Mathematical Morphology Approach Research Articles

ViCE: An automated and quantitative program to assess intestinal tissue morphology

Background and objectiveThe tissue morphology of the intestinal surface is architecturally complex with finger-like projections called villi, and glandular structures called crypts. The ratio of villus height-to-crypt depth ratio (Vh:Cd) is used to quantitatively assess disease severity and response to therapy for intestinal enteropathies, such as celiac disease and is currently quantified manually. Given the time required, manual Vh:Cd measurements have largely been limited to clinical trials and are not used widely in clinical practice. We developed ViCE (Villus Crypt Evaluator), a user-friendly software that automatically quantifies histological parameters in standard hematoxylin and eosin-stained intestinal biopsies. MethodsViCE is based on mathematical morphology operations and is scale and staining agnostic. It evaluates tissue orientation, identifies geometrical structure, and outputs key tissue measurements. ResultsThe output measurements of Vh:Cd are concordant with manual quantifications across multiple datasets. ConclusionsThe underlying mathematical morphological approach for ViCE is robust, and reproducible and easily adaptable for measurement of morphological features in other tissues.

Field programmable gate array based moving object tracking system for robot navigation

This paper proposes a method in which an object tracking robot system is implemented on field programmable gate arrays (FPGAs). The OV7670 camera provides real-time object pictures to the system. To improve picture quality, images are put via the median filter phase. The item is distinguished from the backdrop based on color (red), after which it is subjected to a mathematical morphological approach of filtering to eliminate noise. To send the robot control signals, the object's (new) coordinates are found. In this method, the median filter, color separation, hardware IP cores, and morphological filter are all part of the embedded system on FPGA. Through the direct memory access (DMA) controller, these cores may communicate and perform high-speed pipeline computing at higher data rates. The entire system is executed in real-time on Xilinx's spartan-6 FPGA KIT. The results show practical and promise.

Investigating metropolitan change through mathematical morphology and a dynamic factor analysis of structural and functional land-use indicators

We presented an operational rationale grounded on complex system thinking to quantify structural and functional landscape transformations along three stages representative of post-war metropolitan development in Rome, Italy (urbanisation with population/settlement densification, 1949–1974; suburbanisation with medium-density settlement expansion, 1974–1999; counter-urbanisation with settlement sprawl, 1999–2016). A mathematical morphology approach assessing the geometric form of land patches and a multi-way factor analysis (MFA) of landscape metrics were used to investigate the joint evolution of urban form and land-use functions over time. The empirical results of the MFA delineated the multivariate relationship between nine land-use classes (with distinctive socioeconomic functions) and seven morphological types (reflecting different landscape structures) according to four observation times (1949, 1974, 1999, 2016). Taken as an intrinsic attribute of complex landscape systems experiencing intense transformations, an estimation of the ‘rapidity-of-change’ in the form-functions relationship at a given development stage was derived from MFA outcomes separately for urbanisation, suburbanisation, and counter-urbanisation. A simplified form-functions relationship, reflecting the spatial polarisation in compact settlements and rural (low-density) landscapes, was observed with compact urbanisation. By stimulating urban sprawl into fringe farmland, suburbanisation resulted in patchy and heterogeneous rural landscapes. Counter-urbanization was associated with the fragmentation of built-up settlements leading to a chaotic mosaic of land structures that mixes urban and rural traits. Rapidity-of-change in form-function relationships was greater during suburbanisation than urbanisation and counter-urbanisation. It reflects the intrinsic pressure of economic growth in contemporary cities.

Spatial Profiles of Intratumoral PD-1+ Helper T Cells Predict Prognosis in Head and Neck Squamous Cell Carcinoma.

