Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status...Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.展开更多
BACKGROUND Congestive hepatopathy,also known as nutmeg liver,is liver damage secondary to chronic heart failure(HF).Its morphological characteristics in terms of medical imaging are not defined and remain unclear.AIM ...BACKGROUND Congestive hepatopathy,also known as nutmeg liver,is liver damage secondary to chronic heart failure(HF).Its morphological characteristics in terms of medical imaging are not defined and remain unclear.AIM To leverage machine learning to capture imaging features of congestive hepatopathy using incidentally acquired computed tomography(CT)scans.METHODS We retrospectively analyzed 179 chronic HF patients who underwent echocardiography and CT within one year.Right HF severity was classified into three grades.Liver CT images at the paraumbilical vein level were used to develop a ResNet-based machine learning model to predict tricuspid regurgitation(TR)severity.Model accuracy was compared with that of six gastroenterology and four radiology experts.RESULTS In the included patients,120 were male(mean age:73.1±14.4 years).The accuracy of the results predicting TR severity from a single CT image for the machine learning model was significantly higher than the average accuracy of the experts.The model was found to be exceptionally reliable for predicting severe TR.CONCLUSION Deep learning models,particularly those using ResNet architectures,can help identify morphological changes associated with TR severity,aiding in early liver dysfunction detection in patients with HF,thereby improving outcomes.展开更多
The Ki67 index (KI) is a standard clinical marker for tumor proliferation;however, its application is hindered by intratumoral heterogeneity. In this study, we used digital image analysis to comprehensively analyze Ki...The Ki67 index (KI) is a standard clinical marker for tumor proliferation;however, its application is hindered by intratumoral heterogeneity. In this study, we used digital image analysis to comprehensively analyze Ki67 heterogeneity and distribution patterns in breast carcinoma. Using Smart Pathology software, we digitized and analyzed 42 excised breast carcinoma Ki67 slides. Boxplots, histograms, and heat maps were generated to illustrate the KI distribution. We found that 30% of cases (13/42) exhibited discrepancies between global and hotspot KI when using a 14% KI threshold for classification. Patients with higher global or hotspot KI values displayed greater heterogenicity. Ki67 distribution patterns were categorized as randomly distributed (52%, 22/42), peripheral (43%, 18/42), and centered (5%, 2/42). Our sampling simulator indicated analyzing more than 10 high-power fields was typically required to accurately estimate global KI, with sampling size being correlated with heterogeneity. In conclusion, using digital image analysis in whole-slide images allows for comprehensive Ki67 profile assessment, shedding light on heterogeneity and distribution patterns. This spatial information can facilitate KI surveys of breast cancer and other malignancies.展开更多
Recognizing the variation of genetic resources is the first step in selection.One of the most important variations in grain crops is the uniformity of seed grain weight,which can be converted into seed size.However,it...Recognizing the variation of genetic resources is the first step in selection.One of the most important variations in grain crops is the uniformity of seed grain weight,which can be converted into seed size.However,it has been challenging since it needs high labor costs and time to measure it on a large scale.The current study used an image analysis technique to measure the grain seed area of about 100 seeds per accession with 64 germplasm of Tartary buckwheat(Fagopyrum tataricum)to study variation among and within them.To understand the nature of variation,skewness and kurtosis analysis of probability density function curve for seed area were used.As a result,a large variation among and within accessions was found.This means that the seed sizes within an accession are not uniform in this given cleistogamous species due to its non-uniform flowering time.This implies that the seed size should be considered an important factor for the germplasm enhancement program.展开更多
Mineral dissemination and pore space distribution in ore particles are important features that influence heap leaching performance.To quantify the mineral dissemination and pore space distribution of an ore particle,a...Mineral dissemination and pore space distribution in ore particles are important features that influence heap leaching performance.To quantify the mineral dissemination and pore space distribution of an ore particle,a cylindrical copper oxide ore sample(I center dot 4.6 mm x 5.6 mm)was scanned using high-resolution X-ray computed tomography(HRXCT),a nondestructive imaging technology,at a spatial resolution of 4.85 mu m.Combined with three-dimensional(3D)image analysis techniques,the main mineral phases and pore space were segmented and the volume fraction of each phase was calculated.In addition,the mass fraction of each mineral phase was estimated and the result was validated with that obtained using traditional techniques.Furthermore,the pore phase features,including the pore size distribution,pore surface area,pore fractal dimension,pore centerline,and the pore connectivity,were investigated quantitatively.The pore space analysis results indicate that the pore size distribution closely fits a log-normal distribution and that the pore space morphology is complicated,with a large surface area and low connectivity.This study demonstrates that the combination of HRXCT and 3D image analysis is an effective tool for acquiring 3D mineralogical and pore structural data.展开更多
