Watershed Method Research Articles

Extraction of Tooth Cusps based on DBSCAN Density Clustering and Neighborhood Search Algorithm.

A good tooth cusp extraction is helpful in evaluating the effect of cosmetic dental work in virtual tooth surgery. We propose a new tooth cusp extraction, which integrates the DBSCAN (density-based spatial clustering of applications with noise) clustering algorithm with the neighborhood search algorithm to extract tooth cusp from a three-dimensional cloud-point tooth model. This method used the point cloud height and curvature to screen out the dented point set. Then we employ the DBSCAN clustering algorithm to segment different feature regions of the tooth surface and generate the candidate point set. Finally, the candidate point set was accurately located at the tooth apex through the neighborhood search algorithm and the traversal search method of non-maximum suppression. The experimental results show that the proposed method is superior to the traditional watershed algorithm-based methods by calculating the recall rate and accuracy rate, and also has higher extraction speed and extraction precision than manual extraction methods.

Morphological and Marker-based Watershed Method for Detection and Segmentation of Brain Tumor Regions

Brain tumor detection is a complex problem in medical image analysis. Brain tumor is an abnormal growth of brain cellsthat is usually detected by Magnetic Resonance Images (MRI). In this paper, we propose an efficient algorithm for detecting brain tumors using MRI without skull removal. After applying basic image preprocessing techniques, morphological operations are used to detect the boundaries and sharpen the regions.Segmentation is performed using Otsu thresholding and then a marker watershed technique is used for final brain tumor segmentation. The proposed approach is evaluated on 3000 images from Brain Tumor Image Segmentation Challenge (BRATS) dataset. Experiments showed that with appropriate preprocessing and appropriate thresholding, good segmentation results can be achieved.

Deep learning-based image analysis for in situ microscopic imaging of cell culture process

Mammalian cell culture is an important bioprocess that directly affects the quality and yield of biopharmaceuticals. Traditionally, condition monitoring of the operation is based on sampling periodically and off-line analysis, which is labor intensive, time consuming, and causing time delays. In this work, in situ microscope is investigated for on-line real-time monitoring of the culture process of Chinese hamster ovary cells with focus on investigation of deep learning-based Mask R-CNN algorithm for image analysis. The model is trained by 184 images with 183,040 cells using data augmentation methods and transfer learning technique. Mask R-CNN segmented the clustered cells more effectively than the conventional one combining edge detection, intensity thresholding, and advanced watershed method as well as the multi-scale edge detection method. Its Dice score, accuracy, precision, sensitivity, F1 score, specificity, and relative volume difference reach 0.862, 0.945, 0.901, 0.827, 0.862, 0.977, and 0.082, respectively. The evolution of geometrical features of cells were further analyzed, including equivalent diameter, circularity, aspect ratio, and eccentricity. The result demonstrated the great potential of deep learning technology in analysis of on-line images for optimization and control of the cell culture process.

Enhancing pore network extraction performance via seed-based pore region growing segmentation

Pore-scale modeling, aided by imaging advancements and computational power, is now a vital tool for comprehending fluid flow and transport in porous media. It allows detailed exploration of pore structures and analysis of fluid dynamics and mass transport at smallest scales. This work presents the Pore Region Growing (PREGO) Algorithm, a novel approach to address segmentation challenges encountered in large-sized 3D images used for pore network modeling. The algorithm overcomes limitations of traditional methods like the watershed algorithm, in both computational time and memory of the pore segmentation. Like the watershed method, the proposed work involves identifying seed points, then grows each to fill their respective basis. The algorithm differs from existing approaches in that it efficiently prioritizes and grows the seed points using a FIFO queue, resulting in well-defined segmentation with clear and smooth boundaries between neighboring regions. The output was validated by demonstrating the algorithm's robustness in predicting diffusive behavior and viscous fluid flow within the pore phase network, with excellent agreement in comparison to lattice Boltzmann simulations and experimental data. The proposed algorithm was also shown to accurately predict transport properties under varying porosity, and different types of real porous media images. The evaluation of the Intersection over Union (IoU) and Dice Similarity Coefficient (DSC) metrics revealed that the PREGO technique had a maximum error of 5.44%, whereas the Watershed method exhibited a comparatively higher error rate of 22.3%. Structural analysis of physical properties revealed PREGO captures pore and throat sizes in close agreement with existing approaches. Crucially, computational performance analysis demonstrated its efficiency, significantly reducing memory consumption by 50% and CPU time speed up of 3.35X compared to the standard watershed algorithm using a priority queue.

