Assessment and Visualization of Ki67 Heterogeneity in Breast Cancers through Digital Image Analysis

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.

Automated deep learning system for power line inspection image analysis and processing: architecture and design issues

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 .

Enhanced Tunicate Swarm Optimization with Transfer Learning Enabled Medical Image Analysis System

Medical image analysis is an active research topic,with thousands of studies published in the past few years.Transfer learning(TL)including convolutional neural networks(CNNs)focused to enhance efficiency on an innovative task using the knowledge of the same tasks learnt in advance.It has played a major role in medical image analysis since it solves the data scarcity issue along with that it saves hardware resources and time.This study develops an EnhancedTunicate SwarmOptimization withTransfer Learning EnabledMedical Image Analysis System(ETSOTL-MIAS).The goal of the ETSOTL-MIAS technique lies in the identification and classification of diseases through medical imaging.The ETSOTL-MIAS technique involves the Chan Vese segmentation technique to identify the affected regions in the medical image.For feature extraction purposes,the ETSOTL-MIAS technique designs a modified DarkNet-53 model.To avoid the manual hyperparameter adjustment process,the ETSOTLMIAS technique exploits the ETSO algorithm,showing the novelty of the work.Finally,the classification of medical images takes place by random forest(RF)classifier.The performance validation of the ETSOTL-MIAS technique is tested on a benchmark medical image database.The extensive experimental analysis showed the promising performance of the ETSOTL-MIAS technique under different measures.

Political Optimizer with Deep Learning-Enabled Tongue Color Image Analysis Model

Biomedical image processing is widely utilized for disease detection and classification of biomedical images.Tongue color image analysis is an effective and non-invasive tool for carrying out secondary detection at anytime and anywhere.For removing the qualitative aspect,tongue images are quantitatively inspected,proposing a novel disease classification model in an automated way is preferable.This article introduces a novel political optimizer with deep learning enabled tongue color image analysis(PODL-TCIA)technique.The presented PODL-TCIA model purposes to detect the occurrence of the disease by examining the color of the tongue.To attain this,the PODL-TCIA model initially performs image pre-processing to enhance medical image quality.Followed by,Inception with ResNet-v2 model is employed for feature extraction.Besides,political optimizer(PO)with twin support vector machine(TSVM)model is exploited for image classification process,shows the novelty of the work.The design of PO algorithm assists in the optimal parameter selection of the TSVM model.For ensuring the enhanced outcomes of the PODL-TCIA model,a wide-ranging experimental analysis was applied and the outcomes reported the betterment of the PODL-TCIA model over the recent approaches.

Geometric prior guided hybrid deep neural network for facial beauty analysis

Facial beauty analysis is an important topic in human society.It may be used as a guidance for face beautification applications such as cosmetic surgery.Deep neural networks(DNNs)have recently been adopted for facial beauty analysis and have achieved remarkable performance.However,most existing DNN-based models regard facial beauty analysis as a normal classification task.They ignore important prior knowledge in traditional machine learning models which illustrate the significant contribution of the geometric features in facial beauty analysis.To be specific,landmarks of the whole face and facial organs are introduced to extract geometric features to make the decision.Inspired by this,we introduce a novel dual-branch network for facial beauty analysis:one branch takes the Swin Transformer as the backbone to model the full face and global patterns,and another branch focuses on the masked facial organs with the residual network to model the local patterns of certain facial parts.Additionally,the designed multi-scale feature fusion module can further facilitate our network to learn complementary semantic information between the two branches.In model optimisation,we propose a hybrid loss function,where especially geometric regulation is introduced by regressing the facial landmarks and it can force the extracted features to convey facial geometric features.Experiments performed on the SCUT-FBP5500 dataset and the SCUT-FBP dataset demonstrate that our model outperforms the state-of-the-art convolutional neural networks models,which proves the effectiveness of the proposed geometric regularisation and dual-branch structure with the hybrid network.To the best of our knowledge,this is the first study to introduce a Vision Transformer into the facial beauty analysis task.

Application and progress of artificial intelligence technology in the segmentation of hyperreflective foci in OCT images for ophthalmic disease research

With the advancement of retinal imaging,hyperreflective foci(HRF)on optical coherence tomography(OCT)images have gained significant attention as potential biological biomarkers for retinal neuroinflammation.However,these biomarkers,represented by HRF,present pose challenges in terms of localization,quantification,and require substantial time and resources.In recent years,the progress and utilization of artificial intelligence(AI)have provided powerful tools for the analysis of biological markers.AI technology enables use machine learning(ML),deep learning(DL)and other technologies to precise characterization of changes in biological biomarkers during disease progression and facilitates quantitative assessments.Based on ophthalmic images,AI has significant implications for early screening,diagnostic grading,treatment efficacy evaluation,treatment recommendations,and prognosis development in common ophthalmic diseases.Moreover,it will help reduce the reliance of the healthcare system on human labor,which has the potential to simplify and expedite clinical trials,enhance the reliability and professionalism of disease management,and improve the prediction of adverse events.This article offers a comprehensive review of the application of AI in combination with HRF on OCT images in ophthalmic diseases including age-related macular degeneration(AMD),diabetic macular edema(DME),retinal vein occlusion(RVO)and other retinal diseases and presents prospects for their utilization.