With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remo...With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remotely sensed information classification pattern and a literature review of related research progress, this paper sums up 4 developing phases of object-oriented classification pattern during the past 20 years. Then, we discuss the three aspects of method- ology in detail, namely remotely sensed imagery segmentation, feature analysis and feature selection, and classification rule generation, through comparing them with remotely sensed information classification method based on per-pixel. At last, this paper presents several points that need to be paid attention to in the future studies on object-oriented RS in- formation classification pattern: 1) developing robust and highly effective image segmentation algorithm for multi-spectral RS imagery; 2) improving the feature-set including edge, spatial-adjacent and temporal characteristics; 3) discussing the classification rule generation classifier based on the decision tree; 4) presenting evaluation methods for classification result by object-oriented classification pattern.展开更多
Based on the analysis of high-speed video images, the detachment behavior of dust cake from the ceramic candle filter surface during pulse cleaning process is investigated. The influences of the dust cake loading,the ...Based on the analysis of high-speed video images, the detachment behavior of dust cake from the ceramic candle filter surface during pulse cleaning process is investigated. The influences of the dust cake loading,the reservoir pressure, and the filtration velocity on the cleaning effectiveness are analyzed. Experimental results show that there exists an optimum dust cake thickness for pulse-cleaning process. For thin dust cake, the patchy cleaning exists and the cleaning efficiency is low; if the dust cake is too thick, the pressure drop across the dust cake becomes higher and a higher reservoir pressure may be needed. At the same time there also exists an optimum reservoir pressure for a given filtration condition.展开更多
The particle morphology and surface texture play a major role in influencing mechanical and hydraulic behaviors of sandy soils. This paper presents the use of digital image analysis combined with fractal theory as a t...The particle morphology and surface texture play a major role in influencing mechanical and hydraulic behaviors of sandy soils. This paper presents the use of digital image analysis combined with fractal theory as a tool to quantify the particle morphology and surface texture of two types of quartz sands widely used in the region of Vitória, Espírito Santo, southeast of Brazil. The two investigated sands are sampled from different locations. The purpose of this paper is to present a simple, straightforward,reliable and reproducible methodology that can identify representative sandy soil texture parameters.The test results of the soil samples of the two sands separated by sieving into six size fractions are presented and discussed. The main advantages of the adopted methodology are its simplicity, reliability of the results, and relatively low cost. The results show that sands from the coastal spit(BS) have a greater degree of roundness and a smoother surface texture than river sands(RS). The values obtained in the test are statistically analyzed, and again it is confirmed that the BS sand has a slightly greater degree of sphericity than that of the RS sand. Moreover, the RS sand with rough surface texture has larger specific surface area values than the similar BS sand, which agree with the obtained roughness fractal dimensions. The consistent experimental results demonstrate that image analysis combined with fractal theory is an accurate and efficient method to quantify the differences in particle morphology and surface texture of quartz sands.展开更多
The degradation mechanisms of cementitious materials exposed to sulfate solutions have been controversial, despite considerable research. In this paper, two methodologies of image analysis based on scanning electron m...The degradation mechanisms of cementitious materials exposed to sulfate solutions have been controversial, despite considerable research. In this paper, two methodologies of image analysis based on scanning electron microscope and chemical mapping are used to analyse Portland cement mortars exposed to sodium sulfate solution. The effects of sulfate concentration in solution and water to cement ratio of mortar, which are considered as the most sensitive factors to sulfate attack, are investigated respectively by comparing the macro expansion with microstructure analysis. It is found that the sulfate concentration in pore solution, expressed as sulfate content in C-S-H, plays a critical role on the supersaturation with respect to ettringite and so on the expansion force generated.展开更多
In this study, mitotic metaphase chromosomes in mouse were identified by a new chromosome fluorescence banding technique combining DAPI staining with image analysis. Clear 4＇, 6-diamidino-2-phenylindole （DAPI） mult...In this study, mitotic metaphase chromosomes in mouse were identified by a new chromosome fluorescence banding technique combining DAPI staining with image analysis. Clear 4＇, 6-diamidino-2-phenylindole （DAPI） multiple bands like （J-hands could be produced in mouse. The Meta- Morph software was then used to generate linescans of pixel intensity for the banded chromosomes from short arm to long arm. These linescans were sufficient not only to identify each individual chromosome but also analyze the physical sites of bands in chromosome. Based on the results, the clear and accurate karyotype of mouse metaphase chromosomes was established. The technique is therefore considered to he a new method for cytological studies of mouse.展开更多
