Watershed-based Segmentation Research Articles

An Image-based method for evaluating changes in particle size and morphology distributions of aggregate materials after vibratory compaction test

Particle breakage and abrasion of aggregate materials can be induced by field compaction during construction, which adversely affects their mechanical properties. However, current compaction quality control testing does not evaluate changes in particle size distribution and particle morphology of aggregate materials due to the lack of fast and inexpensive testing methods. In this study, a modified watershed-based segmentation image analysis method and computational geometry algorithms were used to quickly quantify changes in particle size and morphology distributions of a large amount of contacting aggregate particles. The accuracy and required minimum sample size of the image analysis method were statistically evaluated. Compared to the conventional ASTM C136 aggregate sieve analysis test, the image analysis method conducted on a 40% sample size of the conventional method yielded less than 6% difference between the results, which can meet the ASTM C136 test repeatability criteria. In addition, demonstration tests were conducted to incorporate the image analysis method into a laboratory vibratory compaction test for evaluating the overall particle size and morphology changes of an aggregate material after compaction. Results indicate that the initial gradation and water content of the aggregate material can influence the particle breakage and abrasion characteristics of aggregate materials under compaction.

Hybrid classification framework for chronic kidney disease prediction model

ABSTRACT ‘Chronic kidney disease (CKD) – or chronic renal failure (CRF) is a term that encompasses all degrees of decreased kidney function, from damaged–at risk through mild, moderate, and severe chronic kidney failure’. As a risky factor, the disease has steadily turned out to be a major cause of death and morbidity. Accordingly, ultrasound (US) is significant in enhancing the rates of early recognition of CKD. Here, a new CKD detection model is introduced that includes ‘(1) Pre-processing (2) segmentation (3) Feature extraction, and (4) Classification’. Improved Gaussian filtering is used for pre-processing, and watershed-based segmentation is carried out. Additionally, features like the ROI, mean intensity, and the projected Local Vector Pattern (LVP) are retrieved. The ‘Optimized Neural Network (NN) and Long Short-Term Memory (LSTM)’ are then provided the output of the features. Additionally, using Self Updated Cat Swarm Optimization, the weights of NN are adjusted in order to increase the classifier's prediction accuracy (SU-CSO). The categorized output is then calculated by averaging the results from the improved NN and LSTM. Lastly, it is demonstrated that the proposed strategy is superior to other options.

A Novel Segmentation Recognition Algorithm of Agaricus bisporus Based on Morphology and Iterative Marker-Controlled Watershed Transform

Accurate recognition of Agaricus bisporus is a prerequisite for precise automatic harvesting in a factory environment. Aimed at segmenting mushrooms adhering together from the complex background, this paper proposes a watershed-based segmentation recognition algorithm for A. bisporus. First, the foreground of A. bisporus is extracted via Otsu threshold segmentation and morphological operations. Then, a preliminary segmentation algorithm and a novel iterative marker generation method are proposed to prepare watershed markers. On this basis, a marker-controlled watershed algorithm is adopted to segment and recognize A. bisporus individuals. All the algorithms are implemented based on OpenCV (Open Source Computer Vision) libraries. Tests on images of A. bisporus collected at the cultivation bed show that the average correct recognition rate of the proposed algorithm is 95.7%, the average diameter measurement error is 1.15%, and the average coordinate deviation rate is 1.43%. The average processing time is 705.7 ms per single image, satisfying the real-time constraints based on 1 image/s. The proposed algorithm performed better than the current Circle Hough Transform (OpenCV’s implementation). It is convenient and easy to operate, providing a sound basis for subsequent research on mechanized harvesting equipment for A. bisporus.

