Search

Abstract Background Complete resection of malignant gliomas is hampered by the difficulty in distinguishing tumor cells at the infiltration zone. Fluorescence guidance with 5-ALA assists in reaching this goal. Using hyperspectral imaging, previous work characterized five fluorophores’ emission spectra in most human brain tumors. Methods In this paper, the effectiveness of these five spectra was explored for different tumor and tissue classification tasks in 184 patients (891 hyperspectral measurements) harboring low- (n = 30) and high-grade gliomas (n = 115), non-glial primary brain tumors (n = 19), radiation necrosis (n = 2), miscellaneous (n = 10) and metastases (n = 8). Four machine-learning models were trained to classify tumor type, grade, glioma margins, and IDH mutation. Results Using random forests and multilayer perceptrons, the classifiers achieve average test accuracies of 84–87%, 96.1%, 86%, and 91% respectively. All five fluorophore abundances vary between tumor margin types and tumor grades (p

In semi-supervised learning (SSL) for medical image classification, model performance is often hindered by the scarcity of labeled data and the complexity of unlabeled data. This paper proposes an enhanced SSL approach to address these challenges by effectively utilizing unlabeled data through a combination of pseudo-labeling and contrastive learning. The key contribution of our method is the introduction of a Dynamic Sample Reweighting strategy to select reliable unlabeled samples, thereby improving the model’s utilization of unlabeled data. Additionally, we incorporate multiple data augmentation strategies based on the Mean Teacher (MT) model to ensure consistent outputs across different perturbations. To better capture and integrate multi-scale features, we propose a novel feature fusion network, the Medical Multi-scale Feature Fusion Network (MedFuseNet), which enhances the model’s ability to classify complex medical images. Finally, we introduce a pseudo-label guided contrastive learning (PGC) loss function that improves intra-class compactness and inter-class separability of the model’s feature representations. Extensive experiments on three public medical image datasets demonstrate that our method outperforms existing SSL approaches, achieving 93.16% accuracy on the ISIC2018 dataset using only 20% labeled data, highlighting the potential of our approach to advance medical image classification under limited supervision.

The development of medical image classification models necessitates a substantial number of labeled images for model training. In real-world scenarios, sample sizes are typically limited and labeled samples often constitute only a small portion of the dataset. This paper aims to investigate a collaborative similarity learning strategy that optimizes pseudo-labels to enhance model accuracy and expedite its convergence, known as the joint similarity learning framework. By integrating semantic similarity and instance similarity, the pseudo-labels are mutually refined to ensure their quality during initial training. Furthermore, the similarity score is utilized as a weight to guide samples away from misclassification predictions during the classification process. To enhance the model’s generalization ability, an adaptive consistency constraint is introduced into the loss function to improve performance on untrained datasets. The model achieved a satisfactory accuracy of 93.65% at 80% labeling ratio, comparable to supervised learning methods’ performance. Even with very low labeling ratio (e.g., 5%), the model still attained an accuracy of 74.28%. Comparison with other techniques such as Mean Teacher and FixMatch revealed that our approach significantly outperforms them in medical image classification tasks through improving accuracy by approximately 2%, demonstrating this framework’s leadership in medical image classification.

Abstract Histopathological analysis requires a lot of clinical experience and time for pathologists. Artificial intelligence (AI) may have an important role in assisting pathologists and leading to more efficient and effective histopathological diagnoses. To address the challenge of requiring a large number of labelled images to train deep learning models in breast cancer histopathological image classification, a self‐training semi‐supervised learning method consisting three components is proposed: Firstly, a pre‐trained ResNet‐18 was used to extract features and generate pseudo‐labels for unlabelled data; secondly, a relational weight network based on the squeeze‐and‐excitation network (SENet) was trained to calculate the non‐linear distance metrices between labelled and unlabelled samples, in order to improve the accuracy of pseudo‐labelling; lastly, a consistency loss—maximum mean difference (MMD)—was added into the model to minimize the divergence between distributions of unlabelled and labelled samples. Extensive experiments were conducted on the open access BreakHis dataset. The proposed method outperformed the state‐of‐the‐art semi‐supervised methods at all tested annotated percentages (10–70%), and also achieved comparable performance with supervised methods at higher annotated percentages (50%, 70%).