Segmentation of two-phase flow X-ray tomography images to determine contact angle using deep autoencoders

This study improves the characterization of in situ contact angles in porous media by employing deep learning techniques (SegNet, UNet, ResNet, and UResNet) for multiphase segmentation of micro-CT images. The algorithms were tested on high-resolution X-ray images of a steady-state flow experiment where two fluid phases were simultaneously injected at different fractional flows. The models were trained to segment the images into solid, aqueous phase, and non-aqueous phase liquid (NAPL). The UResNet demonstrated the best performance with an f1-score of 0.966 for the test dataset. More importantly, the UResNet offered higher reliability than the watershed algorithm for various fractional flows based on visual inspection and phase distribution analysis. The porosity calculation error of the watershed method (7.8 %) was reduced to 5.1 % by UResNet. Furthermore, UResNet accurately depicted the consistently mixed-wet condition of the rock sample throughout the experiment, in contrast to the watershed segmentation that yielded inconsistencies in contact angle calculations at an aqueous phase fractional flow of 0.01.

Application of AHP-ICM and AHP-EWM in Collapse Disaster Risk Mapping in Huinan County

Collapses are one of the most common geological disasters in mountainous areas, which easily damage buildings and infrastructures and bring huge property losses to people’s production and life. This paper uses Huinan County as the study area, and with the help of a geographic information system (GIS) based on the formation principle of natural disaster risk, the information content method (ICM), the analytical hierarchy process (AHP), and the analytical hierarchy process–information content method (AHP-ICM) model are applied to hazard mapping, and the analytical hierarchy process-entropy weight method (AHP-EWM) model is applied to exposure, vulnerability and emergency responses, and recovery capability mapping. A risk mapping model for collapse disasters was also constructed using these four elements. Firstly, an inventory map of 52 landslides was compiled using remote sensing interpretation, field verification, and comprehensive previous survey data. Then, the study area mapping units were delineated using the curvature watershed method in the slope unit, and 21 indicators were used to draw the collapse disaster risk zoning map by considering the four elements of geological disaster risk. The prediction accuracy of the three hazard mapping models was verified using the receiver operating characteristic (ROC) curve, and the area under the curve (AUC) results of the AHP, ICM, and AHP-ICM models were 80%, 85.7%, and 87.4%, respectively. After a comprehensive comparison, the AHP-ICM model is the best of the three models in terms of collapse hazard mapping, and it was applied to collapse risk mapping with the AHP-EWM model to produce a reasonable and reliable collapse risk zoning map, which provides a basis for collapse management and decision making.

A novel static and dynamic hand gesture recognition using self organizing map with deep convolutional neural network

Gesture recognition has gained a lot of popularity as it allows humans to communicate with real or virtual systems through gestures, offering new and natural interaction modalities. Recent technologies, such as augmented reality (AR) and the Internet of Things (IoT), have witnessed enormous growth in computer applications that focus on human–computer interaction (HCI). However, a few of these tactics make use of a combination of methods, such as image segmentation, pre-processing, and classification. The hessian-based multiscale filtering and YCbCr colour space are used to separate the gesture region to be recognized. A modified marker-controlled watershed method is employed to segment the gesture contour along with the eight-connector graph to increase recognition precision. The proposed hand gesture recognition methodology uses Self Organizing Map (SOM) with Deep Convolutional Neural Network (DCNN) provides better results with fast convergence speed. Experiments were carried out on a dataset of 30 static and 6 dynamic gestures and also evaluated on a publicly available IIITA-ROBITA ISL Gesture Database to show the effectiveness. The results show that the suggested method can recognize gesture classes with 95.63% accuracy rate without significantly affecting the recognition time. The proposed algorithm was then implemented to control household appliances.