A high-throughput semi-automated bone segmentation workflow for murine hindpaw micro-CT datasets

IntroductionMicro-computed tomography (μCT) is a valuable imaging modality for longitudinal quantification of bone volumes to identify disease or treatment effects for a broad range of conditions that affect bone health. Complex structures, such as the hindpaw with up to 31 distinct bones in mice, have considerable analytic potential, but quantification is often limited to a single bone volume metric due to the intensive effort of manual segmentation. Herein, we introduce a high-throughput, user-friendly, and semi-automated method for segmentation of murine hindpaw μCT datasets. MethodsIn vivo μCT was performed on male (n = 4; 2–8-months) and female (n = 4; 2–5-months) C57BL/6 mice longitudinally each month. Additional 9.5-month-old male C57BL/6 hindpaws (n = 6 hindpaws) were imaged by ex vivo μCT to investigate the effects of resolution and integration time on analysis outcomes. The DICOMs were exported to Amira software for the watershed-based segmentation, and watershed markers were generated automatically at approximately 80% accuracy before user correction. The semi-automated segmentation method utilizes the original data, binary mask, and bone-specific markers that expand to the full volume of the bone using watershed algorithms. ResultsCompared to the conventional manual segmentation using Scanco software, the semi-automated approach produced similar raw bone volumes. The semi-automated segmentation also demonstrated a significant reduction in segmentation time for both experienced and novice users compared to standard manual segmentation. ICCs between experienced and novice users were >0.9 (excellent reliability) for all but 4 bones. DiscussionThe described semi-automated segmentation approach provides remarkable reliability and throughput advantages. Adoption of the semi-automated segmentation approach will provide standardization and reliability of bone volume measures across experienced and novice users and between institutions. The application of this model provides a considerable strategic advantage to accelerate various research opportunities in pre-clinical bone and joint analysis towards clinical translation.

Validation of watershed-based segmentation of the cartilage surface from sequential CT arthrography scans.

This study investigated the utility of a 2-dimensional watershed algorithm for identifying the cartilage surface in computed tomography (CT) arthrograms of the knee up to 33 minutes after an intra-articular iohexol injection as boundary blurring increased. A 2D watershed algorithm was applied to CT arthrograms of 3 bovine stifle joints taken 3, 8, 18, and 33 minutes after iohexol injection and used to segment tibial cartilage. Thickness measurements were compared to a reference standard thickness measurement and the 3-minute time point scan. 77.2% of cartilage thickness measurements were within 0.2 mm (1 voxel) of the thickness calculated in the reference scan at the 3-minute time point. 42% fewer voxels could be segmented from the 33-minute scan than the 3-minute scan due to diffusion of the contrast agent out of the joint space and into the cartilage, leading to blurring of the cartilage boundary. The traced watershed lines were closer to the location of the cartilage surface in areas where tissues were in direct contact with each other (cartilage-cartilage or cartilage-meniscus contact). The use of watershed dam lines to guide cartilage segmentation shows promise for identifying cartilage boundaries from CT arthrograms in areas where soft tissues are in direct contact with each other.

The Global Water Body Layer from TanDEM-X Interferometric SAR Data

The interferometric synthetic aperture radar (InSAR) data set, acquired by the TanDEM-X (TerraSAR-X add-on for Digital Elevation Measurement) mission (TDM), represents a unique data source to derive geo-information products at a global scale. The complete Earth’s landmasses have been surveyed at least twice during the mission bistatic operation, which started at the end of 2010. Examples of the delivered global products are the TanDEM-X digital elevation model (DEM) (at a final independent posting of 12 m × 12 m) or the TanDEM-X global Forest/Non-Forest (FNF) map. The need for a reliable water product from TanDEM-X data was dictated by the limited accuracy and difficulty of use of the TDX Water Indication Mask (WAM), delivered as by-product of the global DEM, which jeopardizes its use for scientific applications, as well. Similarly as it has been done for the generation of the FNF map; in this work, we utilize the global data set of TanDEM-X quicklook images at 50 m × 50 m resolution, acquired between 2011 and 2016, to derive a new global water body layer (WBL), covering a range from −60∘ to +90∘ latitudes. The bistatic interferometric coherence is used as the primary input feature for performing water detection. We classify water surfaces in single TanDEM-X images, by considering the system’s geometric configuration and exploiting a watershed-based segmentation algorithm. Subsequently, single overlapping acquisitions are mosaicked together in a two-step logically weighting process to derive the global TDM WBL product, which comprises a binary averaged water/non-water layer as well as a permanent/temporary water indication layer. The accuracy of the new TDM WBL has been assessed over Europe, through a comparison with the Copernicus water and wetness layer, provided by the European Space Agency (ESA), at a 20 m × 20 m resolution. The F-score ranges from 83%, when considering all geocells (of 1∘ latitudes × 1∘ longitudes) over Europe, up to 93%, when considering only the geocells with a water content higher than 1%. At global scale, the quality of the product has been evaluated, by intercomparison, with other existing global water maps, resulting in an overall agreement that often exceeds 85% (F-score) when the content in the geocell is higher than 1%. The global TDM WBL presented in this study will be made available to the scientific community for free download and usage.