The past decade has witnessed an explosive growth in the development and use of artificial intelligence (AI) across diverse fields [...]

Deep learning has substantially improved the state-of-the-art in object detection and image classification. Deep learning usually requires large-scale labelled datasets to train the models; however, due to the restrictions in medical data sharing and accessibility and the expensive labelling cost, the application of deep learning in medical image classification has been dramatically hindered. In this study, we propose a novel method that leverages semi-supervised adversarial learning and pseudo-labelling to incorporate the unlabelled images in model learning. We validate the proposed method on two public databases, including ChestX-ray14 for lung disease classification and BreakHis for breast cancer histopathological image diagnosis. The results show that our method achieved highly effective performance with an accuracy of 93.15% while using only 30% of the labelled samples, which is comparable to the state-of-the-art accuracy for chest X-ray classification; it also outperformed the current methods in multi-class breast cancer histopathological image classification with a high accuracy of 96.87%.

Ship target classification plays an important role in tasks such as maritime traffic control, maritime target tracking, and military reconnaissance. The complex ocean environment often causes obscuration of the ship targets, thus resulting in low accuracy of the obscured targets. This article presents a novel target classification algorithm-improved InceptionV3 and center loss convolution neural network (IICL-CNN)-based on the well-established inception network to improve the accuracy of obscured targets. This algorithm features a new objective function, which is designed to learn common features of both the clear samples and the obscured samples and, in the meantime, reduce the intraclass distance among the obscured samples. Experiments were performed on an optical remote sensing image dataset which consisted of 48 000 ship images in nine categories. The proposed method demonstrated superior performance on the obscured ship targets compared to the original InceptionV3 model. On average, the accuracy was 4.23%, 5.98%, and 17.48% higher on the ship targets that were occluded by levels of 30%, 50%, and 70%, respectively. Our experimental results showed that the proposed IICL-CNN could effectively improve the accuracy of the ship targets at various occlusion levels.

XRT separation equipment is attracting much attention as the mining industry increasingly uses pre-sorting technology. Its sorting accuracy is affected by differences in ore shape and particle size during operation. This paper, in which numerical simulations are conducted to investigate the resistance of ores under various situations, including varying blowing distances, cross-sections, and practical sizes, Additionally, this paper conducts validation tests. The test results indicate that within the 0.1-0.25 m section from the nozzle exit, there is a rapid decrease in velocity, accompanied by a significant change in ore resistance. Beyond the 0.25 m mark, the velocity reduction slows down, while the ore resistance becomes smaller. There exists a notable disparity in the resistance of ores with varying cross-sectional geometries. The size of the jet velocity surface caused by blowing distance significantly influences the resistance of ore with varying particle sizes. Furthermore, the resistance of the ore remains constant subsequent to the impact surface of the ore surpassing the surface of the jet velocity. Consequently, appropriately modifying the blowing distance, inlet pressure, and jet speed in accordance with the cross-sectional area and particle size of the majority of the ores stream can enhance the precision of the sorting process. [ABSTRACT FROM AUTHOR]

Recent studies matching eye gaze patterns with those of others contain research that is heavily reliant on string editing methods borrowed from early work in bioinformatics. Previous studies have shown string editing methods to be susceptible to false negative results when matching mutated genes or unordered regions of interest in scanpaths. Even as new methods have emerged for matching amino acids using novel combinatorial techniques, scanpath matching is still limited by a traditional collinear approach. This approach reduces the ability to discriminate between free viewing scanpaths of two people looking at the same stimulus due to the heavy weight placed on linearity. To overcome this limitation, we here introduce a new method called SoftMatch to compare pairs of scanpaths. SoftMatch diverges from traditional scanpath matching in two different ways: firstly, by preserving locality using fractal curves to reduce dimensionality from 2D Cartesian (x,y) coordinates into 1D (h) Hilbert distances, and secondly by taking a combinatorial approach to fixation matching using discrete Fréchet distance measurements between segments of scanpath fixation sequences. These matching “sequences of fixations over time” are a loose acronym for SoftMatch. Results indicate high degrees of statistical and substantive significance when scoring matches between scanpaths made during free-form viewing of unfamiliar stimuli. Applications of this method can be used to better understand bottom up perceptual processes extending to scanpath outlier detection, expertise analysis, pathological screening, and salience prediction.

