Starting from the diffraction imaging process,we have discussed the relationship between optical imaging system and fractional Fourier transform, and proposed a specific system which can form an inverse amplified imag...Starting from the diffraction imaging process,we have discussed the relationship between optical imaging system and fractional Fourier transform, and proposed a specific system which can form an inverse amplified image of input function.展开更多
BACKGROUND Conventional plain X-ray images of rats,the most common animals used as degeneration models,exhibit unclear vertebral structure and blurry intervertebral disc spaces due to their small size,slender vertebra...BACKGROUND Conventional plain X-ray images of rats,the most common animals used as degeneration models,exhibit unclear vertebral structure and blurry intervertebral disc spaces due to their small size,slender vertebral bodies.AIM To apply molybdenum target X-ray photography in the evaluation of caudal intervertebral disc(IVD)degeneration in rat models.METHODS Two types of rat caudal IVD degeneration models(needle-punctured model and endplate-destructed model)were established,and their effectiveness was verified using nuclear magnetic resonance imaging.Molybdenum target inspection and routine plain X-ray were then performed on these models.Additionally,four observers were assigned to measure the intervertebral height of degenerated segments on molybdenum target plain X-ray images and routine plain X-ray images,respectively.The degeneration was evaluated and statistical analysis was subsequently conducted.RESULTS Nine rats in the needle-punctured model and 10 rats in the endplate-destructed model were effective.Compared with routine plain X-ray images,molybdenum target plain X-ray images showed higher clarity,stronger contrast,as well as clearer and more accurate structural development.The McNemar test confirmed that the difference was statistically significant(P=0.031).In the two models,the reliability of the intervertebral height measured by the four observers on routine plain X-ray images was poor(ICC<0.4),while the data obtained from the molybdenum target plain X-ray images were more reliable.CONCLUSIONMolybdenum target inspection can obtain clearer images and display fine calcification in the imaging evaluation of caudal IVD degeneration in rats,thus ensuring a more accurate evaluation of degeneration.展开更多
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 ...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.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
Subcutaneous vein network plays important roles to maintain microcirculation that is related to some diagnostic aspects.Despite developments of optical imaging technologies,still the difficulties about deep skin vascu...Subcutaneous vein network plays important roles to maintain microcirculation that is related to some diagnostic aspects.Despite developments of optical imaging technologies,still the difficulties about deep skin vascular imaging have been continued.On the other hand,since hemoglobin con-centration of human blood has key role in the veins imaging by optical manner,the used wavelength in vascular imaging,must be chosen considering absorption of hemoglobin.In this research,we constructed a near infrared(NIR)light source because of lower absorption of hemoglobin in this optical region.To obtain vascular image,reflectance geometry was used.Next,from recorded images,vascular network analysis,such as calculation of width of vascular of interest and complexity of selected region were implemented.By comparing with other modalities,we observed that proposed imaging system has great advantages including nonionized radiation,moderate penetration depth of 0.5-3 mm and diameter of 1 mm,cost-effective and algorit hmic simplicity for analysis.展开更多
Sensor-based ore sorting is a technology used to classify high-grade mineralized rocks from low-grade waste rocks to reduce operation costs.Many ore-sorting algorithms using color images have been proposed in the past...Sensor-based ore sorting is a technology used to classify high-grade mineralized rocks from low-grade waste rocks to reduce operation costs.Many ore-sorting algorithms using color images have been proposed in the past,but only some validate their results using mineral grades or optimize the algorithms to classify rocks in real-time.This paper presents an ore-sorting algorithm based on image processing and machine learning that is able to classify rocks from a gold and silver mine based on their grade.The algorithm is composed of four main stages:(1)image segmentation and partition,(2)color and texture feature extraction,(3)sub-image classification using neural networks,and(4)a voting system to determine the overall class of the rock.The algorithm was trained using images of rocks that a geologist manually classified according to their mineral content and then was validated using a different set of rocks analyzed in a laboratory to determine their gold and silver grades.The proposed method achieved a Matthews correlation coefficient of 0.961 points,higher than other classification algorithms based on support vector machines and convolutional neural networks,and a processing time under 44 ms,promising for real-time ore sorting applications.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
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 innova...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.展开更多
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 an...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.展开更多
