irregular shapes of blast cells and its noise-resistant segmentation capability were key to capturing the complex morphological changes essential for accurate segmentation. The combined application of the ALLDet classifier, powered by EfficientNetB3, with our advanced segmentation approach, emerges as a formidable advancement in the early detection and accurate diagnosis of ALL. This breakthrough not only signifies a pivotal leap in leukemia diagnostic methodologies but also holds the promise of significantly elevating the standards of patient care through the provision of timely and precise diagnoses. The implications of this study extend beyond immediate clinical utility, paving the way for future research to further refine and enhance the capabilities of artificial intelligence in medical diagnostics.

Fractional guidance-based level set evolution for noisy image segmentation with intensity inhomogeneity

Intensity inhomogeneity (IIH) and noise are ubiquitous in images acquired by a variety of imaging modalities, which pose an ongoing challenge for segmentation methods used in many applications. This paper proposes a level set evolution equation based on fractional derivative to address the IIH and noise issues in image segmentation, which integrates the information from the input and guidance images. The proposed model is a linear diffusion equation of level set function with nonlinear edge-stopping and guidance sources, in which the edge-stopping source is derived from the input image and a local statistical model (Bayesian formulation) in the level set framework, whereas the guidance source is derived from the guidance image and the fitting term of the popular Chan-Vese model. The guidance source ensures swift contour movement toward the boundary of the objects and enhances the robustness to noise and contour initialization, while the edge-stopping source is used to stop the evolving contour on the boundary of the objects later in the evolution. To tackle the challenge of obtaining accurate guidance images for many applications, an adaptive variable-order of fractional derivative robust to IIH and noise is introduced to generate the desired guidance image from the input image. The proposed diffusion equation with sources is solved numerically by the series splitting method and finite difference scheme. Experimental results on synthetic and real images show that the proposed model has higher performance in terms of accuracy and efficiency of segmentation, compared to several state-of-the-art level set models.

Comparison of Otsu and an adapted Chan–Vese method to determine thyroid active volume using Monte Carlo generated SPECT images

BackgroundThe Otsu method and the Chan–Vese model are two methods proven to perform well in determining volumes of different organs and specific tissue fractions. This study aimed to compare the performance of the two methods regarding segmentation of active thyroid gland volumes, reflecting different clinical settings by varying the parameters: gland size, gland activity concentration, background activity concentration and gland activity concentration heterogeneity.MethodsA computed tomography was performed on three playdough thyroid phantoms with volumes 20, 35 and 50 ml. The image data were separated into playdough and water based on Hounsfield values. Sixty single photon emission computed tomography (SPECT) projections were simulated by Monte Carlo method with isotope Technetium-99 m (^{text {99m}}Tc). Linear combinations of SPECT images were made, generating 12 different combinations of volume and background: each with both homogeneous thyroid activity concentration and three hotspots of different relative activity concentrations (48 SPECT images in total). The relative background levels chosen were 5 %, 10 %, 15 % and 20 % of the phantom activity concentration and the hotspot activities were 100 % (homogeneous case) 150 %, 200 % and 250 %. Poisson noise, (coefficient of variation of 0.8 at a 20 % background level, scattering excluded), was added before reconstruction was done with the Monte Carlo-based SPECT reconstruction algorithm Sahlgrenska Academy reconstruction code (SARec). Two different segmentation algorithms were applied: Otsu’s threshold selection method and an adaptation of the Chan–Vese model for active contours without edges; the results were evaluated concerning relative volume, mean absolute error and standard deviation per thyroid volume, as well as dice similarity coefficient.ResultsBoth methods segment the images well and deviate similarly from the true volumes. They seem to slightly overestimate small volumes and underestimate large ones. Different background levels affect the two methods similarly as well. However, the Chan–Vese model deviates less and paired t-testing showed significant difference between distributions of dice similarity coefficients (p-value <0.01).ConclusionsThe investigations indicate that the Chan–Vese model performs better and is slightly more robust, while being more challenging to implement and use clinically. There is a trade-off between performance and user-friendliness.

