Medical image analysis has become a cornerstone of modern healthcare,driven by the exponential growth of data from imaging modalities such as MRI,CT,PET,ultrasound,and X-ray.Traditional machine learning methods have m...Medical image analysis has become a cornerstone of modern healthcare,driven by the exponential growth of data from imaging modalities such as MRI,CT,PET,ultrasound,and X-ray.Traditional machine learning methods have made early contributions;however,recent advancements in deep learning(DL)have revolutionized the field,offering state-of-the-art performance in image classification,segmentation,detection,fusion,registration,and enhancement.This comprehensive review presents an in-depth analysis of deep learning methodologies applied across medical image analysis tasks,highlighting both foundational models and recent innovations.The article begins by introducing conventional techniques and their limitations,setting the stage for DL-based solutions.Core DL architectures,including Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),Generative Adversarial Networks(GANs),Vision Transformers(ViTs),and hybrid models,are discussed in detail,including their advantages and domain-specific adaptations.Advanced learning paradigms such as semi-supervised learning,selfsupervised learning,and few-shot learning are explored for their potential to mitigate data annotation challenges in clinical datasets.This review further categorizes major tasks in medical image analysis,elaborating on how DL techniques have enabled precise tumor segmentation,lesion detection,modality fusion,super-resolution,and robust classification across diverse clinical settings.Emphasis is placed on applications in oncology,cardiology,neurology,and infectious diseases,including COVID-19.Challenges such as data scarcity,label imbalance,model generalizability,interpretability,and integration into clinical workflows are critically examined.Ethical considerations,explainable AI(XAI),federated learning,and regulatory compliance are discussed as essential components of real-world deployment.Benchmark datasets,evaluation metrics,and comparative performance analyses are presented to support future research.The article concludes with a forward-looking perspective on the role of foundation models,multimodal learning,edge AI,and bio-inspired computing in the future of medical imaging.Overall,this review serves as a valuable resource for researchers,clinicians,and developers aiming to harness deep learning for intelligent,efficient,and clinically viable medical image analysis.展开更多
Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a c...Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a crucial topic of research.With advances in deep learning,researchers have developed numerous methods that combine Transformers and convolutional neural networks(CNNs)to create highly accurate models for medical image segmentation.However,efforts to further enhance accuracy by developing larger and more complex models or training with more extensive datasets,significantly increase computational resource consumption.To address this problem,we propose BiCLIP-nnFormer(the prefix"Bi"refers to the use of two distinct CLIP models),a virtual multimodal instrument that leverages CLIP models to enhance the segmentation performance of a medical segmentation model nnFormer.Since two CLIP models(PMC-CLIP and CoCa-CLIP)are pre-trained on large datasets,they do not require additional training,thus conserving computation resources.These models are used offline to extract image and text embeddings from medical images.These embeddings are then processed by the proposed 3D CLIP adapter,which adapts the CLIP knowledge for segmentation tasks by fine-tuning.Finally,the adapted embeddings are fused with feature maps extracted from the nnFormer encoder for generating predicted masks.This process enriches the representation capabilities of the feature maps by integrating global multimodal information,leading to more precise segmentation predictions.We demonstrate the superiority of BiCLIP-nnFormer and the effectiveness of using CLIP models to enhance nnFormer through experiments on two public datasets,namely the Synapse multi-organ segmentation dataset(Synapse)and the Automatic Cardiac Diagnosis Challenge dataset(ACDC),as well as a self-annotated lung multi-category segmentation dataset(LMCS).展开更多
Confocal laser endomicroscopy(CLE)has become an indispensable tool in the diagnosis and detection of gastrointestinal(GI)diseases due to its high-resolution and high-contrast imaging capabilities.However,the early-sta...Confocal laser endomicroscopy(CLE)has become an indispensable tool in the diagnosis and detection of gastrointestinal(GI)diseases due to its high-resolution and high-contrast imaging capabilities.However,the early-stage imaging changes of gastrointestinal disorders are often subtle,and traditional medical image analysis methods rely heavily on manual interpretation,which is time-consuming,subject to observer variability,and inefficient for accurate lesion identification across large-scale image datasets.With the introduction of artificial intelligence(AI)technologies,AI-driven CLE image analysis systems can automatically extract pathological features and have demonstrated significant clinical value in lesion recognition,classification diagnosis,and malignancy prediction of GI diseases.These systems greatly enhance diagnostic efficiency and early detection capabilities.This review summarizes the applications of AI-assisted CLE in GI diseases,analyzes the limitations of current technologies,and explores future research directions.It is expected that the deep integration of AI and confocal imaging technologies will provide strong support for precision diagnosis and personalized treatment in the field of gastrointestinal disorders.展开更多
Medical image segmentation is a crucial preliminary step for a number of downstream diagnosis tasks.As deep convolutional neural networks successfully promote the development of computer vision,it is possible to make ...Medical image segmentation is a crucial preliminary step for a number of downstream diagnosis tasks.As deep convolutional neural networks successfully promote the development of computer vision,it is possible to make medical image segmentation a semi-automatic procedure by applying deep convolutional neural networks to finding the contours of regions of interest that are then revised by radiologists.However,supervised learning necessitates large annotated data,which are difficult to acquire especially for medical images.Self-supervised learning is able to take advantage of unlabeled data and provide good initialization to be finetuned for downstream tasks with limited annotations.Considering that most self-supervised learning especially contrastive learning methods are tailored to natural image classification and entail expensive GPU resources,we propose a novel and simple pretext-based self-supervised learning method that exploits the value of positional information in volumetric medical images.Specifically,we regard spatial coordinates as pseudo labels and pretrain the model by predicting positions of randomly sampled 2D slices in volumetric medical images.Experiments on four semantic segmentation datasets demonstrate the superiority of our method over other self-supervised learning methods in both semi-supervised learning and transfer learning settings.Codes are available at https://github.com/alienzyj/PPos.展开更多
Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networ...Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.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
Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importan...Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.展开更多
Imaging evaluation of lymph node metastasis and infiltration faces problems such as low artificial outline efficiency and insufficient consistency.Deep learning technology based on convolutional neural networks has gr...Imaging evaluation of lymph node metastasis and infiltration faces problems such as low artificial outline efficiency and insufficient consistency.Deep learning technology based on convolutional neural networks has greatly improved the technical effect of radiomics in lymph node pathological characteristics analysis and efficacy monitoring through automatic lymph node detection,precise segmentation and three-dimensional reconstruction algorithms.This review focuses on the automatic lymph node segmentation model,treatment response prediction algorithm and benign and malignant differential diagnosis system for multimodal imaging,in order to provide a basis for further research on artificial intelligence to assist lymph node disease management and clinical decision-making,and provide a reference for promoting the construction of a system for accurate diagnosis,personalized treatment and prognostic evaluation of lymph node-related diseases.展开更多
Background:Early and accurate diagnosis of cataracts,which ranks among the leading preventable causes of blindness,is critical to securing positive outcomes for patients.Recently,eye image analyses have used deep lear...Background:Early and accurate diagnosis of cataracts,which ranks among the leading preventable causes of blindness,is critical to securing positive outcomes for patients.Recently,eye image analyses have used deep learning(DL)approaches to automate cataract classification more precisely,leading to the development of the Multiscale Parallel Feature Aggregation Network with Attention Fusion(MPFAN-AF).Focused on improving a model’s performance,this approach applies multiscale feature extraction,parallel feature fusion,along with attention-based fusion to sharpen its focus on salient features,which are crucial in detecting cataracts.Methods:Coarse-level features are captured through the application of convolutional layers,and these features undergo refinement through layered kernels of varying sizes.Moreover,this method captures all the diverse representations of cataracts accurately by parallel feature aggregation.Utilizing the Cataract Eye Dataset available on Kaggle,containing 612 labelled images of eyes with and without cataracts proportionately(normal vs.pathological),this model was trained and tested.Results:Results using the proposed model reflect greater precision over traditional convolutional neural networks(CNNs)models,achieving a classification accuracy of 97.52%.Additionally,the model demonstrated exceptional performance in classification tasks.The ablation studies validated that all applications added value to the prediction process,particularly emphasizing the attention fusion module.Conclusion:The MPFAN-AF model demonstrates high efficiency together with interpretability because it shows promise as an integration solution for real-time mobile cataract detection screening systems.Standard performance indicators indicate that AI-based ophthalmology tools have a promising future for use in remote conditions that lack medical resources.展开更多
Artificial intelligence(AI),particularly deep learning algorithms utilizing convolutional neural networks,plays an increasingly pivotal role in enhancing medical image examination.It demonstrates the potential for imp...Artificial intelligence(AI),particularly deep learning algorithms utilizing convolutional neural networks,plays an increasingly pivotal role in enhancing medical image examination.It demonstrates the potential for improving diagnostic accuracy within dental care.Orthopantomograms(OPGs)are essential in dentistry;however,their manual interpretation is often inconsistent and tedious.To the best of our knowledge,this is the first comprehensive application of YOLOv5m for the simultaneous detection and classification of six distinct dental pathologies using panoramic OPG images.The model was trained and refined on a custom dataset that began with 232 panoramic radiographs and was later expanded to 604 samples.These included annotated subclasses representing Caries,Infection,Impacted Teeth,Fractured Teeth,Broken Crowns,and Healthy conditions.The training was performed using GPU resources alongside tuned hyperparameters of batch size,learning rate schedule,and early stopping tailored for generalization to prevent overfitting.Evaluation on a held-out test set showed strong performance in the detection and localization of various dental pathologies and robust overall accuracy.At an IoU of 0.5,the system obtained a mean precision of 94.22%and recall of 90.42%,with mAP being 93.71%.This research confirms the use of YOLOv5m as a robust,highly efficient AI technology for the analysis of dental pathologies using OPGs,providing a clinically useful solution to enhance workflow efficiency and aid in sustaining consistency in complex multi-dimensional case evaluations.展开更多
The application of artificial intelligence(AI)in carotid atherosclerotic plaque detection via computed tomography angiography(CTA)has significantly ad-vanced over the past decade.This mini-review consolidates recent i...The application of artificial intelligence(AI)in carotid atherosclerotic plaque detection via computed tomography angiography(CTA)has significantly ad-vanced over the past decade.This mini-review consolidates recent innovations in deep learning architectures,domain adaptation techniques,and automated pl-aque characterization methodologies.Hybrid models,such as residual U-Net-Pyramid Scene Parsing Network,exhibit a remarkable precision of 80.49%in plaque segmentation,outperforming radiologists in diagnostic efficiency by reducing analysis time from minutes to mere seconds.Domain-adaptive fra-meworks,such as Lesion Assessment through Tracklet Evaluation,demonstrate robust performance across heterogeneous imaging datasets,achieving an area under the curve(AUC)greater than 0.88.Furthermore,novel approaches inte-grating U-Net and Efficient-Net architectures,enhanced by Bayesian optimi-zation,have achieved impressive correlation coefficients(0.89)for plaque quanti-fication.AI-powered CTA also enables high-precision three-dimensional vascular segmentation,with a Dice coefficient of 0.9119,and offers superior cardiovascular risk stratification compared to traditional Agatston scoring,yielding AUC values of 0.816 vs 0.729 at a 15-year follow-up.These breakthroughs address key challenges in plaque motion analysis,with systolic retractive motion biomarkers successfully identifying 80%of vulnerable plaques.Looking ahead,future directions focus on enhancing the interpretability of AI models through explainable AI and leveraging federated learning to mitigate data heterogeneity.This mini-review underscores the transformative potential of AI in carotid plaque assessment,offering substantial implic-ations for stroke prevention and personalized cerebrovascular management strategies.展开更多
Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a co...Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical settings.These methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality combinations.Additionally,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training data.This work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing modalities.The proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”data.Co-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing modalities.The model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation task.EACNet was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance respectively.Notably,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing methods.The analysis suggests that the ensemble approach offers potential benefits,and the adversarial co-training contributes to the increased robustness and accuracy of EACNet for brain tumor segmentation of MRI scans with missing modalities.The experimental results show that EACNet has promising results for the task of brain tumor segmentation of MRI scans with missing modalities and is a better candidate for real-world clinical applications.展开更多
Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors pr...Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors present significant challenges for precise anomaly detection.While U-Net-based architectures have demonstrated strong performance in medical image segmentation,there remains room for improvement in feature extraction and localization accuracy.In this study,we propose a novel hybrid model designed to enhance 3D brain tumor segmentation.The architecture incorporates a 3D ResNet encoder known for mitigating the vanishing gradient problem and a 3D U-Net decoder.Additionally,to enhance the model’s generalization ability,Squeeze and Excitation attention mechanism is integrated.We introduce Gabor filter banks into the encoder to further strengthen the model’s ability to extract robust and transformation-invariant features from the complex and irregular shapes typical in medical imaging.This approach,which is not well explored in current U-Net-based segmentation frameworks,provides a unique advantage by enhancing texture-aware feature representation.Specifically,Gabor filters help extract distinctive low-level texture features,reducing the effects of texture interference and facilitating faster convergence during the early stages of training.Our model achieved Dice scores of 0.881,0.846,and 0.819 for Whole Tumor(WT),Tumor Core(TC),and Enhancing Tumor(ET),respectively,on the BraTS 2020 dataset.Cross-validation on the BraTS 2021 dataset further confirmed the model’s robustness,yielding Dice score values of 0.887 for WT,0.856 for TC,and 0.824 for ET.The proposed model outperforms several state-of-the-art existing models,particularly in accurately identifying small and complex tumor regions.Extensive evaluations suggest integrating advanced preprocessing with an attention-augmented hybrid architecture offers significant potential for reliable and clinically valuable brain tumor segmentation.展开更多
Eye state classification acts as a vital part of the biomedical sector,for instance,smart home device control,drowsy driving recognition,and so on.The modifications in the cognitive levels can be reflected via transformi...Eye state classification acts as a vital part of the biomedical sector,for instance,smart home device control,drowsy driving recognition,and so on.The modifications in the cognitive levels can be reflected via transforming the electro-encephalogram(EEG)signals.The deep learning(DL)models automated extract the features and often showcased improved outcomes over the conventional clas-sification model in the recognition processes.This paper presents an Ensemble Deep Learning with Chimp Optimization Algorithm for EEG Eye State Classifi-cation(EDLCOA-ESC).The proposed EDLCOA-ESC technique involves min-max normalization approach as a pre-processing step.Besides,wavelet packet decomposition(WPD)technique is employed for the extraction of useful features from the EEG signals.In addition,an ensemble of deep sparse autoencoder(DSAE)and kernel ridge regression(KRR)models are employed for EEG Eye State classification.Finally,hyperparameters tuning of the DSAE model takes place using COA and thereby boost the classification results to a maximum extent.An extensive range of simulation analysis on the benchmark dataset is car-ried out and the results reported the promising performance of the EDLCOA-ESC technique over the recent approaches with maximum accuracy of 98.50%.展开更多
Rational nutritional support shall be based on nutritional screening and nutritional assessment. This study is aimed to explore nutritional risk screening and its influencing factors of hospitalized patients in centra...Rational nutritional support shall be based on nutritional screening and nutritional assessment. This study is aimed to explore nutritional risk screening and its influencing factors of hospitalized patients in central urban area. It is helpful for the early detection of problems in nutritional supports, nutrition management and the implementation of intervention measures, which will contribute a lot to improving the patient＇s poor clinical outcome. A total of three tertiary medical institutions were enrolled in this study. From October 2015 to June 2016, 1202 hospitalized patients aged ≥18 years were enrolled in Nutrition Risk Screening 2002（NRS2002） for nutritional risk screening, including 8 cases who refused to participate, 5 cases of same-day surgery and 5 cases of coma. A single-factor chi-square test was performed on 312 patients with nutritional risk and 872 hospitalized patients without nutritional risk. Logistic regression analysis was performed with univariate analysis（P〈0.05）, to investigate the incidence of nutritional risk and influencing factors. The incidence of nutritional risk was 26.35% in the inpatients, 25.90% in male and 26.84% in female, respectively. The single-factor analysis showed that the age ≥60, sleeping disorder, fasting, intraoperative bleeding, the surgery in recent month, digestive diseases, metabolic diseases and endocrine system diseases had significant effects on nutritional risk（P〈0.05）. Having considered the above-mentioned factors as independent variables and nutritional risk（Y=1, N=0） as dependent variable, logistic regression analysis revealed that the age ≥60, fasting, sleeping disorders, the surgery in recent month and digestive diseases are hazardous factors for nutritional risk. Nutritional risk exists in hospitalized patients in central urban areas. Nutritional risk screening should be conducted for inpatients. Nutritional intervention programs should be formulated in consideration of those influencing factors, which enable to reduce the nutritional risk and to promote the rehabilitation of inpatients.展开更多