The earliest and most accurate detection of the pathological manifestations of hepatic diseases ensures effective treatments and thus positive prognostic outcomes.In clinical settings,screening and determining the ext...The earliest and most accurate detection of the pathological manifestations of hepatic diseases ensures effective treatments and thus positive prognostic outcomes.In clinical settings,screening and determining the extent of a pathology are prominent factors in preparing remedial agents and administering approp-riate therapeutic procedures.Moreover,in a patient undergoing liver resection,a realistic preoperative simulation of the subject-specific anatomy and physiology also plays a vital part in conducting initial assessments,making surgical decisions during the procedure,and anticipating postoperative results.Conventionally,various medical imaging modalities,e.g.,computed tomography,magnetic resonance imaging,and positron emission tomography,have been employed to assist in these tasks.In fact,several standardized procedures,such as lesion detection and liver segmentation,are also incorporated into prominent commercial software packages.Thus far,most integrated software as a medical device typically involves tedious interactions from the physician,such as manual delineation and empirical adjustments,as per a given patient.With the rapid progress in digital health approaches,especially medical image analysis,a wide range of computer algorithms have been proposed to facilitate those procedures.They include pattern recognition of a liver,its periphery,and lesion,as well as pre-and postoperative simulations.Prior to clinical adoption,however,software must conform to regulatory requirements set by the governing agency,for instance,valid clinical association and analytical and clinical validation.Therefore,this paper provides a detailed account and discussion of the state-of-the-art methods for liver image analyses,visualization,and simulation in the literature.Emphasis is placed upon their concepts,algorithmic classifications,merits,limitations,clinical considerations,and future research trends.展开更多
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...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.展开更多
Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on...Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.展开更多
Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing oc...Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely.However,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model complexity.To alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular diseases.In MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer parameters.We conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 datasets.The results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and MixNets.Specifically,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.展开更多
As a widely used food preservative,methyl paraben was experimentally evidenced with serious hormonelike adverse effects.Herein,a high performance thin-layer chromatography platformed bioluminescent bioautography and i...As a widely used food preservative,methyl paraben was experimentally evidenced with serious hormonelike adverse effects.Herein,a high performance thin-layer chromatography platformed bioluminescent bioautography and image analysis for the selective quantification and confirmation of methyl paraben was proposed and validated in vinegar and coconut juice.First,the detectability of the bioautography to the analyte on different layer materials was estimated,revealing that normal silica gel was the best choice.After that,the liquid of sample extract and working solution were separated to overcome the background noises due to co-extracted matrices.The separation result was then coupled to the optimized bioautography,enabling instant and straightforward screening of the targeted conpound.For accurate quantification,bioluninescent inhibition pattern caused by the analyte was processed by image analysis,giving useful sensitivity(LOD>16 mg/kg),precision(RSD<10.1%)and accuracy(spike-recovery rate 76.9%-112.2%).Finally,the suspected result was confirmed by determining its MS fingerprint,further strengthening the reliability of screening.展开更多
Cardiovascular disease is the leading cause of death globally.This disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may ...Cardiovascular disease is the leading cause of death globally.This disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may depend on receiving timely assistance as soon as possible.Thus,minimizing the death ratio can be achieved by early detection of heart attack(HA)symptoms.In the United States alone,an estimated 610,000 people die fromheart attacks each year,accounting for one in every four fatalities.However,by identifying and reporting heart attack symptoms early on,it is possible to reduce damage and save many lives significantly.Our objective is to devise an algorithm aimed at helping individuals,particularly elderly individuals living independently,to safeguard their lives.To address these challenges,we employ deep learning techniques.We have utilized a vision transformer(ViT)to address this problem.However,it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product attention.Also,since transformer performance typically relies on large-scale or adequate data,adapting ViT for smaller datasets is more challenging.In response,we propose a three-in-one steam model,theMulti-Head Attention Vision Hybrid(MHAVH).Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques,such as ResNet-50 and VGG-16,renowned for their robust feature extraction capabilities.By incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities,we leverage a 2019 posture-based dataset comprising RGB images,a novel creation by the author that marks the first dataset tailored for posture-based heart attack detection.Given the limited online data availability,we segmented this dataset into gender categories(male and female)and conducted testing on both segmented and original datasets.The training accuracy of our model reached an impressive 99.77%.Upon testing,the accuracy for male and female datasets was recorded at 92.87%and 75.47%,respectively.The combined dataset accuracy is 93.96%,showcasing a commendable performance overall.Our proposed approach demonstrates versatility in accommodating small and large datasets,offering promising prospects for real-world applications.展开更多
