ABSTRACT
Severe ground-level ozone (O3) pollution over major Chinese cities has become one of the most challenging problems, which have deleterious effects on human health and the sustainability of society. This study explored the spatiotemporal distribution characteristics of ground-level O3 and its precursors based on conventional pollutant and meteorological monitoring data in Zhejiang Province from 2016 to 2021. Then, a high-performance convolutional neural network (CNN) model was established by expanding the moment and the concentration variations to general factors. Finally, the response mechanism of O3 to the variation with crucial influencing factors is explored by controlling variables and interpolating target variables. The results indicated that the annual average MDA8-90th concentrations in Zhejiang Province are higher in the northern and lower in the southern. When the wind direction (WD) ranges from east to southwest and the wind speed (WS) ranges between 2 and 3 m/sec, higher O3 concentration prone to occur. At different temperatures (T), the O3 concentration showed a trend of first increasing and subsequently decreasing with increasing NO2 concentration, peaks at the NO2 concentration around 0.02 mg/m3. The sensitivity of NO2 to O3 formation is not easily affected by temperature, barometric pressure and dew point temperature. Additionally, there is a minimum [Formula: see text] at each temperature when the NO2 concentration is 0.03 mg/m3, and this minimum [Formula: see text] decreases with increasing temperature. The study explores the response mechanism of O3 with the change of driving variables, which can provide a scientific foundation and methodological support for the targeted management of O3 pollution.
Subject(s)
Air Pollutants , Air Pollution , Cities , Environmental Monitoring , Neural Networks, Computer , Ozone , Ozone/analysis , Air Pollutants/analysis , China , Air Pollution/statistics & numerical data , Spatio-Temporal AnalysisABSTRACT
PURPOSE: In pediatric medicine, precise estimation of bone age is essential for skeletal maturity evaluation, growth disorder diagnosis, and therapeutic intervention planning. Conventional techniques for determining bone age depend on radiologists' subjective judgments, which may lead to non-negligible differences in the estimated bone age. This study proposes a deep learning-based model utilizing a fully connected convolutional neural network(CNN) to predict bone age from left-hand radiographs. METHODS: The data set used in this study, consisting of 473 patients, was retrospectively retrieved from the PACS (Picture Achieving and Communication System) of a single institution. We developed a fully connected CNN consisting of four convolutional blocks, three fully connected layers, and a single neuron as output. The model was trained and validated on 80% of the data using the mean-squared error as a cost function to minimize the difference between the predicted and reference bone age values through the Adam optimization algorithm. Data augmentation was applied to the training and validation sets yielded in doubling the data samples. The performance of the trained model was evaluated on a test data set (20%) using various metrics including, the mean absolute error (MAE), median absolute error (MedAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The code of the developed model for predicting the bone age in this study is available publicly on GitHub at https://github.com/afiosman/deep-learning-based-bone-age-estimation . RESULTS: Experimental results demonstrate the sound capabilities of our model in predicting the bone age on the left-hand radiographs as in the majority of the cases, the predicted bone ages and reference bone ages are nearly close to each other with a calculated MAE of 2.3 [1.9, 2.7; 0.95 confidence level] years, MedAE of 2.1 years, RMAE of 3.0 [1.5, 4.5; 0.95 confidence level] years, and MAPE of 0.29 (29%) on the test data set. CONCLUSION: These findings highlight the usability of estimating the bone age from left-hand radiographs, helping radiologists to verify their own results considering the margin of error on the model. The performance of our proposed model could be improved with additional refining and validation.
Subject(s)
Age Determination by Skeleton , Deep Learning , Humans , Retrospective Studies , Age Determination by Skeleton/methods , Child , Female , Male , Saudi Arabia , Adolescent , Child, Preschool , Infant , Neural Networks, Computer , Hand Bones/diagnostic imaging , Hand Bones/growth & developmentABSTRACT
EEG-based emotion recognition is becoming crucial in brain-computer interfaces (BCI). Currently, most researches focus on improving accuracy, while neglecting further research on the interpretability of models, we are committed to analyzing the impact of different brain regions and signal frequency bands on emotion generation based on graph structure. Therefore, this paper proposes a method named Dual Attention Mechanism Graph Convolutional Neural Network (DAMGCN). Specifically, we utilize graph convolutional neural networks to model the brain network as a graph to extract representative spatial features. Furthermore, we employ the self-attention mechanism of the Transformer model which allocates more electrode channel weights and signal frequency band weights to important brain regions and frequency bands. The visualization of attention mechanism clearly demonstrates the weight allocation learned by DAMGCN. During the performance evaluation of our model on the DEAP, SEED, and SEED-IV datasets, we achieved the best results on the SEED dataset, showing subject-dependent experiments' accuracy of 99.42% and subject-independent experiments' accuracy of 73.21%. The results are demonstrably superior to the accuracies of most existing models in the realm of EEG-based emotion recognition.