Computer-aided diagnosis based on image color rendering promotes medical image analysis and doctor-patient communication by highlighting important information of medical diagnosis.To overcome the limitations of the co...Computer-aided diagnosis based on image color rendering promotes medical image analysis and doctor-patient communication by highlighting important information of medical diagnosis.To overcome the limitations of the color rendering method based on deep learning,such as poor model stability,poor rendering quality,fuzzy boundaries and crossed color boundaries,we propose a novel hinge-cross-entropy generative adversarial network(HCEGAN).The self-attention mechanism was added and improved to focus on the important information of the image.And the hinge-cross-entropy loss function was used to stabilize the training process of GAN models.In this study,we implement the HCEGAN model for image color rendering based on DIV2K and COCO datasets,and evaluate the results using SSIM and PSNR.The experimental results show that the proposed HCEGAN automatically re-renders images,significantly improves the quality of color rendering and greatly improves the stability of prior GAN models.展开更多
Electrocardiogram(ECG)is a low-cost,simple,fast,and non-invasive test.It can reflect the heart’s electrical activity and provide valuable diagnostic clues about the health of the entire body.Therefore,ECG has been wi...Electrocardiogram(ECG)is a low-cost,simple,fast,and non-invasive test.It can reflect the heart’s electrical activity and provide valuable diagnostic clues about the health of the entire body.Therefore,ECG has been widely used in various biomedical applications such as arrhythmia detection,disease-specific detection,mortality prediction,and biometric recognition.In recent years,ECG-related studies have been carried out using a variety of publicly available datasets,with many differences in the datasets used,data preprocessing methods,targeted challenges,and modeling and analysis techniques.Here we systematically summarize and analyze the ECGbased automatic analysis methods and applications.Specifically,we first reviewed 22 commonly used ECG public datasets and provided an overview of data preprocessing processes.Then we described some of the most widely used applications of ECG signals and analyzed the advanced methods involved in these applications.Finally,we elucidated some of the challenges in ECG analysis and provided suggestions for further research.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
Artificial intelligence(AI)is an interdisciplinary field that combines computer technology,mathematics,and several other fields.Recently,with the rapid development of machine learning(ML)and deep learning(DL),signific...Artificial intelligence(AI)is an interdisciplinary field that combines computer technology,mathematics,and several other fields.Recently,with the rapid development of machine learning(ML)and deep learning(DL),significant progress has been made in the field of AI.As one of the fastest-growing branches,DL can effectively extract features from big data and optimize the performance of various tasks.Moreover,with advancements in digital imaging technology,DL has become a key tool for processing high-dimensional medical image data and conducting medical image analysis in clinical applications.With the development of this technology,the diagnosis of orthopedic diseases has undergone significant changes.In this review,we describe recent research progress on DL in fracture diagnosis and discuss the value of DL in this field,providing a reference for better integration and development of DL technology in orthopedics.展开更多
文摘Medical image analysis has become a cornerstone of modern healthcare,driven by the exponential growth of data from imaging modalities such as MRI,CT,PET,ultrasound,and X-ray.Traditional machine learning methods have made early contributions;however,recent advancements in deep learning(DL)have revolutionized the field,offering state-of-the-art performance in image classification,segmentation,detection,fusion,registration,and enhancement.This comprehensive review presents an in-depth analysis of deep learning methodologies applied across medical image analysis tasks,highlighting both foundational models and recent innovations.The article begins by introducing conventional techniques and their limitations,setting the stage for DL-based solutions.Core DL architectures,including Convolutional Neural Networks(CNNs),Recurrent Neural Networks(RNNs),Generative Adversarial Networks(GANs),Vision Transformers(ViTs),and hybrid models,are discussed in detail,including their advantages and domain-specific adaptations.Advanced learning paradigms such as semi-supervised learning,selfsupervised learning,and few-shot learning are explored for their potential to mitigate data annotation challenges in clinical datasets.This review further categorizes major tasks in medical image analysis,elaborating on how DL techniques have enabled precise tumor segmentation,lesion detection,modality fusion,super-resolution,and robust classification across diverse clinical settings.Emphasis is placed on applications in oncology,cardiology,neurology,and infectious diseases,including COVID-19.Challenges such as data scarcity,label imbalance,model generalizability,interpretability,and integration into clinical workflows are critically examined.Ethical considerations,explainable AI(XAI),federated learning,and regulatory compliance are discussed as essential components of real-world deployment.Benchmark datasets,evaluation metrics,and comparative performance analyses are presented to support future research.The article concludes with a forward-looking perspective on the role of foundation models,multimodal learning,edge AI,and bio-inspired computing in the future of medical imaging.Overall,this review serves as a valuable resource for researchers,clinicians,and developers aiming to harness deep learning for intelligent,efficient,and clinically viable medical image analysis.