Persistent homological cell tracking technology

In this paper, we develop a cell tracking method based on persistent homological figure detection technology. We apply our tracking method to 9 different time-series cell images and extract several kinds of cell movements. Being able to analyze various images with a single method allows researchers to systematically understand and compare different tracking data. Persistent homological cell tracking technology’s 9 parameters all have clear meanings. Thus, researchers can decide the parameters not by black box trial-and-error but by the purpose of their analysis. We use model data with ground truth to see our method’s performance. We compare persistent homological figure detection and cell tracking technology with Image-Pro, sure-foreground in watershed method, and cell detection methods in previous studies. We see that there are some cases where Image-Pro’s tracking stops and requires manual plots, while our method does not require manual plots. We show that our technology includes sure-foreground and has more information, and can be applied to different types of data that previously needed different methods. We also show that our technology is powerful as a detection technology by applying the technology to 5 different types of cell images.

Mass transfer of the multicomponent free jet and one numerical implementation on a graphic processing unit platform

Jet flows are ubiquitous in nature and laboratories. For example, helium and argon jets into ambient air are commonly used to produce atmospheric plasma jets. The jets before and after discharge both are typical multicomponent flows. This study reports on the implementation of a numerical solver based on the graphic processing units to model multicomponent mixture gas flows. To this end, two- and three-dimensional Jacobian matrices for the multicomponent Euler equations were obtained to reconstruct numerical fluxes and build a total variation diminishing scheme. The two-dimensional early-stage mass transfer of gas jets was studied for three mixture gases: He/air, Ar/air, and N2/air to numerically verify the steady functioning of the numerical solver despite the high mass fraction gradients. The mass fraction distribution of helium in ambient air exhibited more complex substructures than those of argon and nitrogen in ambient air. Using the watershed method, self-generated bullets were extracted from the mass fraction distributions of the helium jet. The proposed numerical solver implemented in this study is expected to provide a better understanding of gas jet dynamics, and the Jacobian matrices can provide a mathematical foundation for constructing potential higher schemes.

An assessment on the off-road trafficability using a quantitative rule method with geographical and geological data

The assessment of off-road trafficability is an important issue in special military or disaster relief operations. It is affected by geographical and geological environmental factors, and the factor sensitivity changes with space. Previous research used a qualitative manual rule method and geographical factors to assess off-road trafficability in terms of land coverage and terrain factors. However, this caused problems because the factors were not comprehensive, the method was qualitative, and there was a great deal of noise in the assessment results. To solve these problems, we developed a quantitative rule method to comprehensively assess the obstacles caused by geographical and geological factors to off-road trafficability. First, we reviewed remote sensing images of various factors in the study area, searched for traffic rules, and quantified them using the analytic hierarchy process-weighted information content (AHP-WIC) method. Then, the corresponding relationship between rules and off-road trafficability is established by the clustering method, and it is divided into multiple types of motion (generally>2 types). Finally, we used the improved watershed method to filter off-road trafficability map noise. The results showed that the geological environment (including geological hazards, joint & structure, topographic position index, rock structure, etc.) can seriously hinder off-road trafficability but has not been considered in previous research. For complex field environments, the proposed method can adaptively establish the classification relationship between rules and off-road trafficability. Additionally, the improved watershed method can effectively filter the noise generated by the rule method.