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,th...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.展开更多
Although previous studies have made some clear leap in learning latent dynamics from high-dimensional representations,the performances in terms of accuracy and inference time of long-term model prediction still need t...Although previous studies have made some clear leap in learning latent dynamics from high-dimensional representations,the performances in terms of accuracy and inference time of long-term model prediction still need to be improved.In this study,a deep convolutional network based on the Koopman operator(CKNet)is proposed to model non-linear systems with pixel-level measurements for long-term prediction.CKNet adopts an autoencoder network architecture,consisting of an encoder to generate latent states and a linear dynamical model(i.e.,the Koopman operator)which evolves in the latent state space spanned by the encoder.The decoder is used to recover images from latent states.According to a multi-step ahead prediction loss function,the system matrices for approximating the Koopman operator are trained synchronously with the autoencoder in a mini-batch manner.In this manner,gradients can be synchronously transmitted to both the system matrices and the autoencoder to help the encoder self-adaptively tune the latent state space in the training process,and the resulting model is time-invariant in the latent space.Therefore,the proposed CKNet has the advantages of less inference time and high accuracy for long-term prediction.Experiments are per-formed on OpenAI Gym and Mujoco environments,including two and four non-linear forced dynamical systems with continuous action spaces.The experimental results show that CKNet has strong long-term prediction capabilities with sufficient precision.展开更多
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 ...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.展开更多
Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a ...Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.展开更多
文摘Starting from the diffraction imaging process,we have discussed the relationship between optical imaging system and fractional Fourier transform, and proposed a specific system which can form an inverse amplified image of input function.
基金Supported by the National Key Research and Development Program of China,No.2017YFA0105404。
文摘BACKGROUND Conventional plain X-ray images of rats,the most common animals used as degeneration models,exhibit unclear vertebral structure and blurry intervertebral disc spaces due to their small size,slender vertebral bodies.AIM To apply molybdenum target X-ray photography in the evaluation of caudal intervertebral disc(IVD)degeneration in rat models.METHODS Two types of rat caudal IVD degeneration models(needle-punctured model and endplate-destructed model)were established,and their effectiveness was verified using nuclear magnetic resonance imaging.Molybdenum target inspection and routine plain X-ray were then performed on these models.Additionally,four observers were assigned to measure the intervertebral height of degenerated segments on molybdenum target plain X-ray images and routine plain X-ray images,respectively.The degeneration was evaluated and statistical analysis was subsequently conducted.RESULTS Nine rats in the needle-punctured model and 10 rats in the endplate-destructed model were effective.Compared with routine plain X-ray images,molybdenum target plain X-ray images showed higher clarity,stronger contrast,as well as clearer and more accurate structural development.The McNemar test confirmed that the difference was statistically significant(P=0.031).In the two models,the reliability of the intervertebral height measured by the four observers on routine plain X-ray images was poor(ICC<0.4),while the data obtained from the molybdenum target plain X-ray images were more reliable.CONCLUSIONMolybdenum target inspection can obtain clearer images and display fine calcification in the imaging evaluation of caudal IVD degeneration in rats,thus ensuring a more accurate evaluation of degeneration.
基金Shenzhen Science and Technology Program,Grant/Award Number:ZDSYS20211021111415025Shenzhen Institute of Artificial Intelligence and Robotics for SocietyYouth Science and Technology Talents Development Project of Guizhou Education Department,Grant/Award Number:QianJiaoheKYZi[2018]459。
文摘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.
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Scientic and Technological Research Council of Turkey(TUBITAK),under grand,No:113E771.
文摘Subcutaneous vein network plays important roles to maintain microcirculation that is related to some diagnostic aspects.Despite developments of optical imaging technologies,still the difficulties about deep skin vascular imaging have been continued.On the other hand,since hemoglobin con-centration of human blood has key role in the veins imaging by optical manner,the used wavelength in vascular imaging,must be chosen considering absorption of hemoglobin.In this research,we constructed a near infrared(NIR)light source because of lower absorption of hemoglobin in this optical region.To obtain vascular image,reflectance geometry was used.Next,from recorded images,vascular network analysis,such as calculation of width of vascular of interest and complexity of selected region were implemented.By comparing with other modalities,we observed that proposed imaging system has great advantages including nonionized radiation,moderate penetration depth of 0.5-3 mm and diameter of 1 mm,cost-effective and algorit hmic simplicity for analysis.