BackgroundFunctional interactions between immune cells and neoplastic cells in the tumor immune microenvironment have been actively pursued for both biomarker discovery for patient stratification, as well as therapeutic anti-cancer targets to improve clinical outcomes. Although accumulating evidence indicates that intratumoral infiltration of immune cells has prognostic significance, limited information is available on the spatial infiltration patterns of immune cells within intratumoral regions. This study aimed to understand the intratumoral heterogeneity and spatial distribution of immune cell infiltrates associated with cell phenotypes and prognosis in head and neck squamous cell carcinoma (HNSCC).MethodsA total of 88 specimens of oropharyngeal squamous cell carcinoma, categorized into discovery (n = 38) and validation cohorts (n = 51), were analyzed for immune contexture by multiplexed immunohistochemistry (IHC) and image cytometry-based quantification. Tissue segmentation was performed according to a mathematical morphological approach using neoplastic cell IHC images to dissect intratumoral regions into tumor cell nests versus intratumoral stroma.ResultsTissue segmentation revealed heterogeneity in intratumoral T cells, varying from tumor cell nest-polarized to intratumoral stroma-polarized distributions. Leukocyte composition analysis revealed higher ratios of TH1/TH2 in tumor cell nests with higher percentages of helper T cells, B cells, and CD66b+ granulocytes within intratumoral stroma. A discovery and validation approach revealed a high density of programmed death receptor-1 (PD-1)+ helper T cells in tumor cell nests as a negative prognostic factor for short overall survival. CD163+ tumor-associated macrophages (TAM) provided the strongest correlation with PD-1+ helper T cells, and cases with a high density of PD-1+ helper T cells and CD163+ TAM had a significantly shorter overall survival than other cases.ConclusionThis study reveals the significance of analyzing intratumoral cell nests and reports that an immune microenvironment with a high density of PD-1+ helper T cells in tumoral cell nests is a poor prognostic factor for HNSCC.

Automated Object Detection for Visual Inspection of Nuclear Reactor Cores

Remote visual inspection is a common approach to understanding the health of key components and substructures within nuclear power plants, particularly in difficult to access and high dosage areas. Interpretation of inspection footage is a manually intensive procedure and challenges arise in localizing and dimensioning defects directly from a video feed, which may be subject to uncertainty from a range of sources such as lens distortion, nonuniform lighting, and lack of depth from a monocular camera system. A common approach to addressing these issues is to develop a scaling factor based on identifying a reference object of known dimensions in the image and using this to size regions of interest. Manual, accurate identification of these reference objects is onerous, time consuming, and prone to variation across different human experts, therefore, robust identification of suitable reference objects in an automated, reliable, and repeatable manner is of significant value. In this paper we evaluate two approaches for the automated detection of reference objects in the inspection of graphite cores in the United Kingdom’s fleet of advanced gas-cooled reactors (AGRs). The first method is a multistep approach using tools from mathematical morphology. The approach uses a genetic algorithm to “grow” suitable structuring elements, refine the order of operations, and remove operations proposed by the human designer that have a negative impact on performance. The second approach uses semantic segmentation, a technique which is normally applied to scene labeling in computer vision applications, applied to produce a binary mask, separating the reference object from the background. We show that this second method performs significantly better than the mathematical morphology approach when applied to the identification of brick interface keyways in AGR inspection images. Though improved in terms of accuracy, it is recognized that a greater initial effort is required to train the approach, and as it utilizes black-box neural network approaches, the greater transparency offered by the mathematical morphology approach is lost. While explicability of techniques is often a highly desirable characteristic of automated analysis techniques applied to health assessment within nuclear power plants, the results of the reference object detection can be made explicit to the end user, ensuring that the human analyst is retained within the decision-making process thus mitigating the need for transparency.

Segmentation by an Improved Mathematical Morphology Approach

Segmentation by an Improved Mathematical Morphology Approach

Hard exudate detection based on deep model learned information and multi-feature joint representation for diabetic retinopathy screening