Malignant Detection of Breast Nodules On BIRADS-Based Ultrasound Images Margin, Orientation, And Posterior

Breast cancer has the largest prevalence in the world in 2020, with 2,261,419 cases or 11.7%. It is also the leading cause of cancer death, accounting for 6.9% of all cancer deaths. Asia and Indonesia have the greatest prevalence and mortality rates. This is an urgent issue that must be addressed. Ultrasonography (USG) is advised for assessing the features of breast nodules. Breast nodules on ultrasound pictures are interpreted using the Breast Imaging, Reporting, and Data System (BIRADS) category, which has five features. Yet, the probability of a False Positive Result (FPR) on ultrasound imaging is relatively high. Computer Aided Diagnosis (CAD) was created to reduce FPR. However, CAD research based on many BIRADS traits is currently margined. As a result, based on three BIRADS characteristics, namely the margin, posterior, and orientation aspects, this study aims to proposed the methode for diagnosing breast nodule malignancy. The proposed method consists of 4 stages, namely, pre-processing, automatic segmentation, features extraction, and classification. Pre-processing adaptive median filter maximum window size is 11 pixels, linear histogram normalizing, and Reduction Anisotropic Diffusion (SRAD) filter were used to construct the method. The neutrosophic watershed method was used in the suggested automatic segmentation. Based on the nodule's margin, orientation, and posterior, 10 features were proposed: nodule width, gradient, slenderness, margin sharpness, shadow indicators, skewness, energy, entropy, dispersion, and solidity. MLP is a classification approach. The test used 94 nodule pictures and yielded an accuracy of 88.30%, a sensitivity of 82.35%, a specificity of 91.67%, a Kappa of 0.7449, and an AUC of 0.865. As a result, it is feasible to conclude that the proposed method is capable of detecting malignancy in breast nodules in ultrasound images. To make the proposed method more reliable in the future, automatic RoI can be developed.

An optimal model for classification of lung cancer using grey wolf optimizer and deep hybrid learning

In recent years, metaheuristic methods have shown major advantages in the field of feature selection due to its comprehensibility and possible extensive search competence. However, the majority of evolutionary computation-based feature selection algorithms in use today are wrapper approaches, which are expensive to compute, particularly for extensive biomedical data. Developing an effective evaluation strategy is crucial for significant reduction of computational cost. The proposed framework extracts deep feature from ResNet-50 and VGG-16 based convolutional neural models with initial segmentation process based on marker-controlled watershed method. Next the feature reduction is a two-fold approach with principal component analysis applied to reduce the dimensionality of large feature space from convolutional neural network (CNN) models as first step. The second step is optimal feature subset selection using a swarm intelligence method referred as modified grey wolf optimization. Finally, the selected feature subset is fed to various machine learning classifiers. The experimental result reveals that the proposed algorithm outperforms the other state-of-the-art methods with classification accuracy of 96.56%, thus upholding the dependability of the approach.

X-Ray Tomography Crystal Characterization: Automatic 3D Segmentation.

Understanding the structural parameters of crystals during crystal growth is essential for the pharmaceutical and chemical industries. This study proposes a new method for 3D images of crystals obtained with micro X-ray computed tomography. This method aims to improve the crystal segmentation compared to the watershed methods. It is based on plane recognition at the surface of the crystals. The obtained segmentation is evaluated on a synthetic image and by considering the recognized particle number and convexity. The algorithm applied to three samples (potassium alum, chromium alum, and copper sulfate) reduced oversegmentation by 87% compared to watershed based on ultimate erosion while keeping the convexity of the recognized particle.

The area-reconstruction h-dome technique and its efficient Python implementation for improved particle size image analysis.