An Efficient Local Radial Basis Function Method for Image Segmentation Based on the Chan–Vese Model

An Efficient Local Radial Basis Function Method for Image Segmentation Based on the Chan–Vese Model

Automated Binocular Vision Measurement of Food Dimensions and Volume for Dietary Evaluation

We propose a novel binocular vision technique to obtain food dimensions for dietary evaluation. A wearable device acquired images of food samples, which were segmented using the improved Chan-Vese model and compared with virtual objects. Results showed this method to be robust, achieving higher accuracy than conventional correspondence techniques.

Sugar-free aerated chocolate: Production, investigation of bubble features using X-ray computed tomography and image processing.

In contrast to other imaging techniques, X-ray imaging does not destruct the internal structure of the sample being imaged. Furthermore, this technique is able to capture numerous images of the sample at a low slice thickness, which is almost impossible in other imaging techniques. In this study, sugar was replaced with inulin:maltodextrin mixtures at ratios of 25:75 (i25), 50:50 (i50), and 75:25 (i75). Then, nitrogen (N2 ) and carbon dioxide (CO2 ) were injected into the three mixtures as well as the sugar-containing sample (control) at pressures of 3, 4.5, and 6 bar to produce aerated chocolate. The images of the samples were captured using X-ray computed tomography (XCT). After processing, they were segmented using the Chan-Vese model. Image segmentation showed that the Chan-Vese method, compared with adaptive thresholding, was more able to segment the images and remove the noise. The bubble total volume (10440±9206mm3 ) and average diameter (1.30±0.10mm) of the control were larger than those of the other samples. The results also demonstrated that the sugar-free aerated samples had lower hardness than the corresponding unaerated ones. However, it was reversed in the case of the control. This research sheds light on the industrialization of the production of aerated chocolate and the application of XCT and image processing in the analysis of the microstructure of aerated products.

A Study of Chan-Vese Model with the Introduction of Edge Information

In image segmentation, the image edge information and the selection of edge-stopping function have a extremely important influence on the segmentation effect. As a classical geometric active contour model, Chan-Vese model completely utilizes image global information for segmentation, which has the problems of inability to handle grayscale uneven images and slow curve evolution. This paper introduces edge information into the Chan-Vese model, chooses a new edge stopping function and simplifies the driving force term to build a new image segmentation model. The new model can detect the target fast, displaying better detection effect on the targets of images with uneven grayscale and the detection effect of the target in the uneven gray image is better

A Fault Warning Method for Hotline Tap Clamp Infrared Images Based on Hybrid Segmentation

Substation equipment faults are typically related to the heating of equipment components. The hotline tap clamps of substation are critical components for carrying load currents and thermal fault potential. As a result, a new hybrid early warning approach for hotline tap clamp faults in substation equipment is presented. A two-dimensional Otsu algorithm is used to coarse-segment infrared images to minimize the subsequent complexity. Since the Chan–Vese (CV) model is insufficiently accurate for image segmentation with uneven grayscale, then the differential data obtained by the Prewitt operator to identify the goal edges are combined with the CV model to improve segmentation accuracy. The improved CV model achieves excellent segmentation of the hotline tap clamp in the substation. The temperature statistics are utilized for the segmented images, and the hotline tap clamp fault warning is realized based totally on the relative temperature difference. Finally, the experiments exhibit that the method can enhance the segmentation impact of infrared images and obtain the goal of fault warning.

A novel dual-based ADMM to the Chan-Vese model

A novel dual-based ADMM to the Chan-Vese model

Intelligent velocity picking considering an expert experience based on the Chan–Vese model and mean-shift clustering