Background and objective: Diabetic retinopathy (DR), which is generally diagnosed by the presence of hemorrhages and hard exudates, is one of the most prevalent causes of visual impairment and blindness. Early detection of hard exudates (HEs) in color fundus photographs can help in preventing such destructive damage. However, this is a challenging task due to high intra-class diversity and high similarity with other structures in the fundus images. Most of the existing methods for detecting HEs are based on characterizing HEs using hand crafted features (HCFs) only, which can not characterize HEs accurately. Deep learning methods are scarce in this domain because they require large-scale sample sets for training which are not generally available for most routine medical imaging research.Methods: To address these challenges, we propose a novel methodology for HE detection using deep convolutional neural network (DCNN) and multi-feature joint representation. Specifically, we present a new optimized mathematical morphological approach that first segments HE candidates accurately. Then, each candidate is characterized using combined features based on deep features with HCFs incorporated, which is implemented by a ridge regression-based feature fusion. This method employs multi-space-based intensity features, geometric features, a gray-level co-occurrence matrix (GLCM)-based texture descriptor, a gray-level size zone matrix (GLSZM)-based texture descriptor to construct HCFs, and a DCNN to automatically learn the deep information of HE. Finally, a random forest is employed to identify the true HEs among candidates.Results: The proposed method is evaluated on two benchmark databases. It obtains an F-score of 0.8929 with an area under curve (AUC) of 0.9644 on the e-optha database and an F-score of 0.9326 with an AUC of 0.9323 on the HEI-MED database. These results demonstrate that our approach outperforms state-of-the-art methods. Our model also proves to be suitable for clinical applications based on private clinical images from a local hospital.Conclusions: This newly proposed method integrates the traditional HCFs and deep features learned from DCNN for detecting HEs. It achieves a new state-of-the-art in both detecting HEs and DR screening. Furthermore, the proposed feature selection and fusion strategy reduces feature dimension and improves HE detection performance.

A High-Accuracy Mathematical Morphology and Multilayer Perceptron-Based Approach for Melanoma Detection

According to the World Health Organization (WHO), melanoma is the most severe type of skin cancer and is the leading cause of death from skin cancer worldwide. Certain features of melanoma include size, shape, color, or texture changes of a mole. In this work, a novel, robust and efficient method for the detection and classification of melanoma in simple and dermatological images is proposed. It is achieved by using HSV (Hue, Saturation, Value) color space along with mathematical morphology and a Gaussian filter to detect the region of interest and estimate four descriptors: symmetry, edge, color, and size. Although these descriptors have been used for several years, the way they are computed for this proposal is one of the things that enhances the results. Subsequently, a multilayer perceptron is employed to classify between malignant and benign melanoma. Three datasets of simple and dermatological images commonly used in the literature were employed to train and evaluate the performance of the proposed method. According to k-fold cross-validation, the method outperforms three state-of-art works, achieving an accuracy of 98.5% and 98.6%, a sensitivity of 96.68% and 98.05%, and a specificity of 98.15%, and 98.01%, in simple and dermatological images, respectively. The results have proven that its use as an assistive device for the detection of melanoma would improve reliability levels compared to conventional methods.

Mathematical morphology approach to internal defect analysis of A356 aluminum alloy wheel hubs

A356 aluminum alloy is a material widely used in the production of automobile wheels. Internal defects such as gas holes and shrinkage cavities are likely to develop in the process of low pressure casting. X-ray images of the hub are able to provide some information on such defects. This paper proposes a defect extraction method which is built on mathematical morphology. It involves three operations, i.e., the top-hat transform, the top-hat reconstruction transform and the dilation reconstruction. A larger square structuring element and a small threshold are used firstly to obtain all potential defect areas of the hub. A structuring element of a suitable size are applied to different defect areas in subsequent extraction. A new threshold is then decided to get the final defect extraction results. The experimental results show that the above defect extraction method not only works on X-ray hub images, but is robust against the interference caused by noises and hub geometry, and hence can potentially be extensively applied to X-ray detection of hubs.

A mathematical morphology approach for a qualitative exploration of drought events in space and time

AbstractDrought events occur worldwide and possibly incur severe consequences. Trying to understand and characterize drought events is of considerable importance in order to improve the preparedness for coping with future events. In this paper, we present a methodology that allows for the delineation of drought events by exploiting their spatiotemporal nature. To that end, we apply operators borrowed from mathematical morphology to represent drought events as connected components in space and time. As an illustration, we identify drought events on the basis of a 35‐year data set of daily soil moisture values covering mainland Australia. We then extract characteristics reflecting the affected area, duration and intensity from the proposed representation of a drought event in order to illustrate the impact of tuning parameters in the methodology presented. Yet, this paper we refrain from comparing with other drought delineation methods.