The traditional watershed segmentation methods usually suffer from over segmentation for irregularly shaped particles. This is because the distance map of an irregularly shaped particle contains multiple local maxima, and over segmentation would happen if these local maxima were used as seeds for watershed segmentation. In this work, several methods based on morphological reconstruction, including h-dome transform, h-maxima, and area-reconstruction h-dome transform, are introduced to merge, or erase redundant local maxima, and the performance of these methods in avoiding over segmentation is compared. The results show that the area-reconstruction h-dome transform is the most effective method in controlling over segmentation among the evaluated methods. However, the area-reconstruction h-dome transform is achieved by superposition of binary reconstructions at each grayscale level, which is extremely time-consuming and impractical for batch processing. A hybrid pixel-queue algorithm is applied to accelerate the area-reconstruction h-dome transform, and the algorithm is implemented in Cython to further improve the computational efficiency. For a 2592 × 1944 pixel image, on a PC with an Intel Core i5 2.4GHz processor and 8GB RAM, the processing time of the area-reconstruction h-dome transform after acceleration is about 549 ms, which is 249 times faster than the unaccelerated algorithm and 4 times faster than the reconstruction function in the Scikit-image library (an open-source image processing library for the Python programming language) which performs reconstruction by dilation. The accelerated area-reconstruction h-dome transform algorithm was successfully applied to the segmentation of rubber particles in a thermoplastic polyolefin (TPO) compound. RESEARCH HIGHLIGHTS: Techniques for segmenting particles with irregular shapes based on morphological reconstruction are reviewed. A fast algorithm for area-reconstruction h-dome transform is introduced based on Vincent's first approach combined with the pixel queue algorithm and Cython acceleration. The accelerated reconstruction algorithm is 249 times faster than the unaccelerated algorithm. The fast area-reconstruction h-dome transform algorithm is successfully applied to rubber particle segmentation of a thermal plastic polyolefin.

Implementation of ColorSpace, GrabCut, and Watershed Methods on Digital Image Segmentation of Coral and Fish Objects

Poor coral reefs rising in eastern Indonesia. The colors have disappeared from the seafloor instead, bleached branches are visible. To recognize the differences between dead and healthy coral reefs, an identification system has been created using the image processing method. Object segmentation is a step in digital image processing to separate one object from another based on specific characteristics. In this study, coral objects with various colored backgrounds and things became a problem to separate, so this study aimed to separate these various colors. This research uses color space segmentation to visualize RGB and HSV colors, Grabcut segmentation to separate the largest corals, and watershed segmentation to separate dead corals. Therefore, from this study, the RGB and HSV color visualizations were clearly visible. From Grabcut segmentation, it is found that the largest fish is detected and can be displayed in the segmentation results. At the same time, the watershed segmentation displays dead coral taken by gray segmentation with otsu.

A Hybrid Skin Lesions Segmentation Approach Based on Image Processing Methods

Presently image segmentation remains the most crucial stage in the image processing system. The main idea ofimage segmentation is to partition or divide a random image into several partitions depending on the problem to solve. In this paper, we will be presenting a new method of skin cancer detection based on Otsu’s thresholding algorithm and markercontrolled watershed method. This hybridization process is first of all started by segmenting the input image using fuzzy c-means algorithm which is a clustering method that gives the possibility to a pixel to belong to one or more clusters. After that, we will apply multi-Otsu which is a thresholding algorithm that separates the pixels of an image into a variety of classes depending on the intensity of the gray levels. The next step of this proposed method is the marker-controlled watershedalgorithm that divides the image into homogenous areas or regions by using edge-detection concepts including mathematical morphology. The proposed technique was applied and experienced using several images of different types of skin cancer that were collected and gathered from the web and also from the Kaggle dataset. To assess the worth of the achieved results, we used several evaluation metrics like dice coefficient, sensitivity, specificity as well as Jaccard similarity that all have shown good and satisfactory results.

Estimation of leaf area using watershed and ellipse fitting methods for spinach cultivation images

Estimation of leaf area using watershed and ellipse fitting methods for spinach cultivation images

Removing non-nuclei information from histopathological images: A preprocessing step towards improving nuclei segmentation methods

