Computer Image Analysis Method Research Articles

Analysis of Tribological Properties of Hardfaced High-Chromium Layers Subjected to Wear in Abrasive Soil Mass.

This article presents the results of abrasion wear resistance tests of wear-resistant steel and surfacing under laboratory conditions and natural operation. Abrasion wear resistance determined on the basis of the study by determining geometrical characteristics of the alloying additives using computer image analysis methods, as well as examining the changes occurring on the surface of the workpieces and their wear intensity. Based on the results obtained from laboratory tests, it was noted that AR steel exhibited 14 times greater wear than the padding weld. This wear is affected by alloy additives, which, for the padding weld, are chromium additives. The microstructure image shows that soil mass had a destructive effect mainly on the matrix of the material, whereas in the areas with high concentrations of chromium precipitates, this effect was significantly weaker. The operational test results showed that within the area of the tine subjected to hardfacing, the material loss was lower than that for the same area of the tine in the as-delivered state. For the hardfaced tine, a 7% loss of volume was noted in relation to the operating part before testing and following the friction process. However, for the operating part in the as-delivered state, this difference amounted to 12%.

Research on color and texture characteristics and visual perception of custom wardrobe finishes

In recent years, the custom wardrobe market has been steadily developing. While meeting the functional needs of users, it is gradually shifting towards aesthetic preferences. Rapidly grasping users’ preferences for the appearance of custom wardrobes is a key focus of current research. This study collected a large number of decorative surface images of custom wardrobes and objectively analyzed the design features based on color moments and Tamura texture feature data in computer image analysis methods. K-means cluster analysis was performed on the feature data. Collected images of the points closest to the cluster centers were further screened to select representative finish images, and finally a questionnaire survey was conducted at Nanjing Forestry University, with the help of semantic differential method and factor analysis. The characteristics of the samples were comprehensively summarized to infer design elements. The study found that warm-toned, medium-low saturation, and medium brightness surfaces were preferred by the panel. Different colors, contrasts, saturations, brightness, element features, and arrangements have significantly different effects on visual perception. These conclusions can provide a reference for subsequent custom wardrobe design.

A Multi-Stain Breast Cancer Histological Whole-Slide-Image Data Set from Routine Diagnostics

The analysis of FFPE tissue sections stained with haematoxylin and eosin (H&E) or immunohistochemistry (IHC) is essential for the pathologic assessment of surgically resected breast cancer specimens. IHC staining has been broadly adopted into diagnostic guidelines and routine workflows to assess the status of several established biomarkers, including ER, PGR, HER2 and KI67. Biomarker assessment can also be facilitated by computational pathology image analysis methods, which have made numerous substantial advances recently, often based on publicly available whole slide image (WSI) data sets. However, the field is still considerably limited by the sparsity of public data sets. In particular, there are no large, high quality publicly available data sets with WSIs of matching IHC and H&E-stained tissue sections from the same tumour. Here, we publish the currently largest publicly available data set of WSIs of tissue sections from surgical resection specimens from female primary breast cancer patients with matched WSIs of corresponding H&E and IHC-stained tissue, consisting of 4,212 WSIs from 1,153 patients.

Evaluation of the Second Premolar's Bud Position Using Computer Image Analysis and Neural Modelling Methods.

Panoramic radiograph is a universally used diagnostic method in dentistry for identifying various dental anomalies and assessing developmental stages of the dentition. The second premolar is the tooth with the highest number of developmental abnormalities. The purpose of this study was to generate neural models for assessing the position of the bud of the second premolar tooth based on analysis of tooth-bone indicators of other teeth. The study material consisted of 300 digital pantomographic radiographs of children in their developmental period. The study group consisted of 165 boys and 135 girls. The study included radiographs of patients of Polish nationality, aged 6-10 years, without diagnosed systemic diseases and local disorders. The study resulted in a set of original indicators to accurately assess the development of the second premolar tooth using computer image analysis and neural modelling. Five neural networks were generated, whose test quality was between 68-91%. The network dedicated to all quadrants of the dentition showed the highest test quality at 91%. The training, validation and test subsets were divided in a standard 2:1;1 ratio into 150 training cases, 75 test cases and 75 validation cases.