Human visual system based optimized mathematical morphology approach for enhancement of brain MR images

Brain tumor is a life-threatening disease with fast growth rate, which makes its detection a critical task. However, low contrast and noise content in brain magnetic resonance images (MRI) hampers the screening of brain tumor. Therefore, contrast enhancement of these images are necessary to obtain a more definitive imaging for tumor detection. This paper presents an optimized enhancement model for processing Brain MRI by employing morphological filters in coherence with human visual system (HVS) system. The HVS coherence in response of filtering process is incorporated by combination of top-hat and bottom-hat morphological operators using logarithmic image processing model. Application of morphological filter requires selection of structuring element of requisite shape and size to ensure precision in brain tumor detection. This process is challenging as brain tumors (in MRI) may vary rigorously in size and morphology with each case or stages of tumor. Herein, this constraint has been resolved by using a disk-shaped structuring element whose order (size) is optimized using particle swarm optimization algorithm. The enhancement results are quantitatively evaluated using image quality measurement parameters like contrast improvement index, average signal to noise ratio, peak signal to noise ratio and measure of enhancement.

Using remote sensing to studying quantitative properties of ridge landscapes morphological structure in the Caspian lowland

The paper presents the results of studying ridge landscape patterns (formed by Baer mounds) of the Northern Caspian region on the basis of the mathematical landscape morphology approaches. A methodology for studying patterns includes the use of remote sensing data and mathematical methods. Mathematical analysis of six sample areas has revealed that the perimeters and diameters of the ridges fit the lognormal distribution. Discrete indicators that characterize the location of the ridges, complies Poisson`s distribution in most cases. It was revealed that the river erosion destroys the moan`s morphology which leads to their diameters does not fit the lognormal distribution. We test the arguments in favor of various theories of the Baer mounds origin from the point of view of the quantitative features of the morphological structure.

Iterative modelling of the closing-based differential morphological profile

One of an image processing applications is retinal image optic disk detection. The similarity of the retinal gray scale image between the object and background has been interesting to many researchers to develop the research. In this research, the closing-based differential morphological profile is proposed to detect the optic disc on the retinal image. The closing process is performed by iterative. It is started by pre-processing and followed by the different morphological profile based on the closing operation, i.e., the dilation and erosion processes. The dilation process is iteratively performed and followed by erosion process. The process results are enhanced to obtain the better image when the binary image transformation is conducted. The noise removal process is also necessity to eliminate the detection error. Furthermore, determining of the point centre of an object detection result will be used to create the optic disk. The detection rates of the proposed approach show that the maximum detection accuracy outperformed to the other methods, i.e., 2D-Gaussian filtering-based mathematical morphology approach, differential morphological profile, morphological reconstruction techniques and hybrid fuzzy classifier.

Development of a Software Package for Environmental Risk Assessment Based on Materials of Repeated Remote Surveys

This paper presents the development of a model version of a software package for analyzing the dynamics of dangerous exogenous processes in view of the assessment of natural risks. The work was performed with thermokarst processes and subsidence processes affecting linear engineering structures as examples. Software package development was based on the use of mathematical landscape morphology approaches and the corresponding mathematical models of the morphological structure. Both the expansion of existing foci and the emergence of new foci during pipeline operation were considered in the software package as causes of damage to a linear engineering structure. Decisions on the probability of damage to the structure were based on the corresponding model. The materials of repeated remote surveys served as the input data for the software package, and the probability of damage to the engineering structure within a given time was calculated as a result.

Software tool for automatic detection of solar plages in the Coimbra Observatory spectroheliograms

Full-disk spectroheliograms have been taken in Coimbra on a daily basis since 1926 in the Ca II K-line (K1 and K3). Later, in 1989, with the upgrade of the equipment it was possible to start the observations in the H-alpha line. The spectroheliograms of Coimbra constitutes a huge dataset of solar images, which requires an efficient automatic tool to detect and analyse solar activity features. This work presents a mathematical morphology approach applied to the CaII K3 series. The objective is to create a tool based on the segmentation by watershed transform combined with other morphological operators to detect automatically and analyse chromospheric plages during the solar cycle 24. The tool is validated by comparing its results for cycle 23 with those presented by Dorotovic et al. (2007, 2010). The results obtained are in very good agreement with those, including on images obtained in non-ideal meteorological conditions (eg. some clouds in sky). The results were also qualitatively compared with the results obtained through the application of ASSA model to SDO HMI magnetograms.