ABSTRACT
Cancer is a heterogeneous and multifaceted disease with a significant global footprint. Despite substantial technological advancements for battling cancer, early diagnosis and selection of effective treatment remains a challenge. With the convenience of large-scale datasets including multiple levels of data, new bioinformatic tools are needed to transform this wealth of information into clinically useful decision-support tools. In this field, artificial intelligence (AI) technologies with their highly diverse applications are rapidly gaining ground. Machine learning methods, such as Bayesian networks, support vector machines, decision trees, random forests, gradient boosting, and K-nearest neighbors, including neural network models like deep learning, have proven valuable in predictive, prognostic, and diagnostic studies. Researchers have recently employed large language models to tackle new dimensions of problems. However, leveraging the opportunity to utilize AI in clinical settings will require surpassing significant obstacles-a major issue is the lack of use of the available reporting guidelines obstructing the reproducibility of published studies. In this review, we discuss the applications of AI methods and explore their benefits and limitations. We summarize the available guidelines for AI in healthcare and highlight the potential role and impact of AI models on future directions in cancer research.
ABSTRACT
Introduction: Extracting beat-by-beat information from electrocardiograms (ECGs) is crucial for various downstream diagnostic tasks that rely on ECG-based measurements. However, these measurements can be expensive and time-consuming to produce, especially for long-term recordings. Traditional ECG detection and delineation methods, relying on classical signal processing algorithms such as those based on wavelet transforms, produce high-quality delineations but struggle to generalise to diverse ECG patterns. Machine learning (ML) techniques based on deep learning algorithms have emerged as promising alternatives, capable of achieving similar performance without handcrafted features or thresholds. However, supervised ML techniques require large annotated datasets for training, and existing datasets for ECG detection/delineation are limited in size and the range of pathological conditions they represent. Methods: This article addresses this challenge by introducing two key innovations. First, we develop a synthetic data generation scheme that probabilistically constructs unseen ECG traces from "pools" of fundamental segments extracted from existing databases. A set of rules guides the arrangement of these segments into coherent synthetic traces, while expert domain knowledge ensures the realism of the generated traces, increasing the input variability for training the model. Second, we propose two novel segmentation-based loss functions that encourage the accurate prediction of the number of independent ECG structures and promote tighter segmentation boundaries by focusing on a reduced number of samples. Results: The proposed approach achieves remarkable performance, with a F 1 -score of 99.38% and delineation errors of 2.19 ± 17.73 ms and 4.45 ± 18.32 ms for ECG segment onsets and offsets across the P, QRS, and T waves. These results, aggregated from three diverse freely available databases (QT, LU, and Zhejiang), surpass current state-of-the-art detection and delineation approaches. Discussion: Notably, the model demonstrated exceptional performance despite variations in lead configurations, sampling frequencies, and represented pathophysiology mechanisms, underscoring its robust generalisation capabilities. Real-world examples, featuring clinical data with various pathologies, illustrate the potential of our approach to streamline ECG analysis across different medical settings, fostered by releasing the codes as open source.