Computational pathology reveals unique spatial patterns of immune response in H&E images from COVID-19 autopsies: preliminary findings.

Purpose: We used computerized image analysis and machine learning approaches to characterize spatial arrangement features of the immune response from digitized autopsied H&E tissue images of the lung in coronavirus disease 2019 (COVID-19) patients. Additionally, we applied our approach to tease out potential morphometric differences from autopsies of patients who succumbed to COVID-19 versus H1N1. Approach: H&E lung whole slide images from autopsy specimens of nine COVID-19 and two H1N1 patients were computationally interrogated. 606 image patches ( per patient) of were extracted from the 11 autopsied patient studies. A watershed-based segmentation approach in conjunction with a machine learning classifier was employed to identify two types of nuclei families: lymphocytes and non-lymphocytes (i.e., other nucleated cells such as pneumocytes, macrophages, and neutrophils). Based off the proximity of the individual nuclei, clusters for each nuclei family were constructed. For each of the resulting clusters, a series of quantitative measurements relating to architecture and density of nuclei clusters were calculated. A receiver operating characteristics-based feature selection method, violin plots, and the t-distributed stochastic neighbor embedding algorithm were employed to study differences in immune patterns. Results: In COVID-19, the immune response consistently showed multiple small-size lymphocyte clusters, suggesting that lymphocyte response is rather modest, possibly due to lymphocytopenia. In H1N1, we found larger lymphocyte clusters that were proximal to large clusters of non-lymphocytes, a possible reflection of increased prevalence of macrophages and other immune cells. Conclusion: Our study shows the potential of computational pathology to uncover immune response features that may not be obvious by routine histopathology visual inspection.

Research on Detection Technology for the Changes of Buildings by High Resolution Remote Sensing Image

Remote sensing is one of the most effective monitoring technologies for space change at home and abroad. This paper was designed to investigate the application methods of aerial and space remote sensing techniques in urban building change monitoring. It also proposed an urban spatial data updating method combining the InSAR technology and aerospace remote sensing for large-scale data updating and aerial photogrammetry technology for small-scale key data updating. Through simulation experiments of watershed-based image recognition and monitoring, observation and comparison, this paper adopted a watershed-based segmentation algorithm for GPU and its application to change recognition of urban building images.

Geometrical-Based Generative Adversarial Network to Enhance Digital Rock Image Quality

X-ray microcomputed tomography (micro-CT) is a common tool for the study of porous media structures and properties. High-quality micro-CT data are required to accurately capture pore structures. Acquiring high-quality micro-CT data, however, is not always possible, owing to application limitations and experimental constraints. Therefore, we propose a geometrical-based generative adversarial network (GAN) to rapidly restore noisy micro-CT images to their clean counterparts. The training data and related ground-truth (GT) data are scanned for 7 min and 9.5 h, respectively. To evaluate the performance of the geometrical-based GAN, a ${600}^{3}$ voxel image that has never been used for training is reconstructed and compared with the corresponding GT image. Histogram matching and linear normalization are implemented to adjust the histogram of the reconstructed image to that of the GT image. A watershed-based segmentation method is then applied to delineate pore and solid phases. Lastly, we measure the Minkowski functionals and petrophysical properties, including absolute permeability, pore size distribution, drainage capillary pressure-saturation curve, and imbibition relative permeability, to estimate the physical accuracy of the denoised image. The results show that the proposed geometrical-based GAN can accurately restore noisy micro-CT data. By reducing the scanning time from 9.5 h to 7 min, the expenditure of collecting micro-CT can be decreased significantly. This is particularly important for applications where time-lapse images of a dynamic process are required, high-throughput imaging is necessary for real-time data analysis, or where the quantification of large sample volumes is required.