The velocity of seismic data can initially be established by identifying energy clusters on velocity spectra at different moments, which is crucial to the migration imaging and the stacking of common midpoint (CMP) gathers in the seismic data processing. However, the identification of energy clusters currently relies on manual work, with low efficiency and different standards. With the increasing application of wide-frequency, wide-azimuth, and high-density seismic exploration technology, the amount of seismic data has increased significantly, greatly increasing the cost of manual labor and time. In this paper, an intelligent velocity picking method based on the Chan–Vese (CV) model and mean-shift clustering algorithm was proposed. It can be divided into three steps. First, a velocity trend band is set up on the velocity spectrum by experts to avoid multiples and other noises. Then, the velocity trend band is applied to the Chan–Vese model as the initial time condition to segment the velocity spectrum and obtain the velocity candidate region. Finally, mean-shift clustering is adopted to cluster the useful energy clusters retained in the candidate region derived from the Chan–Vese model. When implementing the mean-shift clustering algorithm, the Gaussian kernel function and the energy of the velocity spectrum are utilized to control the efficiency and accuracy of the cluster. The tests of the model and real data prove that the proposed method can dramatically improve the accuracy and efficiency of velocity picking compared with the K-means and manual picking method.

Ship Contour Extraction From SAR Images Based on Faster R-CNN and Chan–Vese Model

Compared with most ship detection methods for synthetic aperture radar (SAR) images, ship contour extraction can provide more of the detailed shape and edge information of an observed ship and play a significant role in sea surface monitoring and marine transportation. In this study, a joint ship contour extraction method (Faster R-CNN, FNLM, and Chan-Vese model; FFCV method) was proposed to obtain detailed ship information from SAR images, including ship detection in complex scenes and contour extraction in target slices. First, Faster R-CNN was employed to slice ships from large-scene SAR images. Then, Fast non-local mean (FNLM) filtering was applied to denoise and enhance the structural information of the target slices. Finally, an optimized Chan-Vese model was proposed in this paper, which can not only accurately extract the contour of the observed ship, but also reduce the computation time of the model. The SAR ship detection dataset (SSDD) was selected and finely relabeled to evaluate the contour extraction performance. An evaluation index <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R_N</i> , including quantitative value and offset direction, was developed to evaluate the extraction accuracy of the target contour from the SAR images. Compared with the Mask R-CNN network, the average contour extraction accuracy index <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R_N</i> of the proposed FFCV method reached -0.002 on all the images in SSDD dataset, and its results were closer to the real ship contours while maintaining the applicability to complex scenes.

Research on laser center positioning under CV model segmentation

Spot positioning accuracy is an important index of laser processing system and ranging system. When the laser spot is noisy or the gray level is not uniform, the positioning accuracy is easily affected. Aiming at the above problems, this paper proposes a laser spot segmentation method based on the Chan-Vese model, which can improve the accuracy of spot center localization in combination with the gray centroid method. Firstly, the laser spot image is decomposed by two-dimensional wavelet, and the high-frequency component is suppressed by soft threshold function to eliminate the noise in the laser spot image. Secondly, the level set algorithm based on Chan-Vese model is used to segment the laser spot image with adaptive improvement of the initial coordinates of the evolution curve. Finally, the center coordinates are calculated inside the segmentation curve using the gray centroid method. Experimental results show that the method is more accurate and robust.

Robust vegetation segmentation under field conditions using new adaptive weights for hybrid multichannel images based on the Chan-Vese model

This paper proposes a method for detecting vegetation in agricultural images under real field conditions. It includes two modules: The first module constructs a multichannel image by combining four color indices and the L∗a∗b∗ color space using Principal Component Analysis (PCA). The second module detects the vegetation by applying an improved Chan-Vese method. In this method, the energy weights are automatically estimated based on the contrast between foreground regions and the background. To speed up the segmentation process a sweeping algorithm is applied. Experimental results demonstrate that our algorithm outperforms ten state-of-the-art methods, yielding higher accuracy, precision, and achieving better recall and F-score rates. The main advantage of the proposed method is that it performs well under different field conditions. On the seven datasets considered in this work, the proposed method achieved 97.10%,95.70%,95.70%, and 96.37% averages in terms of accuracy, F-score, precision, and recall respectively.

Brain Tumor Segmentation Based on Bendlet Transform and Improved Chan-Vese Model.