ABSTRACT
Background: Lower Extremity Computed Tomography Angiography (CTA) is an effective non-invasive diagnostic tool for lower extremity artery disease (LEAD). This study aimed to develop an automatic classification model based on a coordinate-aware 3D deep neural network to evaluate the degree of arterial stenosis in lower extremity CTA. Methods: This retrospective study included 277 patients who underwent lower extremity CTA between May 1, 2017, and August 31, 2023. Radiologists annotated the lower extremity artery segments according to the degree of stenosis, and 12,450 3D patches containing the regions of interest were segmented to construct the dataset. A Coordinate-Aware Three-Dimensional Neural Network was implemented to classify the degree of stenosis of the lower extremity arteries with these patches. Metrics including accuracy, sensitivity, specificity, F1 score, and receiver operating characteristic (ROC) curves were used to evaluate the performance of the proposed model. Results: The accuracy, F1 score, and area under the ROC curve (AUC) of our proposed model were 93.08 %, 91.96 %, and 99.15 % for the above-knee arteries, and 91.70 %, 89.67 %, and 98.2 % respectively for below-knee arteries. The results of our proposed model exhibited a lead of 4-5% in accuracy score over the 3D baseline model and a lead of more than 10 % over the 2D baseline model. Conclusion: We successfully implemented a deep learning model, a promising tool for assisting radiologists in evaluating lower extremity arterial stenosis on CT angiography.
ABSTRACT
BACKGROUND: With the rapid advancement of deep learning network technology, the application of facial recognition technology in the medical field has received increasing attention. OBJECTIVE: This study aims to systematically review the literature of the past decade on facial recognition technology based on deep learning networks in the diagnosis of rare dysmorphic diseases and facial paralysis, among other conditions, to determine the effectiveness and applicability of this technology in disease identification. METHODS: This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for literature search and retrieved relevant literature from multiple databases, including PubMed, on 31 December 2023. The search keywords included deep learning convolutional neural networks, facial recognition, and disease recognition. A total of 208 articles on facial recognition technology based on deep learning networks in disease diagnosis over the past 10 years were screened, and 22 articles were selected for analysis. The meta-analysis was conducted using Stata 14.0 software. RESULTS: The study collected 22 articles with a total sample size of 57 539 cases, of which 43 301 were samples with various diseases. The meta-analysis results indicated that the accuracy of deep learning in facial recognition for disease diagnosis was 91.0% [95% CI (87.0%, 95.0%)]. CONCLUSION: The study results suggested that facial recognition technology based on deep learning networks has high accuracy in disease diagnosis, providing a reference for further development and application of this technology.
ABSTRACT
The article describes our experience in developing and training an artificial neural network based on artificial intelligence algorithms for recognizing the characteristic features of benign laryngeal tumors and variants of the norm of the larynx based on the analysis of laryngoscopy pictures obtained during the examination of patients. During the preparation of data for training the neural network, a dataset was collected, labeled and loaded, consisting of 1471 images of the larynx in digital formats (jpg, bmp). Next, the neural network was trained and tested in order to recognize images of the norm and neoplasms of the larynx. The developed and trained artificial neural network demonstrated an accuracy of 86% in recognizing of benign laryngeal tumors and variants of the norm of the larynx. The proposed technology can be further used in practical healthcare to control and improve the quality of diagnosis of laryngeal pathologies.
Subject(s)
Laryngeal Neoplasms , Laryngoscopy , Neural Networks, Computer , Humans , Laryngeal Neoplasms/diagnosis , Laryngoscopy/methods , Larynx/physiopathology , Larynx/pathology , MaleABSTRACT
Currently, deep learning is developing rapidly in the field of image segmentation, and medical image segmentation is one of the key applications in this field. Conventional CNN has achieved great success in general medical image segmentation tasks, but it has feature loss in the feature extraction part and lacks the ability to explicitly model remote dependencies, which makes it difficult to adapt to the task of human organ segmentation. Although methods containing attention mechanisms have made good progress in the field of semantic segmentation, most of the current attention mechanisms are limited to a single sample, while the number of samples of human organ images is large, ignoring the correlation between the samples is not conducive to image segmentation. In order to solve these problems, an internal and external dual-attention segmentation network (IEA-Net) is proposed in this paper, and the ICSwR (interleaved convolutional system with residual) module and the IEAM module are designed in this network. The ICSwR contains interleaved convolution and hopping connection, which are used for the initial extraction of the features in the encoder part. The IEAM module (internal and external dual-attention module) consists of the LGGW-SA (local-global Gaussian-weighted self-attention) module and the EA module, which are in a tandem structure. The LGGW-SA module focuses on learning local-global feature correlations within individual samples for efficient feature extraction. Meanwhile, the EA module is designed to capture inter-sample connections, addressing multi-sample complexities. Additionally, skip connections will be incorporated into each IEAM module within both the encoder and decoder to reduce feature loss. We tested our method on the Synapse multi-organ segmentation dataset and the ACDC cardiac segmentation dataset, and the experimental results show that the proposed method achieves better performance than other state-of-the-art methods.