Mammalian pelage color can vary among individuals of many species, although this intraspecific variation is oftenoverlooked by researchers, perhaps because of its sometimes subtle nature and difficulty in assessing it...Mammalian pelage color can vary among individuals of many species, although this intraspecific variation is oftenoverlooked by researchers, perhaps because of its sometimes subtle nature and difficulty in assessing it quantitatively. Thus, suchvariation is rarely studied in mammals, and this is especially true within the order Chiroptera, where there has been very little empiricalresearch. We examined museum specimens of red bats (Lasiurus borealis, family Vespertilionidae) from Georgia, USA, todetermine the extent of sexual dimorphism in pelage color and to explore possible associations between body size and pelagecolor. We photographed 54 specimens under uniform lighting, and used an image analysis program to measure pelage hue on theuropatagium region, which is fully furred in members of the genus Lasiurus. Statistical analyses of pelage hue scores showedmales had significantly redder pelage than females when considered alone, but when examined together with effects of body sizeand collection year, sex was not significant, and collection year and body size were. More recent specimens tended to be less redthan older specimens, which might indicate a wearing of the buffy tips of hairs from older specimens, and smaller bats of bothsexes tended to be more red. These interesting findings are encouraging and we suggest that future explorations into intraspecificvariation in pelage color of bats using this or similar approaches are warranted to clarify the significance of the patterns. Thisstudy also demonstrated that care must be taken in analyses of mammalian pelage color from older museum skins, or at least thatresearchers must take into account the age of the specimens .展开更多
The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its...The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .展开更多
The changes of retinal nuclear DNA content in rats after death was detected and the relationship between degradation of retinal nuclear DNA and postmortem interval （PMI） was analyzed. Ninety healthy adult SD rats, f...The changes of retinal nuclear DNA content in rats after death was detected and the relationship between degradation of retinal nuclear DNA and postmortem interval （PMI） was analyzed. Ninety healthy adult SD rats, female, weighing 250±10 g, were randomly divided into 15 groups. At 20 ℃, the retinal cells were withdrawn every 2 h within 0 to 28 h after death and stained with Feulgen-Vans. Index of density （ID）, integral absorbance （IA） and average absorbance （AA） in retinal nucleus were analyzed by image analysis system. And the obtained data were subjected to linear regression analysis by using SPSS12.0 software. The results showed that in retinal nucleus, AA and IA were gradually declined with the prolongation of PMI, while ID had an increased tendency. Within 28 h after PMI, the regression equations were as follows： YAA=-0.009XAA＋0.590 （R^2=0.949）, YIA=0.097XIA＋18.903 （R^2=0.968）, YID=0.122XID＋2.246 （R^2=0.951）. It was concluded that retinal nuclear DNA after death in rats was degraded gradually and had a good correlation with PMI.展开更多
The objective assessment of fabric pilling based on light projection and image analysis has been exploited recently.The device for capturing the cross-sectional images of the pilled fabrics with light projection is el...The objective assessment of fabric pilling based on light projection and image analysis has been exploited recently.The device for capturing the cross-sectional images of the pilled fabrics with light projection is elaborated.The detection of the profile line and integration of the sequential cross-sectional pilled image are discussed.The threshold based on Gaussian model is recommended for pill segmentation.The results show that the installed system is capable of eliminating the interference with pill information from the fabric color and pattern.展开更多
A new test method was introduced to measure fiber distribution in steel fiber reinforced mortar by using image analysis technique. Through specimen preparation, image acquisition, fiber extraction, and measurement of ...A new test method was introduced to measure fiber distribution in steel fiber reinforced mortar by using image analysis technique. Through specimen preparation, image acquisition, fiber extraction, and measurement of related fiber parameters, quantitative analysis of fiber distribution could be obtained by two parameters, namely dispersion coefficient and orientation factor. Effect of boundaries, size and steel fiber content on fiber distribution was discussed. Results showed that, steel fiber distribution was affected by boundary effect, which would be weakened with the increase of specimen size. If the length and width remained constant, the specimen height had a significant effect on orientation factor of fiber, while its influence on dispersion coefficient was not so obvious. With the increase of steel fiber content, dispersion coefficient decreased slightly, and orientation factor deviated from 0.5.展开更多
In this study, a new method for quantitative and efficient measurement for the ground surface movement was developed. The feature of this technique is to identify geomorphic characteristics by image matching analysis,...In this study, a new method for quantitative and efficient measurement for the ground surface movement was developed. The feature of this technique is to identify geomorphic characteristics by image matching analysis, using the intelligent images made from high resolution DEM(Digital Elevation Model). This method is useful to extract the small ground displacement where the surface shape was not intensely deformed.展开更多
Malaria is an important and worldwide fatal disease that has been widely reported by the World Health Organization(WHO),and it has about 219 million cases worldwide,with 435,000 of those mortal.The common malaria diag...Malaria is an important and worldwide fatal disease that has been widely reported by the World Health Organization(WHO),and it has about 219 million cases worldwide,with 435,000 of those mortal.The common malaria diagnosis approach is heavily reliant on highly trained experts,who use a microscope to examine the samples.Therefore,there is a need to create an automated solution for the diagnosis of malaria.One of the main objectives of this work is to create a design tool that could be used to diagnose malaria from the image of a blood sample.In this paper,we firstly developed a graphical user interface that could be used to help segment red blood cells and infected cells and allow the users to analyze the blood samples.Secondly,a Feed-forward Neural Network(FNN)is designed to classify the cells into two classes.The achieved results show that the proposed techniques can be used to detect malaria,as it has achieved 92%accuracy with a database that contains 27,560 benchmark images.展开更多