Deep learning algorithms have been increasingly used in ship image detection and classification. To improve the ship detection and classification in photoelectric images, an improved recurrent attention convolutional neural network is proposed. The proposed network has a multi-scale architecture and consists of three cascading sub-networks, each with a VGG19 network for image feature extraction and an attention proposal network for locating feature area. A scale-dependent pooling algorithm is designed to select an appropriate convolution in the VGG19 network for classification, and a multi-feature mechanism is introduced in attention proposal network to describe the feature regions. The VGG19 and attention proposal network are cross-trained to accelerate convergence and to improve detection accuracy. The proposed method is trained and validated on a self-built ship database and effectively improve the detection accuracy to 86.7% outperforming the baseline VGG19 and recurrent attention convolutional neural network methods.

Objective: Using diffusion tensor imaging (DTI), we examined chronic stable MS lesions, peri-lesional white matter (PLWM) and normal appearing white matter (NAWM) in patients with relapsing-remitting multiple sclerosis (RRMS) for evidence of progressive tissue destruction and evaluated whether diffusivity change is associated with conventional MRI parameters and clinical findings. Method: Pre- and post-gadolinium T1, T2 and DTI images were acquired from 55 consecutive RRMS patients at baseline and 42.3±9.7months later. Chronic stable T2 lesions of sufficient size were identified in 43 patients (total of 134 lesions). Diffusivity parameters such as axial diffusivity (AD), radial diffusivity (RD), mean diffusivity (MD) and fractional anisotropy (FA) were compared at baseline and follow-up. MRI was also performed in 20 normal subjects of similar age and gender. Results: Within the core of chronic MS lesions the diffusion of water molecules significantly increased over the follow-up period, while in NAWM all diffusivity indices remained stable. Since increase of AD and RD in lesional core was highly concordant, indicating isotropic nature of diffusivity change, and considering potential effect of crossing fibers on directionally-selective indices, only MD, a directionally-independent measure, was used for further analysis. The significant increase of MD in the lesion core during the follow-up period (1.29±0.19μm2/ms and 1.34±0.20μm2/ms at baseline and follow-up respectively, P

Automatic severity assessment and progression prediction can facilitate admission, triage, and referral of COVID-19 patients. This study aims to explore the potential use of lung lesion features in the management of COVID-19, based on the assumption that lesion features may carry important diagnostic and prognostic information for quantifying infection severity and forecasting disease progression. A novel LesionEncoder framework is proposed to detect lesions in chest CT scans and to encode lesion features for automatic severity assessment and progression prediction. The LesionEncoder framework consists of a U-Net module for detecting lesions and extracting features from individual CT slices, and a recurrent neural network (RNN) module for learning the relationship between feature vectors and collectively classifying the sequence of feature vectors. Chest CT scans of two cohorts of COVID-19 patients from two hospitals in China were used for training and testing the proposed framework. When applied to assessing severity, this framework outperformed baseline methods achieving a sensitivity of 0.818, specificity of 0.952, accuracy of 0.940, and AUC of 0.903. It also outperformed the other tested methods in disease progression prediction with a sensitivity of 0.667, specificity of 0.838, accuracy of 0.829, and AUC of 0.736. The LesionEncoder framework demonstrates a strong potential for clinical application in current COVID-19 management, particularly in automatic severity assessment of COVID-19 patients. This framework also has a potential for other lesion-focused medical image analyses.

Digital pathology is gaining prominence among the researchers with developments in advanced imaging modalities and new technologies. Generative adversarial networks (GANs) are a recent development in the field of artificial intelligence and since their inception, have boosted considerable interest in digital pathology. GANs and their extensions have opened several ways to tackle many challenging histopathological image processing problems such as color normalization, virtual staining, ink removal, image enhancement, automatic feature extraction, segmentation of nuclei, domain adaptation and data augmentation. This paper reviews recent advances in histopathological image processing using GANs with special emphasis on the future perspectives related to the use of such a technique. The papers included in this review were retrieved by conducting a keyword search on Google Scholar and manually selecting the papers on the subject of H&E stained digital pathology images for histopathological image processing. In the first part, we describe recent literature that use GANs in various image preprocessing tasks such as stain normalization, virtual staining, image enhancement, ink removal, and data augmentation. In the second part, we describe literature that use GANs for image analysis, such as nuclei detection, segmentation, and feature extraction. This review illustrates the role of GANs in digital pathology with the objective to trigger new research on the application of generative models in future research in digital pathology informatics.