DeepSVDNet:A Deep Learning-Based Approach for Detecting and Classifying Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

Artificial Intelligence(AI)is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy(VTDR),which is a leading cause of visual impairment and blindness worldwide.However,previous automated VTDR detection methods have mainly relied on manual feature extraction and classification,leading to errors.This paper proposes a novel VTDR detection and classification model that combines different models through majority voting.Our proposed methodology involves preprocessing,data augmentation,feature extraction,and classification stages.We use a hybrid convolutional neural network-singular value decomposition(CNN-SVD)model for feature extraction and selection and an improved SVM-RBF with a Decision Tree(DT)and K-Nearest Neighbor(KNN)for classification.We tested our model on the IDRiD dataset and achieved an accuracy of 98.06%,a sensitivity of 83.67%,and a specificity of 100%for DR detection and evaluation tests,respectively.Our proposed approach outperforms baseline techniques and provides a more robust and accurate method for VTDR detection.

Use of high-resolution X-ray computed tomography and 3D image analysis to quantify mineral dissemination and pore space in oxide copper ore particles

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.

Fluorescence Microscopic Image Analysis of Nucleic Acids Based on The Capillary Flow Directed Assembly Ring of Neutral Red-nucleic Acid Supramolecular Complexes

It is critical to establish a direct and precise method with a high sensitivity and selectivity in analytical chemistry. In this research, making use of a well known phenomenon of capillary flow, we have proposed an image analysis method of nucleic acids at the price of a small amount of sample. When a droplet of the supramolecular complex solution, formed by neutral red and nucleic acids(NA) under an approximate neutral condition, was placed on the hydrophobic surface of dimethyl dichlorosilane pretreated glass slides, and it was evaporated, the supramolecular complex exhibited the periphery of the droplet due to the capillary effect, and accumulated there to form a red capillary flow directed assembly ring(CFDAR). A typical CFDAR has an outer diameter of (2 r ) about 1.18 mm and a ring width(2 δ ) of about 41 μm. Depending on the experimental conditions, a variety of CFDAR can be assembled. The experimental results are in agreement with our former theoretical discussion. It was found that when a droplet volume is 0.1 μL, the fluorescence intensity of the CFDAR formed by the NR NA is in proportion to the content of calf thymus DNA in the range of 0-0.28 ng, fish sperm DNA of 0-0.24 ng and yeast RNA of 0-0.16 ng with the limit of detection(3 σ ) of 1 7, 1.4 and 0.9 pg, respectively for the three nucleic acids.

Use of digital image analysis combined with fractal theory to determine particle morphology and surface texture of quartz sands

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.

Multi-Modality Medical Image Fusion Based on Wavelet Analysis and Quality Evaluation

Multi-modality medical image fusion has more and more important applications in medical image analysis and understanding. In this paper, we develop and apply a multi-resolution method based on wavelet pyramid to fuse medical images from different modalities such as PET-MRI and CT-MRI. In particular, we evaluate the different fusion results when applying different selection rules and obtain optimum combination of fusion parameters.

Application of Image Analysis Based on SEM and Chemical Mapping on PC Mortars under Sulfate Attack

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.

Mouse Karyotype Obtained by Combining DAPI Staining with Image Analysis

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.

Image Analysis for Degradation of DNA in Retinal Nuclei of Rat after Death

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.

Assessment of Fiber Distribution in Steel Fiber Mortar Using Image Analysis

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.

Analysis of Two-Dimensional Gel Electrophoresis Images of Protein from Posterior Silk Gland of Silkworm (Bombyx mori) on Day 1 and Day 4 in the 5th Instar Stage

The posterior silk gland （PSG） of silkworm is an important organ where fibroin is synthesized and secreted exclusively. Because fibroin constitutes 75-80% of the silk filament, the mechanism governing fibroin secretion, quality and yield of cocoon can be elucidated by the study on the PSG. Using two-dimensional gel electrophoresis （2-DE） and image analysis system, the changes in the protein composition in the PSG cell were investigated on the day 1 （D1） and day 4 （D4） in the 5th instar stage from five different strains of silkworm （Bombyx mori）. While differences at protein level between days and strains were far less than those observed at the gene level using EST analysis. The change trends in protein composition from D1 to D4 were diverse among the different strains. The results suggest that the secretion of fibroin is regulated by multiple proteins. The site of regulation and the proteins responsible for the regulation vary with the strain, which leads to differences between strains in the capacity of fibroin secretion in the PSG cell.

Image Analysis on Corneal Opacity:A Novel Method to Estimate Postmortem Interval in Rabbits

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.

An approach for wellbore failure analysis using rock cavings and image processing

There have been interests to link different cuttings/cavings to various wellbore failure types during drilling. This concept is essential when caliper and image logs are not available. Identification ofwellbore failure during drilling gives more chance of immediate actions before wireline logging program. In this paper, an approach was presented based on the image processing of ditch cuttings. This approach uses the sphericity and roundness of cuttings as input data to classify caving types and subsequently deter- mine the dominant failure type. Likewise, common definitions of cavings were discussed initially before a new criterion is suggested. This quantitative criterion was examined by observations from caliper and acoustic image logs as well. The proposed approach and criterion were implemented on ditch cuttings taken from a well in Western Australia. Results indicate that the primary failure is shear failure （breakout） due to high levels of angular cavings. However, another failure due to the fluid invasion into pre-existing fractures was also recorded by blocky cavings.

Determination of the Early Time of Death by Computerized Image Analysis of DNA Degradation: Which Is the Best Quantitative Indicator of DNA Degradation?

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.

Image analysis and machine learning-based malaria assessment system

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.