Corneal opacity is one of the most commonly used parameters for estimating postmortem interval （PMI）. This paper proposes a new method to study the relationship between changes of corneal opacity and PMI by processi...Corneal opacity is one of the most commonly used parameters for estimating postmortem interval （PMI）. This paper proposes a new method to study the relationship between changes of corneal opacity and PMI by processing and analyzing cornea images. Corneal regions were extracted from images of rabbits＇ eyes and described by color-based and texture-based features, which could represent the changes of cornea at different PMI. A KNN classifier was used to reveal the association of image features and PMI. The result of the classification showed that the new method was reliable and effective.展开更多
The presence of nonmetallic inclusion particles which appear during steelmaking process is harmful to the properties of steels, which is mainly as a function of some aspects such as size, volume fraction, shape, and d...The presence of nonmetallic inclusion particles which appear during steelmaking process is harmful to the properties of steels, which is mainly as a function of some aspects such as size, volume fraction, shape, and distribution of these particles. The automatic image analysis technique is one of the most important tools for the quantitative determination of these parameters. The classical Student approach and the Extreme Values Method （EVM） were used for the inclusion size and shape determination and the evaluation of distance between the inclusion particles. The results thus obtained indicated that there were significant differences in the characteristics of the inclusion particles in the analyzed products. Both methods achieved results with some differences, indicating that EVM could be used as a faster and more reliable statistical methodology.展开更多
This study evaluated the correlation between DNA degradation of the splenic lymphocytes and the early time of death, examined the early time of death by computerized image analysis technique （CIAT） and identified th...This study evaluated the correlation between DNA degradation of the splenic lymphocytes and the early time of death, examined the early time of death by computerized image analysis technique （CIAT） and identified the best parameter that quantitatively reflects the DNA degradation. The spleen tissues from 34 SD rats were collected, subjected to cell smearing every 2 h within the first 36 h after death, stained by Feulgen-Van＇s staining, three indices reflecting DNA content in splenic lymphocytes, including integral optical density （IOD）, average optical density （AOD）, average gray scale （AG） were measured by the image analysis. Our results showed that IOD and AOD decreased and AG increased over time within the first 36 h. A stepwise linear regression analysis showed that only AG was fitted. A correlation between the postmortem interval （PMI） and AG was identified and the corresponding regression equation was obtained. Our study suggests that CIAT is a useful and promising tool for the estimation of early PMI with good objectivity and reproducibility, and AG is a more effective and better quantitative indicator for the estimation of PMI within the first 36 h after death in rats.展开更多
基金supported by the Deanship of Research and Graduate Studies at King Khalid University under Small Research Project grant number RGP1/139/45.
文摘Integrating multiple medical imaging techniques,including Magnetic Resonance Imaging(MRI),Computed Tomography,Positron Emission Tomography(PET),and ultrasound,provides a comprehensive view of the patient health status.Each of these methods contributes unique diagnostic insights,enhancing the overall assessment of patient condition.Nevertheless,the amalgamation of data from multiple modalities presents difficulties due to disparities in resolution,data collection methods,and noise levels.While traditional models like Convolutional Neural Networks(CNNs)excel in single-modality tasks,they struggle to handle multi-modal complexities,lacking the capacity to model global relationships.This research presents a novel approach for examining multi-modal medical imagery using a transformer-based system.The framework employs self-attention and cross-attention mechanisms to synchronize and integrate features across various modalities.Additionally,it shows resilience to variations in noise and image quality,making it adaptable for real-time clinical use.To address the computational hurdles linked to transformer models,particularly in real-time clinical applications in resource-constrained environments,several optimization techniques have been integrated to boost scalability and efficiency.Initially,a streamlined transformer architecture was adopted to minimize the computational load while maintaining model effectiveness.Methods such as model pruning,quantization,and knowledge distillation have been applied to reduce the parameter count and enhance the inference speed.Furthermore,efficient attention mechanisms such as linear or sparse attention were employed to alleviate the substantial memory and processing requirements of traditional self-attention operations.For further deployment optimization,researchers have implemented hardware-aware acceleration strategies,including the use of TensorRT and ONNX-based model compression,to ensure efficient execution on edge devices.These optimizations allow the approach to function effectively in real-time clinical settings,ensuring viability even in environments with limited resources.Future research directions include integrating non-imaging data to facilitate personalized treatment and enhancing computational efficiency for implementation in resource-limited environments.This study highlights the transformative potential of transformer models in multi-modal medical imaging,offering improvements in diagnostic accuracy and patient care outcomes.