Previous studies have revealed brain adaptations to injury that occurs in optic neuritis (ON); however, the mechanisms underlying the functional connectivity (FC) and gray matter volume (GMV) changes in ON have not been clarified. Here, 51 single attack ON patients and 45 recurrent attacks ON patients were examined using structural MRI and resting-state functional MRI (RS-fMRI), and compared to 49 age- and gender-matched healthy controls (HC). FC analysis with a seed in primary visual cortex (V1 area) was used to assess the differences among three groups. Whole brain GMV was assessed using voxel-based morphometry (VBM). Correlation analyses were performed between FC results, structural MRI and clinical variables. We found positive correlations between the Paced Auditory Serial Addition Test (PASAT) score and FC in V1 area with bilateral middle frontal gyrus. Disease duration is significantly negatively related to FC in V1 area with the left inferior parietal lobule. Compared to the HC, single attack ON patients were found to have decreased FC values in the frontal, temporal lobes, right inferior occipital gyrus, right insula, right inferior parietal lobule, and significant increased FC values in the left thalamus. Recurrent attacks ON patients had the same pattern with single attack ON. No significant differences were found in brain GMV among three groups. This study provides the imaging evidence that impairment and compensation of V1 area connectivity coexist in ON patients, and provides important insights into the underlying neural mechanisms of ON.

Context.--Glioma is the most common primary brain tumor in adults. The diagnosis and grading of different pathological subtypes of glioma is essential in treatment planning and prognosis. Objective.--To propose a deep learning--based approach for the automated classification of glioma histopathology images. Two classification methods, the ensemble method based on 2 binary classifiers and the multiclass method using a single multiclass classifier, were implemented to classify glioma images into astrocytoma, oligodendroglioma, and glioblastoma, according to the 5th edition of the World Health Organization classification of central nervous system tumors, published in 2021. Design.--We tested 2 different deep neural network architectures (VGG19 and ResNet50) and extensively validated the proposed approach based on The Cancer Genome Atlas data set (n ¼ 700). We also studied the effects of stain normalization and data augmentation on the glioma classification task. Results.--With the binary classifiers, our model could distinguish astrocytoma and oligodendroglioma (combined) from glioblastoma with an accuracy of 0.917 (area under the curve [AUC] = 0.976) and astrocytoma from oligodendroglioma (accuracy = 0.821, AUC = 0.865). The multiclass method (accuracy = 0.861, AUC = 0.961) outperformed the ensemble method (accuracy = 0.847, AUC = 0.933) with the best performance displayed by the ResNet50 architecture. Conclusions.--With the high performance of our model (.80%), the proposed method can assist pathologists and physicians to support examination and differential diagnosis of glioma histopathology images, with the aim to expedite personalized medical care. [ABSTRACT FROM AUTHOR]

Introduction: Accurate diagnosis is crucial for brain tumors, given their low survival rates and high treatment costs. However, traditional methods relying on manual interpretation of medical images are time-consuming and prone to errors. Attention-based deep learning, utilizing deep neural networks to selectively focus on relevant features, offers a promising solution. Material and Methods: This paper presents an overview of recent advancements in attention-based deep learning for brain tumor image analysis. While the reviewed models have demonstrated respectable performance across different datasets, they have yet to achieve state-of-theart results. Results: Advanced techniques, including super-resolution image reconstruction, multi-swin-transformer blocks, and spatial group-wise enhanced attention blocks, have shown improved segmentation network performance. Integration of graph attention, swin-transformer, and gradient awareness minimization with positional attention convolution blocks, selfattention blocks, and intermittent fully connected layers has considerably enhanced the efficiency of classification networks. Conclusion: While attention-based deep learning has shown improvements in performance, challenges persist. These challenges include the requirement for large datasets, resource limitations, accurate segmentation of irregularly shaped tumors, and high computational demands. Future studies should address these challenges to further enhance the efficiency of brain tumor diagnoses in real-world settings. [ABSTRACT FROM AUTHOR]