基金funded by the National Natural Science Foundation of China(Grant No.6240072655)the Hubei Provincial Key Research and Development Program(Grant No.2023BCB151)+1 种基金the Wuhan Natural Science Foundation Exploration Program(Chenguang Program,Grant No.2024040801020202)the Natural Science Foundation of Hubei Province of China(Grant No.2025AFB148).
文摘Image segmentation is attracting increasing attention in the field of medical image analysis.Since widespread utilization across various medical applications,ensuring and improving segmentation accuracy has become a crucial topic of research.With advances in deep learning,researchers have developed numerous methods that combine Transformers and convolutional neural networks(CNNs)to create highly accurate models for medical image segmentation.However,efforts to further enhance accuracy by developing larger and more complex models or training with more extensive datasets,significantly increase computational resource consumption.To address this problem,we propose BiCLIP-nnFormer(the prefix"Bi"refers to the use of two distinct CLIP models),a virtual multimodal instrument that leverages CLIP models to enhance the segmentation performance of a medical segmentation model nnFormer.Since two CLIP models(PMC-CLIP and CoCa-CLIP)are pre-trained on large datasets,they do not require additional training,thus conserving computation resources.These models are used offline to extract image and text embeddings from medical images.These embeddings are then processed by the proposed 3D CLIP adapter,which adapts the CLIP knowledge for segmentation tasks by fine-tuning.Finally,the adapted embeddings are fused with feature maps extracted from the nnFormer encoder for generating predicted masks.This process enriches the representation capabilities of the feature maps by integrating global multimodal information,leading to more precise segmentation predictions.We demonstrate the superiority of BiCLIP-nnFormer and the effectiveness of using CLIP models to enhance nnFormer through experiments on two public datasets,namely the Synapse multi-organ segmentation dataset(Synapse)and the Automatic Cardiac Diagnosis Challenge dataset(ACDC),as well as a self-annotated lung multi-category segmentation dataset(LMCS).
基金Supported by Interdisciplinary Program of Shanghai Jiao Tong University,No.YG2024 LC01National Natural Science Foundation of China,No.62406190.
文摘Confocal laser endomicroscopy(CLE)has become an indispensable tool in the diagnosis and detection of gastrointestinal(GI)diseases due to its high-resolution and high-contrast imaging capabilities.However,the early-stage imaging changes of gastrointestinal disorders are often subtle,and traditional medical image analysis methods rely heavily on manual interpretation,which is time-consuming,subject to observer variability,and inefficient for accurate lesion identification across large-scale image datasets.With the introduction of artificial intelligence(AI)technologies,AI-driven CLE image analysis systems can automatically extract pathological features and have demonstrated significant clinical value in lesion recognition,classification diagnosis,and malignancy prediction of GI diseases.These systems greatly enhance diagnostic efficiency and early detection capabilities.This review summarizes the applications of AI-assisted CLE in GI diseases,analyzes the limitations of current technologies,and explores future research directions.It is expected that the deep integration of AI and confocal imaging technologies will provide strong support for precision diagnosis and personalized treatment in the field of gastrointestinal disorders.
基金the Major Research Plan of the National Natural Science Foundation of China(No.92059206)。
文摘Medical image segmentation is a crucial preliminary step for a number of downstream diagnosis tasks.As deep convolutional neural networks successfully promote the development of computer vision,it is possible to make medical image segmentation a semi-automatic procedure by applying deep convolutional neural networks to finding the contours of regions of interest that are then revised by radiologists.However,supervised learning necessitates large annotated data,which are difficult to acquire especially for medical images.Self-supervised learning is able to take advantage of unlabeled data and provide good initialization to be finetuned for downstream tasks with limited annotations.Considering that most self-supervised learning especially contrastive learning methods are tailored to natural image classification and entail expensive GPU resources,we propose a novel and simple pretext-based self-supervised learning method that exploits the value of positional information in volumetric medical images.Specifically,we regard spatial coordinates as pseudo labels and pretrain the model by predicting positions of randomly sampled 2D slices in volumetric medical images.Experiments on four semantic segmentation datasets demonstrate the superiority of our method over other self-supervised learning methods in both semi-supervised learning and transfer learning settings.Codes are available at https://github.com/alienzyj/PPos.
基金the Deanship of Graduate Studies and Scientific Research at Najran University,Saudi Arabia,for their financial support through the Easy Track Research program,grant code(NU/EFP/MRC/13).
文摘Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.
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.