Deep Learning-Based Masonry Wall Image Analysis

In this paper we introduce a novel machine learning-based fully automatic approach for the semantic analysis and documentation of masonry wall images, performing in parallel automatic detection and virtual completion of occluded or damaged wall regions, and brick segmentation leading to an accurate model of the wall structure. For this purpose, we propose a four-stage algorithm which comprises three interacting deep neural networks and a watershed transform-based brick outline extraction step. At the beginning, a U-Net-based sub-network performs initial wall segmentation into brick, mortar and occluded regions, which is followed by a two-stage adversarial inpainting model. The first adversarial network predicts the schematic mortar-brick pattern of the occluded areas based on the observed wall structure, providing in itself valuable structural information for archeological and architectural applications. The second adversarial network predicts the pixels’ color values yielding a realistic visual experience for the observer. Finally, using the neural network outputs as markers in a watershed-based segmentation process, we generate the accurate contours of the individual bricks, both in the originally visible and in the artificially inpainted wall regions. Note that while the first three stages implement a sequential pipeline, they interact through dependencies of their loss functions admitting the consideration of hidden feature dependencies between the different network components. For training and testing the network a new dataset has been created, and an extensive qualitative and quantitative evaluation versus the state-of-the-art is given. The experiments confirmed that the proposed method outperforms the reference techniques both in terms of wall structure estimation and regarding the visual quality of the inpainting step, moreover it can be robustly used for various different masonry wall types.

MtreeRing: An R package with graphical user interface for automatic measurement of tree ring widths using image processing techniques

Accurate measurements of ring-width series are essential for dendrochronological analyses. We present an R package MtreeRing for ring-width measurements on scanned digital images. A morphological alternate sequential filter is used for noise reduction in the original image. Ring boundaries are determined by the steepest negative slopes in the light reflectance of latewood-earlywood transitions. To automatically identify tree rings, the package provides three alternative methods (watershed-based segmentation, Canny edge detector, and a linear detection algorithm), each with advantages and disadvantages and suited to different wood anatomical features. The user can also manually mark tree rings on species with complex anatomical structures. The arcs of inner-rings and angles of successive inclined ring boundaries are used to correct ring-width series. Differences in ring-width measurements between MtreeRing and WinDENDRO in a given coniferous species (Larix gmelinii) were assessed, and no significant difference between programs was found. Furthermore, the package provides an R-based web application which was developed using the Shiny framework. This beginner-friendly application allows viewing and interacting with tree ring images. It requires no programming experience and can run on either a local computer or a remote server.

A deep learning-based algorithm for 2-D cell segmentation in microscopy images

BackgroundAutomatic and reliable characterization of cells in cell cultures is key to several applications such as cancer research and drug discovery. Given the recent advances in light microscopy and the need for accurate and high-throughput analysis of cells, automated algorithms have been developed for segmenting and analyzing the cells in microscopy images. Nevertheless, accurate, generic and robust whole-cell segmentation is still a persisting need to precisely quantify its morphological properties, phenotypes and sub-cellular dynamics.ResultsWe present a single-channel whole cell segmentation algorithm. We use markers that stain the whole cell, but with less staining in the nucleus, and without using a separate nuclear stain. We show the utility of our approach in microscopy images of cell cultures in a wide variety of conditions. Our algorithm uses a deep learning approach to learn and predict locations of the cells and their nuclei, and combines that with thresholding and watershed-based segmentation. We trained and validated our approach using different sets of images, containing cells stained with various markers and imaged at different magnifications. Our approach achieved a 86% similarity to ground truth segmentation when identifying and separating cells.ConclusionsThe proposed algorithm is able to automatically segment cells from single channel images using a variety of markers and magnifications.

Automatic extraction of endocranial surfaces from CT images of crania.