Disease interpretation by computer-aided diagnosis systems in digital pathology depends on reliable detection and segmentation of nuclei in hematoxylin and eosin (HE) images. These 2 tasks are challenging since appearance of both cell nuclei and background structures are very variable. This paper presents a method to improve nuclei detection and segmentation in HE images by removing tiles that only contain background information. The method divides each image into smaller patches and uses their projection to the noiselet space to capture different spatial features from non-nuclei background and nuclei structures. The noiselet features are clustered by a K-means algorithm and the resultant partition, defined by the cluster centroids, is herein named the noiselet code-book. A part of an image, a tile, is divided into patches and represented by the histogram of occurrences of the projected patches in the noiselet code-book. Finally, with these histograms, a classifier learns to differentiate between nuclei and non-nuclei tiles. By applying a conventional watershed-marked method to detect and segment nuclei, evaluation consisted in comparing pure watershed method against denoising-plus-watershed in an open database with 8 different types of tissues. The averaged F-score of nuclei detection improved from 0.830 to 0.86 and the dice score after segmentation increased from 0.701 to 0.723.

Improved Procedure for the 3D Reconstruction of Asphalt Concrete Mesostructures Considering the Similarity of Aggregate Phase Geometry between Adjacent CT Slices.

Existing image segmentation algorithms used for the computed tomography (CT) images of asphalt concrete mostly ignore the similarity of aggregate phase geometry between adjacent CT slices, thus increasing the variability in the aggregate phase pixel values between adjacent slices and leading to a large number of model defects, e.g., interconnected aggregates, flaky aggregates, and incomplete aggregates. The developed mesostructural models with these defects pose a challenge to following simulation operations. To address this issue, an improved procedure for the 3D reconstruction of asphalt concrete mesostructures considering the similarity of aggregate phase geometry between adjacent slices was developed, which includes two adjacent-slice pixel-value-correction algorithms, a multi-directional multiple-correction method, and an image pixel interpolation process. First, the bilinear interpolation algorithm was employed to improve the pixel density of 2D CT images and the average filtering algorithm was used to reduce the noise of the CT images. Subsequently, the OTSU method was employed to separate the asphalt mortar matrix phase from the aggregate phase, and the marker-based watershed segmentation method was used to separate the interconnected aggregates. Finally, the adjacent-slice pixel-value-correction algorithm was used to recover the similarity of aggregate phase geometry between adjacent CT slices, and the multi-directional multiple-correction method was used to further enhance the geometric similarity. The results show that the developed 3D reconstruction procedure removes most of the model defects in the 3D mesostructural model of asphalt concrete, thus realistically maintaining the 3D spatial distribution features and contour characteristics.

Aneurysm Neck Overestimation has a Relatively Modest Impact on Simulated Hemodynamics.

Overestimation of intracranial aneurysm neck width by 3D angiography is a recognized clinical problem, and has long been a concern for image-based computational fluid dynamics (CFD). Recently, it was demonstrated that neck overestimation in 3D rotational angiography (3DRA) could be corrected via segmentation with upsampled resolution and gradient enhancement (SURGE). Our aim was to leverage this approach to determine whether and how neck overestimation actually impacts CFD-derived hemodynamics. A subset of 17 cases having the largest neck errors from a consecutive clinical sample of 60 was segmented from 3DRA using both standard watershed and SURGE methods. High-fidelity, pulsatile CFD was performed, and a variety of scalar hemodynamic parameters that have been associated with aneurysm growth and/or rupture status were derived. With a few exceptions, flow and wall shear stress (WSS) patterns were qualitatively similar between neck-overestimated and corrected models. Sac-averaged WSS values were significantly lower after neck correction (p = 0.0005) but were highly correlated with their neck-overestimated counterparts (R2 = 0.98). Jet impingement was significantly more concentrated in the neck-corrected vs. -uncorrected models (p = 0.0011), and only moderately correlated (R2 = 0.61). Parameters quantifying velocity or WSS fluctuations were not significantly different after neck correction, but this reflected their poorer correlations (R2 < 0.4). Nevertheless, for all hemodynamic parameters, median absolute differences were < 26%, and no parameter had more than 5/17 cases with absolute differences > 50%. Differences in hemodynamicsdue to neck width overestimationwere found to be at most equal to, and often less than, those reported for other sources of error/uncertainty in intracranial aneurysm CFD, such as solver settings or assumed inflow rates.