ABSTRACT
Skin microvasculature is vital for human cardiovascular health and thermoregulation, but its imaging and analysis presents significant challenges. Statistical methods such as speckle decorrelation in optical coherence tomography angiography (OCTA) often require multiple co-located B-scans, leading to lengthy acquisitions prone to motion artefacts. Deep learning has shown promise in enhancing accuracy and reducing measurement time by leveraging local information. However, both statistical and deep learning methods typically focus solely on processing individual 2D B-scans, neglecting contextual information from neighbouring B-scans. This limitation compromises spatial context and disregards the 3D features within tissue, potentially affecting OCTA image accuracy. In this study, we propose a novel approach utilising 3D convolutional neural networks (CNNs) to address this limitation. By considering the 3D spatial context, these 3D CNNs mitigate information loss, preserving fine details and boundaries in OCTA images. Our method reduces the required number of B-scans while enhancing accuracy, thereby increasing clinical applicability. This advancement holds promise for improving clinical practices and understanding skin microvascular dynamics crucial for cardiovascular health and thermoregulation.
Subject(s)
Imaging, Three-Dimensional , Microvessels , Neural Networks, Computer , Skin , Tomography, Optical Coherence , Tomography, Optical Coherence/methods , Humans , Microvessels/diagnostic imaging , Microvessels/physiology , Skin/diagnostic imaging , Skin/blood supply , Imaging, Three-Dimensional/methods , Image Processing, Computer-Assisted/methods , Deep LearningABSTRACT
DNA N6 methyladenine (6mA) plays an important role in many biological processes, and accurately identifying its sites helps one to understand its biological effects more comprehensively. Previous traditional experimental methods are very labor-intensive and traditional machine learning methods also seem to be somewhat insufficient as the database of 6mA methylation groups becomes progressively larger, so we propose a deep learning-based method called multi-scale convolutional model based on global response normalization (CG6mA) to solve the prediction problem of 6mA site. This method is tested with other methods on three different kinds of benchmark datasets, and the results show that our model can get more excellent prediction results.
ABSTRACT
INTRODUCTION: Early prediction and timely treatment are essential for minimizing the risk of visual loss or blindness of retinopathy of prematurity, emphasizing the importance of ROP screening in clinical routine. OBJECTIVE: To establish predictive models for ROP occurrence based on the risk factors using artificial neural network. METHODS: A cohort of 591 infants was recruited in this retrospective study. The association between ROP and perinatal factors was analyzed by univariate analysis and multivariable logistic regression. We developed predictive models for ROP screening using back propagation neural network, which was further optimized by applying genetic algorithm method. To assess the predictive performance of the models, the areas under the curve, sensitivity, specificity, negative predictive value, positive predictive value and accuracy were used to show the performances of the prediction models. RESULTS: ROP of any stage was found in 193 (32.7%) infants. Twelve risk factors of ROP were selected. Based on these factors, predictive models were built using BP neural network and genetic algorithm-back propagation (GA-BP) neural network. The areas under the curve for prediction models were 0.857, and 0.908 in test, respectively. CONCLUSIONS: We developed predictive models for ROP using artificial neural network. GA-BP neural network exhibited superior predictive ability for ROP when dealing with its non-linear clinical data.
Subject(s)
Gestational Age , Neural Networks, Computer , Retinopathy of Prematurity , Humans , Retinopathy of Prematurity/diagnosis , Retinopathy of Prematurity/epidemiology , Retrospective Studies , Infant, Newborn , Female , Male , Risk Factors , Predictive Value of Tests , ROC Curve , Neonatal Screening/methods , AlgorithmsABSTRACT
Cell type identification is an indispensable analytical step in single-cell data analyses. To address the high noise stemming from gene expression data, existing computational methods often overlook the biologically meaningful relationships between genes, opting to reduce all genes to a unified data space. We assume that such relationships can aid in characterizing cell type features and improving cell type recognition accuracy. To this end, we introduce scPriorGraph, a dual-channel graph neural network that integrates multi-level gene biosemantics. Experimental results demonstrate that scPriorGraph effectively aggregates feature values of similar cells using high-quality graphs, achieving state-of-the-art performance in cell type identification.