The authors present a method for extracting polygon data of endocranial surfaces from CT images of human crania. Based on the fact that the endocast is the largest empty space in the crania, we automate a procedure for endocast extraction by integrating several image processing techniques. Given CT images of human crania, the proposed method extracts endocranial surfaces by the following three steps. The first step is binarization in order to fill void structures, such as diploic space and cracks in the skull. We use a void detection method based on mathematical morphology. The second step is watershed-based segmentation of the endocranial part from the binary image of the CT image. Here, we introduce an automatic initial seed assignment method for the endocranial region using the distance field of the binary image. The final step is partial polygonization of the CT images using the segmentation results as mask images. The resulting polygons represent only the endocranial part, and the closed manifold surfaces are computed even though the endocast is not isolated in the cranium. Since only the isovalue threshold and the size of void structures are required, the procedure is not dependent on the experience of the user. The present paper also demonstrates that the proposed method can extract polygon data of endocasts from CT images of various crania.

Marker-Controlled Watershed-Based Segmentation of Multiresolution Remote Sensing Images

A new technique for the segmentation of single- and multiresolution (MR) remote sensing images is proposed. To guarantee the preservation of details at fine scales, edge-based watershed is used, with automatically generated markers that help in limiting oversegmentation. For MR images, the panchromatic and multispectral components are processed independently, extracting both the edge maps and the morphological and spectral markers that are eventually fused at the highest resolution, thus avoiding any information loss induced by pansharpening. Numerical results on object layer extraction and simple classification tasks prove the proposed techniques to provide accurate segmentation maps, which preserve fine details and, contrary to state-of-the-art products, can single out objects equally well at very different scales.

Adaptive Restoration of Multispectral Datasets used for SVM classification

Removing noise from images while keeping its important details unchanged is a challenging issue in image restoration. In this paper, we propose a novel approach based on partial differential equations (PDE) in order to mitigate three well-known types of noises from remote sensing data while important features such as edges are preserved. In the presented method, after performing the Watershed-based segmentation as a preprocessing step, optimum values of PDE parameters are adaptively found based on the noise type and the image texture. In order to evaluate the performance of the proposed algorithm, Peak Signal-to-Noise Ratio (PSNR) criterion is applied. Moreover, feeding the original/noisy/denoised images into SVM classifier and exploring the classification ratios are suggested as an application-based assessment. The gained results prove a considerable enhancement both in quantitative metrics (PSNR and MSE) and SVM classification ratios (from 71.71% to 95.07%).

Fast X-ray Micro-Tomography of Multiphase Flow in Berea Sandstone: A Sensitivity Study on Image Processing

Synchrotron-based fast micro-tomography is the method of choice to observe in situ multiphase flow and displacement dynamics on the pore scale. However, the image processing workflow is sensitive to a suite of manually selected parameters which can lead to ambiguous results. In this work, the relationship between porosity and permeability in response to systematically varied gray-scale threshold values was studied for different segmentation approaches on a dataset of Berea sandstone at a voxel length of 3 \(\upmu \)m. For validation of the image processing workflow, porosity, permeability, and capillary pressure were compared to laboratory measurements on a larger-sized core plug of the same material. It was found that for global thresholding, minor variations in the visually permissive range lead to large variations in porosity and even larger variations in permeability. The latter is caused by changes in the pore-scale flow paths. Pore throats were found to be open for flow at large thresholds but closed for smaller thresholds. Watershed-based segmentation was found to be significantly more robust to manually chosen input parameters. Permeability and capillary pressure closely match experimental values; for capillary pressure measurements, the plateau of calculated capillary pressure curves was similar to experimental curves. Modeling on structures segmented with hysteresis thresholding was found to overpredict experimental capillary pressure values, while calculated permeability showed reasonable agreement to experimental data. This demonstrates that a good representation of permeability or capillary pressure alone is not a sufficient quality criterion for appropriate segmentation, but the data should be validated with both parameters. However, porosity is the least reliable quality criterion. In the segmented images, always a lower porosity was found compared to experimental values due to micro-porosity below the imaging resolution. As a result, it is recommended to base the validation of image processing workflows on permeability and capillary pressure and not on porosity. Decane-brine distributions from a multiphase flow experiment were modeled in a thus validated \(\upmu \)-CT pore space using a morphological approach which captures only capillary forces. A good overall correspondence was found when comparing (capillary-controlled) equilibrium fluid distributions before and after pore-scale displacement events.