基金Supported by Grant-in-Aid for Research on Hepatitis from the Japan Agency for Medical Research and Development,No.24fk0210128h0002Grant-in-Aid for Scientific Research,No.KAKENHI-23K07372.
文摘BACKGROUND Congestive hepatopathy,also known as nutmeg liver,is liver damage secondary to chronic heart failure(HF).Its morphological characteristics in terms of medical imaging are not defined and remain unclear.AIM To leverage machine learning to capture imaging features of congestive hepatopathy using incidentally acquired computed tomography(CT)scans.METHODS We retrospectively analyzed 179 chronic HF patients who underwent echocardiography and CT within one year.Right HF severity was classified into three grades.Liver CT images at the paraumbilical vein level were used to develop a ResNet-based machine learning model to predict tricuspid regurgitation(TR)severity.Model accuracy was compared with that of six gastroenterology and four radiology experts.RESULTS In the included patients,120 were male(mean age:73.1±14.4 years).The accuracy of the results predicting TR severity from a single CT image for the machine learning model was significantly higher than the average accuracy of the experts.The model was found to be exceptionally reliable for predicting severe TR.CONCLUSION Deep learning models,particularly those using ResNet architectures,can help identify morphological changes associated with TR severity,aiding in early liver dysfunction detection in patients with HF,thereby improving outcomes.
文摘The Ki67 index (KI) is a standard clinical marker for tumor proliferation;however, its application is hindered by intratumoral heterogeneity. In this study, we used digital image analysis to comprehensively analyze Ki67 heterogeneity and distribution patterns in breast carcinoma. Using Smart Pathology software, we digitized and analyzed 42 excised breast carcinoma Ki67 slides. Boxplots, histograms, and heat maps were generated to illustrate the KI distribution. We found that 30% of cases (13/42) exhibited discrepancies between global and hotspot KI when using a 14% KI threshold for classification. Patients with higher global or hotspot KI values displayed greater heterogenicity. Ki67 distribution patterns were categorized as randomly distributed (52%, 22/42), peripheral (43%, 18/42), and centered (5%, 2/42). Our sampling simulator indicated analyzing more than 10 high-power fields was typically required to accurately estimate global KI, with sampling size being correlated with heterogeneity. In conclusion, using digital image analysis in whole-slide images allows for comprehensive Ki67 profile assessment, shedding light on heterogeneity and distribution patterns. This spatial information can facilitate KI surveys of breast cancer and other malignancies.
基金supported by a grant from the Standardization and Integration of Resources Information for Seed-Cluster in Hub-Spoke Material Bank Program(Project No.PJ01587004),Rural Development Administration,Republic of Korea.
文摘Recognizing the variation of genetic resources is the first step in selection.One of the most important variations in grain crops is the uniformity of seed grain weight,which can be converted into seed size.However,it has been challenging since it needs high labor costs and time to measure it on a large scale.The current study used an image analysis technique to measure the grain seed area of about 100 seeds per accession with 64 germplasm of Tartary buckwheat(Fagopyrum tataricum)to study variation among and within them.To understand the nature of variation,skewness and kurtosis analysis of probability density function curve for seed area were used.As a result,a large variation among and within accessions was found.This means that the seed sizes within an accession are not uniform in this given cleistogamous species due to its non-uniform flowering time.This implies that the seed size should be considered an important factor for the germplasm enhancement program.