Subject(s)
Single-Cell Analysis , Single-Cell Analysis/methods , Humans , Neural Networks, Computer , RNA-Seq/methods , Computational Biology/methods , Algorithms , Software , Single-Cell Gene Expression AnalysisABSTRACT
Introduction: The integration of self-attention mechanisms into Spiking Neural Networks (SNNs) has garnered considerable interest in the realm of advanced deep learning, primarily due to their biological properties. Recent advancements in SNN architecture, such as Spikformer, have demonstrated promising outcomes. However, we observe that Spikformer may exhibit excessive energy consumption, potentially attributable to redundant channels and blocks. Methods: To mitigate this issue, we propose a one-shot Spiking Transformer Architecture Search method, namely Auto-Spikformer. Auto-Spikformer extends the search space to include both transformer architecture and SNN inner parameters. We train and search the supernet based on weight entanglement, evolutionary search, and the proposed Discrete Spiking Parameters Search (DSPS) methods. Benefiting from these methods, the performance of subnets with weights inherited from the supernet without even retraining is comparable to the original Spikformer. Moreover, we propose a new fitness function aiming to find a Pareto optimal combination balancing energy consumption and accuracy. Results and discussion: Our experimental results demonstrate the effectiveness of Auto-Spikformer, which outperforms the original Spikformer and most CNN or ViT models with even fewer parameters and lower energy consumption.
ABSTRACT
Automated procedures for classifying vehicle damage are critical in industries requiring extensive vehicle management. Despite substantial research demands, challenges in the field of vehicle damage classification persist due to the scarcity of public datasets and the complexity of constructing datasets. In response to these challenges, we introduce a Three-Quarter View Car Damage Dataset (TQVCD dataset), emphasizing simplicity in labeling, data accessibility, and rich information inherent in three-quarter views. The TQVCD dataset distinguishes class by vehicle orientation (front or rear) and type of damage while maintaining a three-quarter view. We evaluate performance using five prevalent pre-trained deep learning architectures-ResNet-50, DenseNet-160, EfficientNet-B0, MobileNet-V2, and ViT-employing a suite of binary classification models. To enhance classification robustness, we implement a model ensemble method to effectively mitigate individual model dependencies' deviations. Additionally, we interview three experts from the used-car platform to validate the necessity of a vehicle damage classification model using the corresponding dataset from an industrial perspective. Empirical findings underscore the dataset's comprehensive coverage of vehicle perspectives, facilitating efficient data collection and damage classification while minimizing labor-intensive labeling efforts.
ABSTRACT
In this paper, a new approach has been introduced for classifying the music genres. The proposed approach involves transforming an audio signal into a unified representation known as a sound spectrum, from which texture features have been extracted using an enhanced Rigdelet Neural Network (RNN). Additionally, the RNN has been optimized using an improved version of the partial reinforcement effect optimizer (IPREO) that effectively avoids local optima and enhances the RNN's generalization capability. The GTZAN dataset has been utilized in experiments to assess the effectiveness of the proposed RNN/IPREO model for music genre classification. The results show an impressive accuracy of 92 % by incorporating a combination of spectral centroid, Mel-spectrogram, and Mel-frequency cepstral coefficients (MFCCs) as features. This performance significantly outperformed K-Means (58 %) and Support Vector Machines (up to 68 %). Furthermore, the RNN/IPREO model outshined various deep learning architectures such as Neural Networks (65 %), RNNs (84 %), CNNs (88 %), DNNs (86 %), VGG-16 (91 %), and ResNet-50 (90 %). It is worth noting that the RNN/IPREO model was able to achieve comparable results to well-known deep models like VGG-16, ResNet-50, and RNN-LSTM, sometimes even surpassing their scores. This highlights the strength of its hybrid CNN-Bi-directional RNN design in conjunction with the IPREO parameter optimization algorithm for extracting intricate and sequential auditory data.