文摘Sensor-based ore sorting is a technology used to classify high-grade mineralized rocks from low-grade waste rocks to reduce operation costs.Many ore-sorting algorithms using color images have been proposed in the past,but only some validate their results using mineral grades or optimize the algorithms to classify rocks in real-time.This paper presents an ore-sorting algorithm based on image processing and machine learning that is able to classify rocks from a gold and silver mine based on their grade.The algorithm is composed of four main stages:(1)image segmentation and partition,(2)color and texture feature extraction,(3)sub-image classification using neural networks,and(4)a voting system to determine the overall class of the rock.The algorithm was trained using images of rocks that a geologist manually classified according to their mineral content and then was validated using a different set of rocks analyzed in a laboratory to determine their gold and silver grades.The proposed method achieved a Matthews correlation coefficient of 0.961 points,higher than other classification algorithms based on support vector machines and convolutional neural networks,and a processing time under 44 ms,promising for real-time ore sorting applications.
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support for this work from the Deanship of Scientific Research (DSR),University of Tabuk,Tabuk,Saudi Arabia,under grant number S-1440-0262.
文摘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.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under grant number(RGP 2/158/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R161)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQU4340237DSR11).
文摘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.
文摘The earliest and most accurate detection of the pathological manifestations of hepatic diseases ensures effective treatments and thus positive prognostic outcomes.In clinical settings,screening and determining the extent of a pathology are prominent factors in preparing remedial agents and administering approp-riate therapeutic procedures.Moreover,in a patient undergoing liver resection,a realistic preoperative simulation of the subject-specific anatomy and physiology also plays a vital part in conducting initial assessments,making surgical decisions during the procedure,and anticipating postoperative results.Conventionally,various medical imaging modalities,e.g.,computed tomography,magnetic resonance imaging,and positron emission tomography,have been employed to assist in these tasks.In fact,several standardized procedures,such as lesion detection and liver segmentation,are also incorporated into prominent commercial software packages.Thus far,most integrated software as a medical device typically involves tedious interactions from the physician,such as manual delineation and empirical adjustments,as per a given patient.With the rapid progress in digital health approaches,especially medical image analysis,a wide range of computer algorithms have been proposed to facilitate those procedures.They include pattern recognition of a liver,its periphery,and lesion,as well as pre-and postoperative simulations.Prior to clinical adoption,however,software must conform to regulatory requirements set by the governing agency,for instance,valid clinical association and analytical and clinical validation.Therefore,this paper provides a detailed account and discussion of the state-of-the-art methods for liver image analyses,visualization,and simulation in the literature.Emphasis is placed upon their concepts,algorithmic classifications,merits,limitations,clinical considerations,and future research trends.
基金Supported by the NationalNaturalScience Foundation of China( No. 2 0 175 0 1) and U niversity Key Teachers Programdirected under the Ministry of Education ofP.R.China( No. 2 0 0 0 - 6 5 )
文摘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.
基金supported by MRC,UK (MC_PC_17171)Royal Society,UK (RP202G0230)+8 种基金BHF,UK (AA/18/3/34220)Hope Foundation for Cancer Research,UK (RM60G0680)GCRF,UK (P202PF11)Sino-UK Industrial Fund,UK (RP202G0289)LIAS,UK (P202ED10,P202RE969)Data Science Enhancement Fund,UK (P202RE237)Fight for Sight,UK (24NN201)Sino-UK Education Fund,UK (OP202006)BBSRC,UK (RM32G0178B8).
文摘Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.
基金Stable Support Plan Program,Grant/Award Number:20200925174052004Shenzhen Natural Science Fund,Grant/Award Number:JCYJ20200109140820699+2 种基金National Natural Science Foundation of China,Grant/Award Number:82272086Guangdong Provincial Department of Education,Grant/Award Numbers:2020ZDZX3043,SJZLGC202202Guangdong Provincial Key Laboratory,Grant/Award Number:2020B121201001。
文摘Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely.However,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model complexity.To alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular diseases.In MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer parameters.We conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 datasets.The results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and MixNets.Specifically,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.
基金financially supported by National Natural Science Foundation of China (21804058)Shanxi Postdoc Reward (SXBYKY2022001)+1 种基金Shanxi Scholarship Council of China (2021068)Shanxi Agricultural University High-Level Talent Project (2021XG013)。
文摘As a widely used food preservative,methyl paraben was experimentally evidenced with serious hormonelike adverse effects.Herein,a high performance thin-layer chromatography platformed bioluminescent bioautography and image analysis for the selective quantification and confirmation of methyl paraben was proposed and validated in vinegar and coconut juice.First,the detectability of the bioautography to the analyte on different layer materials was estimated,revealing that normal silica gel was the best choice.After that,the liquid of sample extract and working solution were separated to overcome the background noises due to co-extracted matrices.The separation result was then coupled to the optimized bioautography,enabling instant and straightforward screening of the targeted conpound.For accurate quantification,bioluninescent inhibition pattern caused by the analyte was processed by image analysis,giving useful sensitivity(LOD>16 mg/kg),precision(RSD<10.1%)and accuracy(spike-recovery rate 76.9%-112.2%).Finally,the suspected result was confirmed by determining its MS fingerprint,further strengthening the reliability of screening.