基金financially supported by the National Natural Science Foundation of China(No.51304076)the Natural Science Foundation of Hunan Province,China(No.14JJ4064)
文摘Mineral dissemination and pore space distribution in ore particles are important features that influence heap leaching performance.To quantify the mineral dissemination and pore space distribution of an ore particle,a cylindrical copper oxide ore sample(I center dot 4.6 mm x 5.6 mm)was scanned using high-resolution X-ray computed tomography(HRXCT),a nondestructive imaging technology,at a spatial resolution of 4.85 mu m.Combined with three-dimensional(3D)image analysis techniques,the main mineral phases and pore space were segmented and the volume fraction of each phase was calculated.In addition,the mass fraction of each mineral phase was estimated and the result was validated with that obtained using traditional techniques.Furthermore,the pore phase features,including the pore size distribution,pore surface area,pore fractal dimension,pore centerline,and the pore connectivity,were investigated quantitatively.The pore space analysis results indicate that the pore size distribution closely fits a log-normal distribution and that the pore space morphology is complicated,with a large surface area and low connectivity.This study demonstrates that the combination of HRXCT and 3D image analysis is an effective tool for acquiring 3D mineralogical and pore structural data.
基金Under the auspices of the National Natural Science Foundation of China (No. 40301038), Talents Recruitment Foun-dation of Nanjing University
文摘With the wide use of high-resolution remotely sensed imagery, the object-oriented remotely sensed informa- tion classification pattern has been intensively studied. Starting with the definition of object-oriented remotely sensed information classification pattern and a literature review of related research progress, this paper sums up 4 developing phases of object-oriented classification pattern during the past 20 years. Then, we discuss the three aspects of method- ology in detail, namely remotely sensed imagery segmentation, feature analysis and feature selection, and classification rule generation, through comparing them with remotely sensed information classification method based on per-pixel. At last, this paper presents several points that need to be paid attention to in the future studies on object-oriented RS in- formation classification pattern: 1) developing robust and highly effective image segmentation algorithm for multi-spectral RS imagery; 2) improving the feature-set including edge, spatial-adjacent and temporal characteristics; 3) discussing the classification rule generation classifier based on the decision tree; 4) presenting evaluation methods for classification result by object-oriented classification pattern.
基金Supported by the National Natural Science Foundation of China (No. 50376042)Doctoral Program Foundation of Institute of Higher Education of China (20040425007).
文摘Based on the analysis of high-speed video images, the detachment behavior of dust cake from the ceramic candle filter surface during pulse cleaning process is investigated. The influences of the dust cake loading,the reservoir pressure, and the filtration velocity on the cleaning effectiveness are analyzed. Experimental results show that there exists an optimum dust cake thickness for pulse-cleaning process. For thin dust cake, the patchy cleaning exists and the cleaning efficiency is low; if the dust cake is too thick, the pressure drop across the dust cake becomes higher and a higher reservoir pressure may be needed. At the same time there also exists an optimum reservoir pressure for a given filtration condition.
文摘The particle morphology and surface texture play a major role in influencing mechanical and hydraulic behaviors of sandy soils. This paper presents the use of digital image analysis combined with fractal theory as a tool to quantify the particle morphology and surface texture of two types of quartz sands widely used in the region of Vitória, Espírito Santo, southeast of Brazil. The two investigated sands are sampled from different locations. The purpose of this paper is to present a simple, straightforward,reliable and reproducible methodology that can identify representative sandy soil texture parameters.The test results of the soil samples of the two sands separated by sieving into six size fractions are presented and discussed. The main advantages of the adopted methodology are its simplicity, reliability of the results, and relatively low cost. The results show that sands from the coastal spit(BS) have a greater degree of roundness and a smoother surface texture than river sands(RS). The values obtained in the test are statistically analyzed, and again it is confirmed that the BS sand has a slightly greater degree of sphericity than that of the RS sand. Moreover, the RS sand with rough surface texture has larger specific surface area values than the similar BS sand, which agree with the obtained roughness fractal dimensions. The consistent experimental results demonstrate that image analysis combined with fractal theory is an accurate and efficient method to quantify the differences in particle morphology and surface texture of quartz sands.
基金Founded by National Basic Research Program of China(973 Program)(No.2009CB623203)National Natural Science Foundation of China(No.51078186)Jiangsu Natural Science Foundation(No.BK2010071)
文摘The degradation mechanisms of cementitious materials exposed to sulfate solutions have been controversial, despite considerable research. In this paper, two methodologies of image analysis based on scanning electron microscope and chemical mapping are used to analyse Portland cement mortars exposed to sodium sulfate solution. The effects of sulfate concentration in solution and water to cement ratio of mortar, which are considered as the most sensitive factors to sulfate attack, are investigated respectively by comparing the macro expansion with microstructure analysis. It is found that the sulfate concentration in pore solution, expressed as sulfate content in C-S-H, plays a critical role on the supersaturation with respect to ettringite and so on the expansion force generated.