文摘Deep learning (DL) has seen an exponential development in recent years, with major impact in many medical fields, especially in the field of medical image. The purpose of the work converges in determining the importance of each component, describing the specificity and correlations of these elements involved in achieving the precision of interpretation of medical images using DL. The major contribution of this work is primarily to the updated characterisation of the characteristics of the constituent elements of the deep learning process, scientific data, methods of knowledge incorporation, DL models according to the objectives for which they were designed and the presentation of medical applications in accordance with these tasks. Secondly, it describes the specific correlations between the quality, type and volume of data, the deep learning patterns used in the interpretation of diagnostic medical images and their applications in medicine. Finally presents problems and directions of future research. Data quality and volume, annotations and labels, identification and automatic extraction of specific medical terms can help deep learning models perform image analysis tasks. Moreover, the development of models capable of extracting unattended features and easily incorporated into the architecture of DL networks and the development of techniques to search for a certain network architecture according to the objectives set lead to performance in the interpretation of medical images.
基金Supported by Clinical Trials from the Nanjing Drum Tower Hospital,Affiliated Hospital of Medical School,Nanjing University,No.2021-LCYJ-MS-11Nanjing Drum Tower Hospital National Natural Science Foundation Youth Cultivation Project,No.2024-JCYJQP-15.
文摘Imaging evaluation of lymph node metastasis and infiltration faces problems such as low artificial outline efficiency and insufficient consistency.Deep learning technology based on convolutional neural networks has greatly improved the technical effect of radiomics in lymph node pathological characteristics analysis and efficacy monitoring through automatic lymph node detection,precise segmentation and three-dimensional reconstruction algorithms.This review focuses on the automatic lymph node segmentation model,treatment response prediction algorithm and benign and malignant differential diagnosis system for multimodal imaging,in order to provide a basis for further research on artificial intelligence to assist lymph node disease management and clinical decision-making,and provide a reference for promoting the construction of a system for accurate diagnosis,personalized treatment and prognostic evaluation of lymph node-related diseases.
文摘Background:Early and accurate diagnosis of cataracts,which ranks among the leading preventable causes of blindness,is critical to securing positive outcomes for patients.Recently,eye image analyses have used deep learning(DL)approaches to automate cataract classification more precisely,leading to the development of the Multiscale Parallel Feature Aggregation Network with Attention Fusion(MPFAN-AF).Focused on improving a model’s performance,this approach applies multiscale feature extraction,parallel feature fusion,along with attention-based fusion to sharpen its focus on salient features,which are crucial in detecting cataracts.Methods:Coarse-level features are captured through the application of convolutional layers,and these features undergo refinement through layered kernels of varying sizes.Moreover,this method captures all the diverse representations of cataracts accurately by parallel feature aggregation.Utilizing the Cataract Eye Dataset available on Kaggle,containing 612 labelled images of eyes with and without cataracts proportionately(normal vs.pathological),this model was trained and tested.Results:Results using the proposed model reflect greater precision over traditional convolutional neural networks(CNNs)models,achieving a classification accuracy of 97.52%.Additionally,the model demonstrated exceptional performance in classification tasks.The ablation studies validated that all applications added value to the prediction process,particularly emphasizing the attention fusion module.Conclusion:The MPFAN-AF model demonstrates high efficiency together with interpretability because it shows promise as an integration solution for real-time mobile cataract detection screening systems.Standard performance indicators indicate that AI-based ophthalmology tools have a promising future for use in remote conditions that lack medical resources.
基金funding from the Princess Nourah bint Abdulrahman University Researchers Supporting Project(PNURSP2025R195)the University of Bisha through its Fast-Track Research Support Program.
文摘Artificial intelligence(AI),particularly deep learning algorithms utilizing convolutional neural networks,plays an increasingly pivotal role in enhancing medical image examination.It demonstrates the potential for improving diagnostic accuracy within dental care.Orthopantomograms(OPGs)are essential in dentistry;however,their manual interpretation is often inconsistent and tedious.To the best of our knowledge,this is the first comprehensive application of YOLOv5m for the simultaneous detection and classification of six distinct dental pathologies using panoramic OPG images.The model was trained and refined on a custom dataset that began with 232 panoramic radiographs and was later expanded to 604 samples.These included annotated subclasses representing Caries,Infection,Impacted Teeth,Fractured Teeth,Broken Crowns,and Healthy conditions.The training was performed using GPU resources alongside tuned hyperparameters of batch size,learning rate schedule,and early stopping tailored for generalization to prevent overfitting.Evaluation on a held-out test set showed strong performance in the detection and localization of various dental pathologies and robust overall accuracy.At an IoU of 0.5,the system obtained a mean precision of 94.22%and recall of 90.42%,with mAP being 93.71%.This research confirms the use of YOLOv5m as a robust,highly efficient AI technology for the analysis of dental pathologies using OPGs,providing a clinically useful solution to enhance workflow efficiency and aid in sustaining consistency in complex multi-dimensional case evaluations.
基金Supported by Henan Province International Science and Technology Cooperation Project,2024,No.242102520054.