Development of an Optical System Based on Spectral Imaging Used for a Slug Control Robot

The state-of-the-art technique to control slug pests in agriculture is the spreading of slug pellets. This method has some downsides, because slug pellets also harm beneficials and often fail because their efficiency depends on the prevailing weather conditions. This study is part of a research project which is developing a pest control robot to monitor the field, detect slugs, and eliminate them. Robots represent a promising alternative to slug pellets. They work independent of weather conditions and can distinguish between pests and beneficials. As a prerequisite, a robot must be able to reliably identify slugs irrespective of the characteristics of the surrounding conditions. In this context, the utilization of computer vision and image analysis methods are challenging, because slugs look very similar to the soil, particularly in color images. Therefore, the goal of this study was to develop an optical filter-based system that distinguishes between slugs and soil. In this context, the spectral characteristics of both slugs and soil in the visible and visible near-infrared (VNIR) wavebands were measured. Conspicuous maxima followed by conspicuous local minima were found for the reflection spectra of slugs in the near infrared range from 850 nm to 990 nm]. Thus, this enabled differentiation between slugs and soils; soils showed a monotonic increase in the intensity of the relative reflection for this wavelength. The extrema determined in the reflection spectra of slugs were used to develop and set up a slug detector device consisting of a monochromatic camera, a filter changer and two narrow bandpass filters with nominal wavelengths of 925 nm and 975 nm. The developed optical system takes two photographs of the target area at night. By subtracting the pixel values of the images, the slugs are highlighted, and the soil is removed in the image due to the properties of the reflection spectra of soils and slugs. In the resulting image, the pixels of slugs were, on average, 12.4 times brighter than pixels of soil. This enabled the detection of slugs by a threshold method.

Integrated Cells and Collagen Fibers Spatial Image Analysis.

Modern technologies designed for tissue structure visualization like brightfield microscopy, fluorescent microscopy, mass cytometry imaging (MCI) and mass spectrometry imaging (MSI) provide large amounts of quantitative and spatial information about cells and tissue structures like vessels, bronchioles etc. Many published reports have demonstrated that the structural features of cells and extracellular matrix (ECM) and their interactions strongly predict disease development and progression. Computational image analysis methods in combination with spatial analysis and machine learning can reveal novel structural patterns in normal and diseased tissue. Here, we have developed a Python package designed for integrated analysis of cells and ECM in a spatially dependent manner. The package performs segmentation, labeling and feature analysis of ECM fibers, combines this information with pre-generated single-cell based datasets and realizes cell-cell and cell-fiber spatial analysis. To demonstrate performance and compatibility of our computational tool, we integrated it with a pipeline designed for cell segmentation, classification, and feature analysis in the KNIME analytical platform. For validation, we used a set of mouse mammary gland tumors and human lung adenocarcinoma tissue samples stained for multiple cellular markers and collagen as the main ECM protein. The developed package provides sufficient performance and precision to be used as a novel method to investigate cell-ECM relationships in the tissue, as well as detect structural patterns correlated with specific disease outcomes.

Comparison of transcriptome between high- and low-marbling fineness in longissimus thoracis muscle of Korean cattle.

ObjectiveThis study compared differentially expressed genes (DEGs) between groups with high and low numbers of fine marbling particles (NFMP) in the longissimus thoracis muscle (LT) of Korean cattle to understand the molecular events associated with fine marbling particle formation.MethodsThe size and distribution of marbling particles in the LT were assessed with a computer image analysis method. Based on the NFMP, 10 LT samples were selected and assigned to either high- (n = 5) or low- (n = 5) NFMP groups. Using RNA sequencing, LT transcriptomic profiles were compared between the high- and low-NFMP groups. DEGs were selected at p<0.05 and |fold change| >2 and subjected to functional annotation.ResultsIn total, 328 DEGs were identified, with 207 up-regulated and 121 down-regulated genes in the high-NFMP group. Pathway analysis of these DEGs revealed five significant (p<0.05) Kyoto encyclopedia of genes and genomes pathways; the significant terms included endocytosis (p = 0.023), protein processing in endoplasmic reticulum (p = 0.019), and adipocytokine signaling pathway (p = 0.024), which are thought to regulate adipocyte hypertrophy and hyperplasia. The expression of sirtuin4 (p<0.001) and insulin receptor substrate 2 (p = 0.043), which are associated with glucose uptake and adipocyte differentiation, was higher in the high-NFMP group than in the low-NFMP group.ConclusionTranscriptome differences between the high- and low-NFMP groups suggest that pathways regulating adipocyte hyperplasia and hypertrophy are involved in the marbling fineness of the LT.