文摘In this study, mitotic metaphase chromosomes in mouse were identified by a new chromosome fluorescence banding technique combining DAPI staining with image analysis. Clear 4＇, 6-diamidino-2-phenylindole （DAPI） multiple bands like （J-hands could be produced in mouse. The Meta- Morph software was then used to generate linescans of pixel intensity for the banded chromosomes from short arm to long arm. These linescans were sufficient not only to identify each individual chromosome but also analyze the physical sites of bands in chromosome. Based on the results, the clear and accurate karyotype of mouse metaphase chromosomes was established. The technique is therefore considered to he a new method for cytological studies of mouse.
基金supported by a grant rrom the Morris Animal Foundation
文摘Mammalian pelage color can vary among individuals of many species, although this intraspecific variation is oftenoverlooked by researchers, perhaps because of its sometimes subtle nature and difficulty in assessing it quantitatively. Thus, suchvariation is rarely studied in mammals, and this is especially true within the order Chiroptera, where there has been very little empiricalresearch. We examined museum specimens of red bats (Lasiurus borealis, family Vespertilionidae) from Georgia, USA, todetermine the extent of sexual dimorphism in pelage color and to explore possible associations between body size and pelagecolor. We photographed 54 specimens under uniform lighting, and used an image analysis program to measure pelage hue on theuropatagium region, which is fully furred in members of the genus Lasiurus. Statistical analyses of pelage hue scores showedmales had significantly redder pelage than females when considered alone, but when examined together with effects of body sizeand collection year, sex was not significant, and collection year and body size were. More recent specimens tended to be less redthan older specimens, which might indicate a wearing of the buffy tips of hairs from older specimens, and smaller bats of bothsexes tended to be more red. These interesting findings are encouraging and we suggest that future explorations into intraspecificvariation in pelage color of bats using this or similar approaches are warranted to clarify the significance of the patterns. Thisstudy also demonstrated that care must be taken in analyses of mammalian pelage color from older museum skins, or at least thatresearchers must take into account the age of the specimens .
基金This work was supported by Science and Technology Project of State Grid Corporation“Research on Key Technologies of Power Artificial Intelligence Open Platform”(5700-202155260A-0-0-00).
文摘The continuous growth in the scale of unmanned aerial vehicle (UAV) applications in transmission line inspection has resulted in a corresponding increase in the demand for UAV inspection image processing. Owing to its excellent performance in computer vision, deep learning has been applied to UAV inspection image processing tasks such as power line identification and insulator defect detection. Despite their excellent performance, electric power UAV inspection image processing models based on deep learning face several problems such as a small application scope, the need for constant retraining and optimization, and high R&D monetary and time costs due to the black-box and scene data-driven characteristics of deep learning. In this study, an automated deep learning system for electric power UAV inspection image analysis and processing is proposed as a solution to the aforementioned problems. This system design is based on the three critical design principles of generalizability, extensibility, and automation. Pre-trained models, fine-tuning (downstream task adaptation), and automated machine learning, which are closely related to these design principles, are reviewed. In addition, an automated deep learning system architecture for electric power UAV inspection image analysis and processing is presented. A prototype system was constructed and experiments were conducted on the two electric power UAV inspection image analysis and processing tasks of insulator self-detonation and bird nest recognition. The models constructed using the prototype system achieved 91.36% and 86.13% mAP for insulator self-detonation and bird nest recognition, respectively. This demonstrates that the system design concept is reasonable and the system architecture feasible .
基金This project was supported by a grant from Hubei Provincial Natural Sciences Foundation of China (No. 2004 ABA200).
文摘The changes of retinal nuclear DNA content in rats after death was detected and the relationship between degradation of retinal nuclear DNA and postmortem interval （PMI） was analyzed. Ninety healthy adult SD rats, female, weighing 250±10 g, were randomly divided into 15 groups. At 20 ℃, the retinal cells were withdrawn every 2 h within 0 to 28 h after death and stained with Feulgen-Vans. Index of density （ID）, integral absorbance （IA） and average absorbance （AA） in retinal nucleus were analyzed by image analysis system. And the obtained data were subjected to linear regression analysis by using SPSS12.0 software. The results showed that in retinal nucleus, AA and IA were gradually declined with the prolongation of PMI, while ID had an increased tendency. Within 28 h after PMI, the regression equations were as follows： YAA=-0.009XAA＋0.590 （R^2=0.949）, YIA=0.097XIA＋18.903 （R^2=0.968）, YID=0.122XID＋2.246 （R^2=0.951）. It was concluded that retinal nuclear DNA after death in rats was degraded gradually and had a good correlation with PMI.