文摘The application of artificial intelligence(AI)in carotid atherosclerotic plaque detection via computed tomography angiography(CTA)has significantly ad-vanced over the past decade.This mini-review consolidates recent innovations in deep learning architectures,domain adaptation techniques,and automated pl-aque characterization methodologies.Hybrid models,such as residual U-Net-Pyramid Scene Parsing Network,exhibit a remarkable precision of 80.49%in plaque segmentation,outperforming radiologists in diagnostic efficiency by reducing analysis time from minutes to mere seconds.Domain-adaptive fra-meworks,such as Lesion Assessment through Tracklet Evaluation,demonstrate robust performance across heterogeneous imaging datasets,achieving an area under the curve(AUC)greater than 0.88.Furthermore,novel approaches inte-grating U-Net and Efficient-Net architectures,enhanced by Bayesian optimi-zation,have achieved impressive correlation coefficients(0.89)for plaque quanti-fication.AI-powered CTA also enables high-precision three-dimensional vascular segmentation,with a Dice coefficient of 0.9119,and offers superior cardiovascular risk stratification compared to traditional Agatston scoring,yielding AUC values of 0.816 vs 0.729 at a 15-year follow-up.These breakthroughs address key challenges in plaque motion analysis,with systolic retractive motion biomarkers successfully identifying 80%of vulnerable plaques.Looking ahead,future directions focus on enhancing the interpretability of AI models through explainable AI and leveraging federated learning to mitigate data heterogeneity.This mini-review underscores the transformative potential of AI in carotid plaque assessment,offering substantial implic-ations for stroke prevention and personalized cerebrovascular management strategies.
基金supported by Gansu Natural Science Foundation Programme(No.24JRRA231)National Natural Science Foundation of China(No.62061023)Gansu Provincial Education,Science and Technology Innovation and Industry(No.2021CYZC-04)。
文摘Brain tumor segmentation is critical in clinical diagnosis and treatment planning.Existing methods for brain tumor segmentation with missing modalities often struggle when dealing with multiple missing modalities,a common scenario in real-world clinical settings.These methods primarily focus on handling a single missing modality at a time,making them insufficiently robust for the additional complexity encountered with incomplete data containing various missing modality combinations.Additionally,most existing methods rely on single models,which may limit their performance and increase the risk of overfitting the training data.This work proposes a novel method called the ensemble adversarial co-training neural network(EACNet)for accurate brain tumor segmentation from multi-modal magnetic resonance imaging(MRI)scans with multiple missing modalities.The proposed method consists of three key modules:the ensemble of pre-trained models,which captures diverse feature representations from the MRI data by employing an ensemble of pre-trained models;adversarial learning,which leverages a competitive training approach involving two models;a generator model,which creates realistic missing data,while sub-networks acting as discriminators learn to distinguish real data from the generated“fake”data.Co-training framework utilizes the information extracted by the multimodal path(trained on complete scans)to guide the learning process in the path handling missing modalities.The model potentially compensates for missing information through co-training interactions by exploiting the relationships between available modalities and the tumor segmentation task.EACNet was evaluated on the BraTS2018 and BraTS2020 challenge datasets and achieved state-of-the-art and competitive performance respectively.Notably,the segmentation results for the whole tumor(WT)dice similarity coefficient(DSC)reached 89.27%,surpassing the performance of existing methods.The analysis suggests that the ensemble approach offers potential benefits,and the adversarial co-training contributes to the increased robustness and accuracy of EACNet for brain tumor segmentation of MRI scans with missing modalities.The experimental results show that EACNet has promising results for the task of brain tumor segmentation of MRI scans with missing modalities and is a better candidate for real-world clinical applications.
基金the National Science and Technology Council(NSTC)of the Republic of China,Taiwan,for financially supporting this research under Contract No.NSTC 112-2637-M-131-001.
文摘Accurate and efficient brain tumor segmentation is essential for early diagnosis,treatment planning,and clinical decision-making.However,the complex structure of brain anatomy and the heterogeneous nature of tumors present significant challenges for precise anomaly detection.While U-Net-based architectures have demonstrated strong performance in medical image segmentation,there remains room for improvement in feature extraction and localization accuracy.In this study,we propose a novel hybrid model designed to enhance 3D brain tumor segmentation.The architecture incorporates a 3D ResNet encoder known for mitigating the vanishing gradient problem and a 3D U-Net decoder.Additionally,to enhance the model’s generalization ability,Squeeze and Excitation attention mechanism is integrated.We introduce Gabor filter banks into the encoder to further strengthen the model’s ability to extract robust and transformation-invariant features from the complex and irregular shapes typical in medical imaging.This approach,which is not well explored in current U-Net-based segmentation frameworks,provides a unique advantage by enhancing texture-aware feature representation.Specifically,Gabor filters help extract distinctive low-level texture features,reducing the effects of texture interference and facilitating faster convergence during the early stages of training.Our model achieved Dice scores of 0.881,0.846,and 0.819 for Whole Tumor(WT),Tumor Core(TC),and Enhancing Tumor(ET),respectively,on the BraTS 2020 dataset.Cross-validation on the BraTS 2021 dataset further confirmed the model’s robustness,yielding Dice score values of 0.887 for WT,0.856 for TC,and 0.824 for ET.The proposed model outperforms several state-of-the-art existing models,particularly in accurately identifying small and complex tumor regions.Extensive evaluations suggest integrating advanced preprocessing with an attention-augmented hybrid architecture offers significant potential for reliable and clinically valuable brain tumor segmentation.
基金supported by the Researchers Supporting Program(TUMA-Project-2021–27)Almaarefa University,Riyadh,Saudi ArabiaTaif University Researchers Supporting Project Number(TURSP-2020/161),Taif University,Taif,Saudi Arabia.