基金Researchers Supporting Project Number(RSPD2024R576),King Saud University,Riyadh,Saudi Arabia。
文摘Cardiovascular disease is the leading cause of death globally.This disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may depend on receiving timely assistance as soon as possible.Thus,minimizing the death ratio can be achieved by early detection of heart attack(HA)symptoms.In the United States alone,an estimated 610,000 people die fromheart attacks each year,accounting for one in every four fatalities.However,by identifying and reporting heart attack symptoms early on,it is possible to reduce damage and save many lives significantly.Our objective is to devise an algorithm aimed at helping individuals,particularly elderly individuals living independently,to safeguard their lives.To address these challenges,we employ deep learning techniques.We have utilized a vision transformer(ViT)to address this problem.However,it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product attention.Also,since transformer performance typically relies on large-scale or adequate data,adapting ViT for smaller datasets is more challenging.In response,we propose a three-in-one steam model,theMulti-Head Attention Vision Hybrid(MHAVH).Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques,such as ResNet-50 and VGG-16,renowned for their robust feature extraction capabilities.By incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities,we leverage a 2019 posture-based dataset comprising RGB images,a novel creation by the author that marks the first dataset tailored for posture-based heart attack detection.Given the limited online data availability,we segmented this dataset into gender categories(male and female)and conducted testing on both segmented and original datasets.The training accuracy of our model reached an impressive 99.77%.Upon testing,the accuracy for male and female datasets was recorded at 92.87%and 75.47%,respectively.The combined dataset accuracy is 93.96%,showcasing a commendable performance overall.Our proposed approach demonstrates versatility in accommodating small and large datasets,offering promising prospects for real-world applications.
基金Supported by Zhejiang Provincial Natural Science Foundation of China(No.LGF22H120013)the Ningbo Natural Science Foundation(No.2023J209+3 种基金No.2021J023)Ningbo Medical Science and Technology Project(No.2021Y57)Ningbo Yinzhou District Agricultural Community Development Science and Technology Project(No.2022AS022)Ningbo Eye Hospital Scientific Technology Plan Project and Talent Introduction Start Subject(No.2022RC001).
文摘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.
基金National Natural Science Foundation of China,Grant/Award Numbers:61825305,62003361,U21A20518China Postdoctoral Science Foundation,Grant/Award Number:47680。
文摘Although previous studies have made some clear leap in learning latent dynamics from high-dimensional representations,the performances in terms of accuracy and inference time of long-term model prediction still need to be improved.In this study,a deep convolutional network based on the Koopman operator(CKNet)is proposed to model non-linear systems with pixel-level measurements for long-term prediction.CKNet adopts an autoencoder network architecture,consisting of an encoder to generate latent states and a linear dynamical model(i.e.,the Koopman operator)which evolves in the latent state space spanned by the encoder.The decoder is used to recover images from latent states.According to a multi-step ahead prediction loss function,the system matrices for approximating the Koopman operator are trained synchronously with the autoencoder in a mini-batch manner.In this manner,gradients can be synchronously transmitted to both the system matrices and the autoencoder to help the encoder self-adaptively tune the latent state space in the training process,and the resulting model is time-invariant in the latent space.Therefore,the proposed CKNet has the advantages of less inference time and high accuracy for long-term prediction.Experiments are per-formed on OpenAI Gym and Mujoco environments,including two and four non-linear forced dynamical systems with continuous action spaces.The experimental results show that CKNet has strong long-term prediction capabilities with sufficient precision.
基金This research was funded by the National Natural Science Foundation of China(Nos.71762010,62262019,62162025,61966013,12162012)the Hainan Provincial Natural Science Foundation of China(Nos.823RC488,623RC481,620RC603,621QN241,620RC602,121RC536)+1 种基金the Haikou Science and Technology Plan Project of China(No.2022-016)the Project supported by the Education Department of Hainan Province,No.Hnky2021-23.
文摘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.
文摘Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.