Influence of the Type of Cement on the Action of the Admixture Containing Aluminum Powder.

The study of the effect of cement type on the action of an admixture increasing the volume of concrete (containing aluminum powder), used in amounts of 0.5–1.5% of cement mass, was presented. The tests were carried out on cement mortars with Portland (CEM I) and ground granulated blast-furnace slag cement (CEM III). The following tests were carried out for the tested mortars: the air content in fresh mortars, compressive strength, flexural strength, increase in mortar volume, bulk density, pore structure evaluation (by the computer image analysis method) and changes in the concentration of OH− ions during the hydration of used cements. Differences in the action of the tested admixture depending on the cement used were found. To induce the expansion of CEM III mortars, a smaller amount of admixture is required than in the case of CEM I cement. Using the admixture in amounts above 1% of the cement mass causes cracks of mortars with CEM III cement due to slow hydrogen evolution, which occurs after mortar plasticity is lost. The use of an aluminum-containing admixture reduces the strength properties of the cement mortars, the effect being stronger in the case of CEM III cement. The influence of the sample molding time on the admixture action was also found.

An open-access computer image analysis (CIA) method to predict meat and fat content from an android smartphone-derived picture of the bovine 5th-6th rib.

Marbling and rib composition are important attributes related to carcass yields and values, beef quality, consumer satisfaction and purchasing decisions. An open-access computer image analysis method based on a fresh beef rib image captured under nonstandardized and uncontrolled conditions was developed to determine the intramuscular, intermuscular and total fat content. For this purpose, cross-section images of the 5th-6th rib from 130 bovine carcasses were captured with a Galaxy S8 smartphone. The pictures were analyzed with a program developed using ImageJ open source software. The 17 processed image features that were obtained were mined relative to gold standard measures, namely, intermuscular fat, total fat and muscles dissected from a rib and weighed, and intramuscular fat content (IMF - marbling) determined by the Soxhlet method. The best predictions with the lowest prediction errors were obtained by the sparse partial least squares method for both IMF percent and rib composition and from a combination of animal and image analysis features captured from the caudal face of the 6th rib captured on a table. These predictions were more accurate than those based on animal and image analysis features captured from the caudal face of the 5th rib on hanging carcasses. The external-validated prediction precision was 90% for IMF and ranged from 71 to 86% for the total fat, intermuscular and muscle rib weight ratios. Therefore, an easy, low-cost, user-friendly and rapid method based on a smartphone picture from the 6th rib of bovine carcasses provides an accurate method for fat content determination.

Influence of polymer modification on the microstructure of shielding concrete.

In this paper an analysis of the influence of polymer modification on the microstructure, shielding properties against neutrons, and compressive strength of heavy-weight magnetite concrete is carried out. The modifications involve the addition of acrylic or epoxy dispersions as well as micro- or/and macrofibers. A computer image analysis method is used to evaluate the microstructure of concretes and parameters of pore structure are calculated; these parameters include relative volume fraction, relative specific surface area, and pore arrangement ratios, including a proprietary ratio based on Voronoi tessellation. An assessment of significance of differences between stereological parameters of reference concrete and polymer modified concretes, as well as the impact of polymer form (dispersion or fibers) on shielding properties and compressive strength is carried out using Student’s t-test. The results show that except for the effect of the addition of both polypropylene micro- and macrofibers on the relative volume of pores, all other modifications result in statistically significant changes in the values of stereological parameters. Nevertheless, it is shown that neither polymer dispersions nor fibers have a statistically significant impact on shielding properties, but that they do influence compressive strength.