文摘Eye state classification acts as a vital part of the biomedical sector,for instance,smart home device control,drowsy driving recognition,and so on.The modifications in the cognitive levels can be reflected via transforming the electro-encephalogram(EEG)signals.The deep learning(DL)models automated extract the features and often showcased improved outcomes over the conventional clas-sification model in the recognition processes.This paper presents an Ensemble Deep Learning with Chimp Optimization Algorithm for EEG Eye State Classifi-cation(EDLCOA-ESC).The proposed EDLCOA-ESC technique involves min-max normalization approach as a pre-processing step.Besides,wavelet packet decomposition(WPD)technique is employed for the extraction of useful features from the EEG signals.In addition,an ensemble of deep sparse autoencoder(DSAE)and kernel ridge regression(KRR)models are employed for EEG Eye State classification.Finally,hyperparameters tuning of the DSAE model takes place using COA and thereby boost the classification results to a maximum extent.An extensive range of simulation analysis on the benchmark dataset is car-ried out and the results reported the promising performance of the EDLCOA-ESC technique over the recent approaches with maximum accuracy of 98.50%.
基金supported by Soft Science Application Program of Wuhan Scientific and Technological Bureau of China(No.2016040306010211)
文摘Rational nutritional support shall be based on nutritional screening and nutritional assessment. This study is aimed to explore nutritional risk screening and its influencing factors of hospitalized patients in central urban area. It is helpful for the early detection of problems in nutritional supports, nutrition management and the implementation of intervention measures, which will contribute a lot to improving the patient＇s poor clinical outcome. A total of three tertiary medical institutions were enrolled in this study. From October 2015 to June 2016, 1202 hospitalized patients aged ≥18 years were enrolled in Nutrition Risk Screening 2002（NRS2002） for nutritional risk screening, including 8 cases who refused to participate, 5 cases of same-day surgery and 5 cases of coma. A single-factor chi-square test was performed on 312 patients with nutritional risk and 872 hospitalized patients without nutritional risk. Logistic regression analysis was performed with univariate analysis（P〈0.05）, to investigate the incidence of nutritional risk and influencing factors. The incidence of nutritional risk was 26.35% in the inpatients, 25.90% in male and 26.84% in female, respectively. The single-factor analysis showed that the age ≥60, sleeping disorder, fasting, intraoperative bleeding, the surgery in recent month, digestive diseases, metabolic diseases and endocrine system diseases had significant effects on nutritional risk（P〈0.05）. Having considered the above-mentioned factors as independent variables and nutritional risk（Y=1, N=0） as dependent variable, logistic regression analysis revealed that the age ≥60, fasting, sleeping disorders, the surgery in recent month and digestive diseases are hazardous factors for nutritional risk. Nutritional risk exists in hospitalized patients in central urban areas. Nutritional risk screening should be conducted for inpatients. Nutritional intervention programs should be formulated in consideration of those influencing factors, which enable to reduce the nutritional risk and to promote the rehabilitation of inpatients.
基金Foundation of China(No.61902311)funding for this studysupported in part by the Natural Science Foundation of Shaanxi Province in China under Grants 2022JM-508,2022JM-317 and 2019JM-162.
文摘Computer-aided diagnosis based on image color rendering promotes medical image analysis and doctor-patient communication by highlighting important information of medical diagnosis.To overcome the limitations of the color rendering method based on deep learning,such as poor model stability,poor rendering quality,fuzzy boundaries and crossed color boundaries,we propose a novel hinge-cross-entropy generative adversarial network(HCEGAN).The self-attention mechanism was added and improved to focus on the important information of the image.And the hinge-cross-entropy loss function was used to stabilize the training process of GAN models.In this study,we implement the HCEGAN model for image color rendering based on DIV2K and COCO datasets,and evaluate the results using SSIM and PSNR.The experimental results show that the proposed HCEGAN automatically re-renders images,significantly improves the quality of color rendering and greatly improves the stability of prior GAN models.
基金Supported by the NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization(U1909208)the Science and Technology Major Project of Changsha(kh2202004)the Changsha Municipal Natural Science Foundation(kq2202106).
文摘Electrocardiogram(ECG)is a low-cost,simple,fast,and non-invasive test.It can reflect the heart’s electrical activity and provide valuable diagnostic clues about the health of the entire body.Therefore,ECG has been widely used in various biomedical applications such as arrhythmia detection,disease-specific detection,mortality prediction,and biometric recognition.In recent years,ECG-related studies have been carried out using a variety of publicly available datasets,with many differences in the datasets used,data preprocessing methods,targeted challenges,and modeling and analysis techniques.Here we systematically summarize and analyze the ECGbased automatic analysis methods and applications.Specifically,we first reviewed 22 commonly used ECG public datasets and provided an overview of data preprocessing processes.Then we described some of the most widely used applications of ECG signals and analyzed the advanced methods involved in these applications.Finally,we elucidated some of the challenges in ECG analysis and provided suggestions for further research.
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.
基金supported by the National Natural Science Foundation of China(No.81974355,No.82172524).
文摘Artificial intelligence(AI)is an interdisciplinary field that combines computer technology,mathematics,and several other fields.Recently,with the rapid development of machine learning(ML)and deep learning(DL),significant progress has been made in the field of AI.As one of the fastest-growing branches,DL can effectively extract features from big data and optimize the performance of various tasks.Moreover,with advancements in digital imaging technology,DL has become a key tool for processing high-dimensional medical image data and conducting medical image analysis in clinical applications.With the development of this technology,the diagnosis of orthopedic diseases has undergone significant changes.In this review,we describe recent research progress on DL in fracture diagnosis and discuss the value of DL in this field,providing a reference for better integration and development of DL technology in orthopedics.