ABSTRACT
Radiologists encounter significant challenges when segmenting and determining brain tumors in patients because this information assists in treatment planning. The utilization of artificial intelligence (AI), especially deep learning (DL), has emerged as a useful tool in healthcare, aiding radiologists in their diagnostic processes. This empowers radiologists to understand the biology of tumors better and provide personalized care to patients with brain tumors. The segmentation of brain tumors using multi-modal magnetic resonance imaging (MRI) images has received considerable attention. In this survey, we first discuss multi-modal and available magnetic resonance imaging modalities and their properties. Subsequently, we discuss the most recent DL-based models for brain tumor segmentation using multi-modal MRI. We divide this section into three parts based on the architecture: the first is for models that use the backbone of convolutional neural networks (CNN), the second is for vision transformer-based models, and the third is for hybrid models that use both convolutional neural networks and transformer in the architecture. In addition, in-depth statistical analysis is performed of the recent publication, frequently used datasets, and evaluation metrics for segmentation tasks. Finally, open research challenges are identified and suggested promising future directions for brain tumor segmentation to improve diagnostic accuracy and treatment outcomes for patients with brain tumors. This aligns with public health goals to use health technologies for better healthcare delivery and population health management.
ABSTRACT
Estimating cognitive workload levels is an emerging research topic in the cognitive neuroscience domain, as participants' performance is highly influenced by cognitive overload or underload results. Different physiological measures such as Electroencephalography (EEG), Functional Magnetic Resonance Imaging, Functional near-infrared spectroscopy, respiratory activity, and eye activity are efficiently used to estimate workload levels with the help of machine learning or deep learning techniques. Some reviews focus only on EEG-based workload estimation using machine learning classifiers or multimodal fusion of different physiological measures for workload estimation. However, a detailed analysis of all physiological measures for estimating cognitive workload levels still needs to be discovered. Thus, this survey highlights the in-depth analysis of all the physiological measures for assessing cognitive workload. This survey emphasizes the basics of cognitive workload, open-access datasets, the experimental paradigm of cognitive tasks, and different measures for estimating workload levels. Lastly, we emphasize the significant findings from this review and identify the open challenges. In addition, we also specify future scopes for researchers to overcome those challenges.
ABSTRACT
Deep convolutional neural networks (CNNs) are commonly used as computational models for the primate ventral stream, while deep spiking neural networks (SNNs) incorporated with both the temporal and spatial spiking information still lack investigation. We compared performances of SNN and CNN in prediction of visual responses to the naturalistic stimuli in area V4, inferior temporal (IT), and orbitofrontal cortex (OFC). The accuracies based on SNN were significantly higher than that of CNN in prediction of temporal-dynamic trajectory and averaged firing rate of visual response in V4 and IT. The temporal dynamics were captured by SNN for neurons with diverse temporal profiles and category selectivities, and most sensitively captured around the time of peak responses for each brain region. Consistently, SNN activities showed significantly stronger correlations with IT, V4 and OFC responses. In SNN, correlations with neural activities were stronger for later time-step features than early time-step features. The temporal-dynamic prediction was also significantly improved by considering preceding neural activities during the prediction. Thus, our study demonstrated SNN as a powerful temporal-dynamic model for cortical responses to complex naturalistic stimuli.
ABSTRACT
BACKGROUND: The intersection of artificial intelligence and medical image analysis has ushered in a new era of innovation and changed the landscape of brain tumor detection and diagnosis. Correct detection and classification of brain tumors based on medical images is crucial for early diagnosis and effective treatment. Convolutional Neural Network (CNN) models are widely used for disease detection. However, they are sometimes unable to sufficiently recognize the complex features of medical images. METHODS: This paper proposes a fused Deep Learning (DL) model that combines Graph Neural Networks (GNN), which recognize relational dependencies of image regions, and CNN, which captures spatial features, is proposed to improve brain tumor detection. By integrating these two architectures, our model achieves a more comprehensive representation of brain tumor images and improves classification performance. The proposed model is evaluated on a public dataset of 10847 MRI images. The results show that the proposed model outperforms the existing pre-trained models and traditional CNN architectures. RESULTS: The fused DL model achieves 93.68% accuracy in brain tumor classification. The results indicate that the proposed model outperforms the existing pre-trained models and traditional CNN architectures. CONCLUSION: The numerical results suggest that the model should be further investigated for potential use in clinical trials to improve clinical decision-making.