Influence of Particle Shape on the Density and Compressive Performance of Calcareous Sand

Particle shape influence the bearing capacity of calcareous sand foundations in island reef engineering. An improved Computer Image Analysis method that combined with mathematical statistics was proposed to categorize and sort different shapes of calcareous sand particles within the size range of 5–10 mm. Three single-shape calcareous sand specimens (granular shape, dendritic shape, long strip shape) were obtained. A new self-developed vibration device was used measuring the maximum density of calcareous, the shape and content as the variables in the orthogonal test. On this basis, the lateral compression tests were carried out to assess the influence of particle shape on the density, compressive performance of calcareous sand. Test results showed that better discriminability was achieved by taking mean flatness (EL/B) as the quantification parameter of the particle shapes. The average flatness EL/B of specimens is approximately normally distributed in the statistical results. The shape and content of sand particles had an obvious influence on the density of calcareous sand. The compressive properties of calcareous sands with different particle shapes have obvious differences. After loaded, the particle size distribution of specimen improved, the average flatness EL/B of the granular-shaped specimens increased, while that of the dendritic-shaped and the long-strip-shaped specimens decreased, the average flatness EL/B of the specimens tended to be uniform. The relative fracture rate Br and the load value Pmax satisfied the exponential function fitting relationship. Therefore, it can be argued that particle shape should be taken into consideration when optimizing the foundation design in island reef engineering to achieve better compressive performance of the foundation.

PSV-37 Relationships among carcass and sensory traits, auction price, and computer image analysis traits of marbling characteristics in Korean beef cattle

Abstract This study examined relationships among carcass and sensory traits, auction price, and computer image analysis (CIA) traits of marbling characteristics in Korean cattle beef. In experiment 1, 43 Korean cattle steers reared in similar feeding conditions were slaughtered at 34 months of age, and carcass traits were evaluated by official meat graders. Carcass auction prices were determined by wholesalers. Cross-sectional photographs of the beef were taken at the 13th thoracic vertebra using beef carcass photography equipment. Image files were analyzed for marbling characteristics using Beef Analyzer II software. Longissimus thoracis (LT) samples obtained after carcass grading were analyzed for sensory traits. Correlations among several variables were analyzed using either Pearson’s correlation or Spearman’s correlation analysis. Marbling score and quality grade (QG) had strong positive correlations (0.63 ≤ r ≤ 0.88, P &amp;lt; 0.01) with several CIA traits, including number of coarse marbling particles (MPs), number of fine MPs, and fineness index. Auction price had strong positive correlations (0.69 ≤ r ≤ 0.76, P &amp;lt; 0.01) with these CIA traits. Most sensory traits were not correlated with CIA traits. In experiment 2, 267 additional LT images photographed at the slaughter house were used for correlation analysis between auction price and CIA traits within an individual QG class [QGs 1 (middle), 1+, and 1++ (best)]. Carcass auction price was positively correlated (0.36 ≤ r ≤ 0.51, P &amp;lt; 0.01) with number of coarse MPs, number of fine MPs, and fineness index in both QGs 1+ and 1++ but not in QG 1. Overall, marbling score and QG had positive correlations with several CIA traits of marbling characteristics. Carcass auction price had positive correlations with CIA traits in QGs 1+ and 1++ but not in QG 1. In conclusion, a CIA method after modification could be incorporated into current beef quality grading systems.

P.651 Mood congruent helplessness associates with prefrontal Intrinsic connectivity in major depression

In this work we have proposed to use multifractal analysis to evaluate the effectiveness of the healing process in postresectal and postcystal bone loss using the guided bone regeneration (GBR).The material of the study consists of 19 radiographic images obtained from patients (13 females and 6 males), observed within 1-year-long period, who had undergone bone augmentation with xenogenic material. Using radiographic images (RVG) made with digital radiography set Kodak RVG 6100 on the day of the procedure (Group A) and 12 months later (Group B), the degree of reconstruction of intraosseous defects were compared. A visual subjective evaluation of the healing process based on RVG images may not be sufficient. For this purpose, modern computer image analysis methods can be used. Pre-processing of radiographic images consisted of separating areas of interest (ROI) and binarization. The resulting images were analyzed using multifractals. The properties of biological structures cannot be sufficiently described in the Euclidean space, but they can be characterized by a parameter called the fractal dimension.Significant increase (p < 0.0001) of multifractal features were found in patients from group B. Individual parameters may characterize bone structure, which had undergone bone augmentation with xenogenic material. Finally, we showed that the properly selected multifractal quantificators obtained for those images could be used to assign those images to the appropriate group.The proposed analysis based on RVG images could help to evaluate the healing process after bone loss. The analysis and interpretation of the healing process after bone loss using monofractal and multifractal analysis as a multi-steps process quantify a stable (good) clinical result.