基金This research was supported by the Research Fund for Etoctoral Program of Higher Education (No. 99025508)
文摘The objective assessment of fabric pilling based on light projection and image analysis has been exploited recently.The device for capturing the cross-sectional images of the pilled fabrics with light projection is elaborated.The detection of the profile line and integration of the sequential cross-sectional pilled image are discussed.The threshold based on Gaussian model is recommended for pill segmentation.The results show that the installed system is capable of eliminating the interference with pill information from the fabric color and pattern.
基金National Basic Research Program of China (973 Program) (No. 2009CB623200)National Natural Science Foundation of China (Nos. 50908104 and 50978126)
文摘A new test method was introduced to measure fiber distribution in steel fiber reinforced mortar by using image analysis technique. Through specimen preparation, image acquisition, fiber extraction, and measurement of related fiber parameters, quantitative analysis of fiber distribution could be obtained by two parameters, namely dispersion coefficient and orientation factor. Effect of boundaries, size and steel fiber content on fiber distribution was discussed. Results showed that, steel fiber distribution was affected by boundary effect, which would be weakened with the increase of specimen size. If the length and width remained constant, the specimen height had a significant effect on orientation factor of fiber, while its influence on dispersion coefficient was not so obvious. With the increase of steel fiber content, dispersion coefficient decreased slightly, and orientation factor deviated from 0.5.
文摘In this study, a new method for quantitative and efficient measurement for the ground surface movement was developed. The feature of this technique is to identify geomorphic characteristics by image matching analysis, using the intelligent images made from high resolution DEM(Digital Elevation Model). This method is useful to extract the small ground displacement where the surface shape was not intensely deformed.
基金This work is partly supported by the Fundamental Research Funds for the Central Universities of China under grants GK202003080the Natural Science Foundation of Shaanxi Province under Grants 2021JM-205the UK Engineering and Physical Sciences Research Council through grants EP/V034111/1.
文摘Malaria is an important and worldwide fatal disease that has been widely reported by the World Health Organization(WHO),and it has about 219 million cases worldwide,with 435,000 of those mortal.The common malaria diagnosis approach is heavily reliant on highly trained experts,who use a microscope to examine the samples.Therefore,there is a need to create an automated solution for the diagnosis of malaria.One of the main objectives of this work is to create a design tool that could be used to diagnose malaria from the image of a blood sample.In this paper,we firstly developed a graphical user interface that could be used to help segment red blood cells and infected cells and allow the users to analyze the blood samples.Secondly,a Feed-forward Neural Network(FNN)is designed to classify the cells into two classes.The achieved results show that the proposed techniques can be used to detect malaria,as it has achieved 92%accuracy with a database that contains 27,560 benchmark images.
文摘Corneal opacity is one of the most commonly used parameters for estimating postmortem interval （PMI）. This paper proposes a new method to study the relationship between changes of corneal opacity and PMI by processing and analyzing cornea images. Corneal regions were extracted from images of rabbits＇ eyes and described by color-based and texture-based features, which could represent the changes of cornea at different PMI. A KNN classifier was used to reveal the association of image features and PMI. The result of the classification showed that the new method was reliable and effective.
文摘The presence of nonmetallic inclusion particles which appear during steelmaking process is harmful to the properties of steels, which is mainly as a function of some aspects such as size, volume fraction, shape, and distribution of these particles. The automatic image analysis technique is one of the most important tools for the quantitative determination of these parameters. The classical Student approach and the Extreme Values Method （EVM） were used for the inclusion size and shape determination and the evaluation of distance between the inclusion particles. The results thus obtained indicated that there were significant differences in the characteristics of the inclusion particles in the analyzed products. Both methods achieved results with some differences, indicating that EVM could be used as a faster and more reliable statistical methodology.
基金The project was supported by a grant form the Wuhan Mu-nicipal Chengguang Research Program (No 20015005049)
文摘This study evaluated the correlation between DNA degradation of the splenic lymphocytes and the early time of death, examined the early time of death by computerized image analysis technique （CIAT） and identified the best parameter that quantitatively reflects the DNA degradation. The spleen tissues from 34 SD rats were collected, subjected to cell smearing every 2 h within the first 36 h after death, stained by Feulgen-Van＇s staining, three indices reflecting DNA content in splenic lymphocytes, including integral optical density （IOD）, average optical density （AOD）, average gray scale （AG） were measured by the image analysis. Our results showed that IOD and AOD decreased and AG increased over time within the first 36 h. A stepwise linear regression analysis showed that only AG was fitted. A correlation between the postmortem interval （PMI） and AG was identified and the corresponding regression equation was obtained. Our study suggests that CIAT is a useful and promising tool for the estimation of early PMI with good objectivity and reproducibility, and AG is a more effective and better quantitative indicator for the estimation of PMI within the first 36 h after death in rats.