Contrast Enhancement of Grayscale and Color images using Adaptive Techniques

Contrast enhancement is an emerging research area in digital image processing domain. It is an important factor in any subjective evaluation of image quality in medical image processing. As there are possibilities for degradation of image quality during the acquisition, there arises the need of an efficient contrast enhancement technique that can remove the redundant pixels from the images prior to final processing. In this paper, we have proposed two adaptive approaches for contrast enhancement. The first approach is used for enhancing grayscale image using mathematical morphology and second approach is for color image using enhanced sigmoid function. The enhancement process of grayscale image was evaluated by using PSNR and that of color image was evaluated by using a factor called measure of contrast. The experimental results indicate that the two proposed methods show better performance for image in grayscale as well as in color.

Mathematical Morphology and Deep Learning-based Approach for Bearing Fault Recognition

Mathematical Morphology and Deep Learning-based Approach for Bearing Fault Recognition

Extraction of Street from Google Earth Imagery Region City Using Mathematical Morphology Approach

The Silk Road on a map in the architect and civil urgently is needed for the purposes of mapping and planning, but on the other side to get a map takes a message and considerable cost. Then, after getting a map it still needs to be done in conducting first design of the layout, which makes basic maps done manually (tracing). For architecture students in performing activities requiring the design of the existing map for required repeatedly as a medium to create space analysis. It is necessary to map existing methods of making convenient with image-based processing. This study proposes a method of making a part of the existing maps more quickly and efficiently based on digital image processing. The method developed is aimed at extracting the road (linkage) using GPS Google Earth imagery data, using mathematical morphology algorithms, object detection. The proposed method has been implemented in MATLAB programming language into a prototype application software; it can detect and extract the linkage to clear the image of GPS. Prototype software that has been made is very usefull for the application in the architecture field, that is to get a basic picture of the existing mapping of the region. Is particularly useful as an application to create a base of image analysis process design task for students of architecture.

A novel mathematical morphology based edge detection method for medical images

Today, digital image processing is an important area of research. Many medical applications apply image processing techniques to enhance and improve the quality of medical diagnosis. Effective edge detection of images is a fundamental problem in digital image processing. There are different approaches proposed to detect edges of the image such as classical gradients and second derivatives based operators. However, existing approaches have various tradeoffs in the presence of noise and suffer from poor de-noising which leads to an inaccurate edge detection. In this paper, an edge detection approach based on mathematical morphology is proposed to improve edge detection in noisy medical images of fractured bones, head CT, mammogram and colored eye’s fundus. Our evaluation results showed that the proposed detector outperforms classical detectors as well as existing mathematical morphology approaches in detecting edges of medical images under noise effect named “salt and pepper”. The proposed detector applies multiple structured elements to suppress noise and detect edges, thus produces thinner and better linked edges in noisy medical images.

False arrhythmia alarms reduction in the intensive care unit: a multimodal approach

The purpose of this study was to develop algorithms to lower the incidence of false arrhythmia alarms in the ICU using information from independent sources, namely electrocardiogram (ECG), arterial blood pressure (ABP) and photoplethysmogram (PPG). Our approach relies on robust adaptive signal processing techniques in order to extract accurate heart rate (HR) values from the different waveforms. Based on the quality of available signals, heart rate was either estimated from pulsatile waveforms using an adaptive frequency tracking algorithm or computed from ECGs using an adaptive mathematical morphology approach. Furthermore, we developed a supplementary measure based on the spectral purity of the ECGs to determine whether a ventricular tachycardia or flutter/fibrillation arrhythmia has taken place. Finally, alarm veracity was determined based on a set of decision rules on HR and spectral purity values. The proposed method was evaluated on the PhysioNet/CinC Challenge 2015 database, which is composed of 1250 life-threatening alarm recordings, each categorized into either bradycardia, tachycardia, asystole, ventricular tachycardia or ventricular flutter/fibrillation arrhythmia. This resulted in overall true positive rates of 95%/99% and overall true negative rates of 76%/80% on the real-time and retrospective subsets of the test dataset, respectively.