Image Analysis of Sewage Sludge and Barley Straw as Biological Materials Composted under Different Conditions.

Composting is one of the most important methods of sewage sludge management. This paper describes the methods of computer image analysis used for objective comparison of the appearance of composted materials under diverse conditions in terms of size and thermal insulation of the composting chambers. The research material was a mixture of sewage sludge and barley straw. The composting process was performed under strictly controlled laboratory conditions, using 10 composting chambers with five different volumes. In half of them additional thermal insulation was used, while in the others no insulation was applied. A proper composting process run was observed only in the three chambers with the largest volume and with additional thermal insulation. The images of the materials were subjected to a wide analysis, wherein the values of 17 parameters regarding color and texture were estimated. Significant differences were observed in the appearances between materials obtained during the properly running composting processes and those obtained in the chambers of insufficient size and thermal insulation. The values of the considered parameters determined for images of the composted material under normal and abnormal conditions were significantly different from each other. Thus, these parameters may be used as indicators of a correctly conducted composting process. In the cases of 15 parameters, the values of these differences exceeded 10%, and in the cases of 10 parameters 50%, while in the cases of three parameters as much as 100%.

ES08.07 System Approach to Screening Management

ES08.07 System Approach to Screening Management

Multifractal characterization of healing process after bone loss

ObjectiveIn this work we have proposed to use multifractal analysis to evaluate the effectiveness of the healing process in postresectal and postcystal bone loss using the guided bone regeneration (GBR). MethodsThe material of the study consists of 19 radiographic images obtained from patients (13 females and 6 males), observed within 1-year-long period, who had undergone bone augmentation with xenogenic material. Using radiographic images (RVG) made with digital radiography set Kodak RVG 6100 on the day of the procedure (Group A) and 12 months later (Group B), the degree of reconstruction of intraosseous defects were compared. A visual subjective evaluation of the healing process based on RVG images may not be sufficient. For this purpose, modern computer image analysis methods can be used. Pre-processing of radiographic images consisted of separating areas of interest (ROI) and binarization. The resulting images were analyzed using multifractals. The properties of biological structures cannot be sufficiently described in the Euclidean space, but they can be characterized by a parameter called the fractal dimension. ResultsSignificant increase (p < 0.0001) of multifractal features were found in patients from group B. Individual parameters may characterize bone structure, which had undergone bone augmentation with xenogenic material. Finally, we showed that the properly selected multifractal quantificators obtained for those images could be used to assign those images to the appropriate group. ConclusionThe proposed analysis based on RVG images could help to evaluate the healing process after bone loss. The analysis and interpretation of the healing process after bone loss using monofractal and multifractal analysis as a multi-steps process quantify a stable (good) clinical result.