A New Method for Sperm Characterization for Infertility Treatment: Hypothesis Testing by Using Combination of Watershed Segmentation and Graph Theory

Shape and movement features of sperms are important parameters for infertility study and treatment. In this article, a new method is introduced for characterization sperms in microscopic videos. In this method, first a hypothesis framework is defined to distinguish sperms from other particles in captured video. Then decision about each hypothesis is done in following steps: Selecting some primary regions as candidates for sperms by watershed-based segmentation, pruning of some false candidates during successive frames using graph theory concept and finally confirming correct sperms by using their movement trajectories. Performance of the proposed method is evaluated on real captured images belongs to semen with high density of sperms. The obtained results show the proposed method may detect 97% of sperms in presence of 5% false detections and track 91% of moving sperms. Furthermore, it can be shown that better characterization of sperms in proposed algorithm doesn't lead to extracting more false sperms compared to some present approaches.

Height-Height Correlation Function to Determine Grain Size in Iron Phthalocyanine Thin Films

Quasi one-dimensional iron chains are formed in thermally evaporated iron phthalocyanine (FeC32N8H16) thin films on silicon substrates. The chain length is modified by the deposition temperature during growth. Atomic force microscopy images show spherical grains at low deposition temperatures that become highly elongated at high deposition temperatures due to diffusion. The grain distributions are quantitatively characterized with a watershed-based segmentation algorithm and a height-height correlation function. The grain size distributions are found to be characteristically distinct for the α-phase and β-phase samples. The average effective grain size from the distribution is proportional to the correlation length found from the height-height correlation function and grows exponentially with deposition temperature. The long-range roughness and Hurst parameter increase only slightly with the deposition temperature.

Analysis of Scalar Maps for the Segmentation of the Corpus Callosum in Diffusion Tensor Fields

Diffusion tensor imaging (DTI) is a powerful technique for imaging axonal anatomy in vivo and its automatic segmentation is important for quantitative analysis and visualization. Application of the watershed transform is a recent approach for robustly segmenting diffusion tensor images. Since an important step of the watershed-based segmentation is the gradient computation, this paper investigates scalar maps from DTI and their ability to enhance borders and, therefore, their usefulness in gradient calculation. A comparison between existing scalar maps is conducted in the context of segmentation. New diffusion scalar maps, inspired by mathematical morphology concepts are proposed and included in the comparison. The watershed transform is then applied to segment the corpus callosum, based on the computed scalar maps.

A novel segmentation method for breast ultrasound images based on neutrosophic l‐means clustering

Fully automatic and accurate breast lesion segmentation is an essential and challenging task. In this paper, the authors develop a novel, effective, and fully automatic method for breast ultrasound (BUS) image segmentation. The segmentation method utilizes a novel phase feature to improve the image quality, and a novel neutrosophic clustering approach to detect the accurate lesion boundary. First, a region of interest is generated to cut off complex background. After speckle reduction, an enhancement algorithm based on phase in max-energy orientation (PMO) is developed to further improve the image quality. The PMO is a newly proposed 2D phase feature obtained by filtering the image in the frequency domain and calculating the phase accumulation in the orientation with maximum energy. Finally, the authors propose a novel clustering approach called neutrosophic l-means (NLM) to detect the lesion boundary. NLM is a generalized clustering method that can be used to solve other clustering problems as well. In this paper, NLM is used to segment images with vague boundaries, and to deal with uncertainty better. To evaluate the performance of the proposed method, the authors compare it with the traditional fuzzy c-means clustering, active contour, level set, and watershed-based segmentation methods, using a common database. Radiologist's manual delineations are used as the golden standards. Five assessment metrics are utilized to evaluate the performance from different aspects. Both accuracy and efficiency are analyzed. Sensitivity analysis is also conducted to test the robustness of the proposed method. Compared with the other methods, the proposed method generates the most similar boundaries to the radiologist's manual delineations (TP rate is 92.4%, FP rate is 7.2%, and similarity rate is 86.3%; Hausdorff distance is 22.5 pixels and mean absolute distance is 4.8 pixels), with efficient processing speed (averagely 9.8 s per image). Sensitivity analysis shows the robustness of the proposed method as well. The proposed method is a fully automatic segmentation method for BUS images that can generate accurate lesion boundaries even for complicated cases. The fast processing speed, robustness, and accuracy of the proposed method suggest its potential applications in clinics.