Automated segmentation of brain tumors is a difficult procedure due to the variability and blurred boundary of the lesions. In this study, we propose an automated model based on Bendlet transform and improved Chan-Vese (CV) model for brain tumor segmentation. Since the Bendlet system is based on the principle of sparse approximation, Bendlet transform is applied to describe the images and map images to the feature space and, thereby, first obtain the feature set. This can help in effectively exploring the mapping relationship between brain lesions and normal tissues, and achieving multi-scale and multi-directional registration. Secondly, the SSIM region detection method is proposed to preliminarily locate the tumor region from three aspects of brightness, structure, and contrast. Finally, the CV model is solved by the Hermite-Shannon-Cosine wavelet homotopy method, and the boundary of the tumor region is more accurately delineated by the wavelet transform coefficient. We randomly selected some cross-sectional images to verify the effectiveness of the proposed algorithm and compared with CV, Ostu, K-FCM, and region growing segmentation methods. The experimental results showed that the proposed algorithm had higher segmentation accuracy and better stability.

Welding Defects Detection in Radiographic Images Using an Improved Denoising Technique Combined with an Enhanced Chan-Vese Model

The detection of welding defects is becoming an important operation in the industry and the field of non-destructive testing. Among the most used techniques in the detection of weld defects, it is radiography. The radiographic images acquired are generally of low contrast, poor quality, and uneven lighting. Therefore, the detection of welding defects becomes a difficult task. In this work, a new hybrid approach based on the combination of several techniques is proposed. It consists of three stages: firstly, we define the region of interest (ROI). Secondly, a preprocessing operation based on an improved version of denoising by soft thresholding of wavelet coefficients and an optimized threshold is applied to improve the image quality (noise reduction, contrast enhancement). Thirdly, an enhanced Chan-Vese model is proposed to segment the denoised ROI region. This enhanced model is based on the choice of a cluster obtained by the Fuzzy C-Mean algorithm (FCM) as the initial contour. The proposed approach is applied to the various radiographic welding images from the GDxray database to extract the characteristics of the welding defects. The results obtained clearly show the effectiveness of the proposed approach compared to conventional techniques.

A Machine-Learning-Based Medical Imaging Fast Recognition of Injury Mechanism for Athletes of Winter Sports.

The Beijing 2022 Winter Olympics will begin soon, which is mainly focused on winter sports. Athletes from different countries will arrive in Beijing one after another for training and competition. The health protection of athletes of winter sports is very important in training and competition. The occurrence of sports injury is characterized by multiple factors, uncertainty, and accidents. This paper mainly pays attention to the head injury with the highest severity. Athletes' high safety awareness is a part of reducing injury, but safety awareness cannot effectively reduce the occurrence of injury in competition, and timely treatment of injured athletes is particularly important. After athletes are injured, a telemedicine image acquisition system can be built, so that medical experts can identify athletes' injuries in time and provide the basis for further diagnosis and treatment. In order to improve the accuracy of medical image processing, a C-support vector machine (SVM) medical image segmentation method combining the Chan-Vese (CV) model and SVM is proposed in this paper. After segmentation, the edge and detail features of the image are more prominent, which meet the requirements of high precision for medical image segmentation. Meanwhile, a high-precision registration algorithm of brain functional time-series images based on machine learning (ML) is proposed, and the automatic optimization of high-precision registration of brain function time-series images is performed by ML algorithm. The experimental results show that the proposed algorithm has higher segmentation accuracy above 80% and less registration time below 40 ms, which can provide a reference for doctors to quickly identify the injury and shorten the time.

Distance regularization energy terms in level set image segment model: A survey

The level set is a classical image segmentation model. In order to achieve its stable evolution, the level set function should be a signed distance function (SDF). However, due to the common appearance of irregularities, it must periodically be initialized in order to remain a SDF near the zero level set. Distance regularization terms have been used to maintain the stable evolution of the level set function. We provide a survey of the various distance regularization potential functions. Firstly, we summarize many kinds of distance regularization potential functions studied in the literature. We then divide them into five classes according to the type of potential function. Secondly, we analyze the properties of every class of potential functions and their diffusion rate functions. Finally, to demonstrate the effectiveness of the distance regularization potential functions, we apply them with a region based level set energy functional for image segmentation. Experimental analyses are conducted to compare the segmentation performance of various distance regularization potential functions when combined with the classical Chan Vese model.