Expression of SOCS1 in overload papillary muscles of mice cardiac ventricle

Objective To investigate the expression of suppressor of cytokine signaling 1 (SOCS1) in overloaded ventricle papillary muscle, so as to understand its expression characteristics in structural remodeling after the overloading and the biomechanical properties of the muscle under cubic jellyfish toxin-1(CfTX-1) pretreatment that can affect cell signal transduction. Methods Abdominal aortic-venous fistula (AVF) were operated in Kunming mice (n=5), and the cardiac left ventricles were harvested after two weeks of fistulation. The mice in normal group were sham operated as a control (n=5). In vitro culture, the left ventricular papillary muscle of normal mice was used (n=20). In the stretching group, the isolated papillary muscles were double-ratio stretched and fixed on silicone plate. In the relaxation group, the muscles were not stretched. A separated subgroup that transfected with SOCS1 plasmids were set in each group of stretching and relaxation. The papillary muscle samples of each group were cultured in culture medium for 3 days at 37 ℃, and then homogenized for extracting total protein. The total protein was separated by 10% sodium dodecyl sulfate-polyacrylamide gel electrophoresis. The 23 ku band with SOCS1 was used as the target band, and the integrated optical density (IOD) value was measured by computer image analysis method. The expression of SOCS1 protein was detected by Western Blot and the imprinted IOD value was also measured. The papillary muscle in the stretching group was stretched by micro-positioned stretching method, and the initial load was 1 g. After stabilization, the papillary muscle was stretched by 15 mm for continuously 5 times, and the passive tension characteristic curves during the first and fifth stretching were observed and recorded. The peak passive tension (PTmax) and its deceleration velocity (DV) of the papillary muscle were calculated based on the curves. Results Comparing with the AVF group, the normal group had higher IOD values of 23 ku band and SOCS1 blot in total protein of the papillary muscle, and the differences were statistically significant (all P<0.01). The IOD value of 23 ku band in the SOCS1 transfected stretching group was significantly higher than those of the two relaxation groups, and the differences were statistically significant (all P<0.01). However, the difference of this value was not statistically significant between the two relaxation groups. The average IOD value of SOCS1 blot in the SOCS1 transfected stretching group was higher than those of the normal stretching group and the SOCS1 transfected relaxation group, and the differences were statistically significant (all P<0.01). Comparing with the normal group, the AVF group had higher PTmax and ultimate PTmax of the papillary muscles, and had a lower DV values, and the differences were statistically significant (all P<0.01). Conclusions The expression of SOCS1 is sensitive to tension load, and has a positive effect as an overload-sensitive signal in improving myocardial adaptability, protecting myocardial structure and maintaining systolic and diastolic function. CfTX-1 also has a positive effect on improving the compliance of ventricular papillary muscles. Key words: Mechanical load; Ventricular papillary muscle; Stretching culture; Transfection; Suppressor of cytokine signaling 1

Application of computer vision and image analysis method in cheese-quality evaluation: a review

Application of computer vision and image analysis method in cheese-quality evaluation: a review

Identification and Characterization of Particle Shapes from Images of Sand Assemblies Using Pattern Recognition

Pattern recognition was used on images of contacting three-dimensional sand particle assemblies to detect foreground sand grains that exhibit full-particle projections. Once identified, the roundness and sphericity of those particles could be determined using previously developed computational geometry image analysis methods. The pattern recognition used cascade and sliding window techniques from the literature with modifications to account for the unique features of sand grains, including variable sizes and a range of elongations and orientations of long axes in an image. A library of over 85,000 images was created to train the pattern recognition program. An example problem illustrated the capabilities of the method to generate particle roundness and sphericity curves.

Application of neural image analysis in evaluating the quality of greenhouse tomatoes

The paper presents the research on the use of methods of computer image analysis and artificial neural modeling in the process of assessing the quality of greenhouse tomatoes variety Cappricia. The subject of the study was tomatoes of the sizes from 40mm to 67mm and the colours: 1–6, include intermediate colours. The process of image acquisition and obtaining empirical data was conducted throughout the entire growing season in the period from the first harvest in the middle of May to the last harvest at the beginning of November. Satisfactory quality characteristics were obtained in the case of the RBF 37:37-39-1:1 and RBF 22:22-20-2:2 models. RBF 37:37-39-1:1 network, whose output variable was the colour of the tomato, the training quality was 0.930827, the validation quality was 0.911982, and the test quality was 0.979390. The RMSE rate of network training for the training set was 0.075986, for the validation set it was 0.072194, and for the test set 0.061714. For the RBF 22:22-20-2:2 network, the variables were colour and hardness. This network is characterised by a training quality of 0.985038, a validation quality of 0.990694 and a test quality of 0.985130. The RMSE rate of the network training is 0.065667, of the network validation it is 0.066187 and of the network test 0.073868.The research showed that performing a correct classification requires taking two digital images of the examined tomatoes, one of the stem and one of the front of the tomato, and generating training sets that contain average values for the extracted characteristics.