The research on staging of pre-symptomatic and prodromal phase of neurological disorders, e.g., Alzheimer's disease (AD), is essential for prevention of dementia. New strategies for AD staging with a focus on early detection, are demanded to optimize potential efficacy of disease-modifying therapies that can halt or slow the disease progression. Recently, neuroimaging are increasingly used as additional research-based markers to detect AD onset and predict conversion of MCI and normal control (NC) to AD. Researchers have proposed a variety of neuroimaging biomarkers to characterize the patterns of the pathology of AD and MCI, and suggested that multi-view neuroimaging biomarkers could lead to better performance than single-view biomarkers in AD staging. However, it is still unclear what leads to such synergy and how to preserve or maximize. In an attempt to answer these questions, we proposed a cross-view pattern analysis framework for investigating the synergy between different neuroimaging biomarkers. We quantitatively analyzed nine types of biomarkers derived from FDG-PET and T1-MRI, and evaluated their performance in a task of classifying AD, MCI, and NC subjects obtained from the ADNI baseline cohort. The experiment results showed that these biomarkers could depict the pathology of AD from different perspectives, and output distinct patterns that are significantly associated with the disease progression. Most importantly, we found that these features could be separated into clusters, each depicting a particular aspect; and the inter-cluster features could always achieve better performance than the intra-cluster features in AD staging. [ABSTRACT FROM AUTHOR]

The ATP synthases have been isolated by affinity chromatography from the mitochondria of the fungal species Yarrowia lipolytica, Pichia pastoris, Pichia angusta and Saccharomyces cerevisiae. The subunit compositions of the purified enzyme complexes depended on the detergent used to solubilize and purify the complex, and the presence or absence of exogenous phospholipids. All four enzymes purified in the presence of n-dodecyl-β-D-maltoside had a complete complement of core subunits involved directly in the synthesis of ATP, but they were deficient to different extents in their supernumerary membrane subunits. In contrast, the enzymes from P. angusta and S. cerevisiae purified in the presence of n-decyl-β-maltose neopentyl glycol and the phospholipids 1-palmitoyl-2-oleoyl-sn-glycero-3-phosphocholine, 1-palmitoyl-2-oleoyl-sn-glycero-3-phosphoethanolamine, cardiolipin (diphosphatidylglycerol) and 1-palmitoyl-2-oleoyl-sn-glycero-3-[phospho-rac-(1-glycerol)] had a complete complement of core subunits and also contained all of the known supernumerary membrane subunits, e, f, g, j, k and ATP8 (or Aap1), plus an additional new membrane component named subunit l, related in sequence to subunit k. The catalytic domain of the enzyme from P. angusta was more resistant to thermal denaturation than the enzyme from S. cerevisiae, but less stable than the catalytic domain of the bovine enzyme, but the stator and the integrity of the transmembrane proton pathway were most stable in the enzyme from P. angusta. The P. angusta enzyme provides a suitable source of enzyme for studying the structure of the membrane domain and properties associated with that sector of the enzyme complex. [ABSTRACT FROM AUTHOR]

By means of econometrics, the calculating models and methods of efficiency analysis of the electricity futures market are proposed from three aspects: the market validity, the price discovery function and the hedge function. In this paper, considering the heteroskedasticity and nonstationarity of the electricity price, the validity test method of the electricity futures market is proposed by using the variance ratio. Based on the co-integration theory, the price discovery function analysis method of the electricity futures market is proposed. In addition, based on the generalized autoregressive conditional heteroskedasticity, the hedging ratio and performance evaluation method of the electricity futures market is proposed. By the empirical research on the Nordic electricity futures market, it can be found that its operation is efficient. It satisfies the weak-form efficiency hypothesis; the futures and spot prices are co-integrated; the futures market plays a dominant role in the price discovery; the hedge reduces the risk of transaction to a certain extent; and the operation efficiency during 2000-2003 is higher than that during 1996-1999. Although there are some inefficient factors, the Nordic electricity futures market is gradually tending towards maturity. [ABSTRACT FROM AUTHOR]

The structure of the intact monomeric ATP synthase from the fungus, Pichia angusta, has been solved by electron cryo-microscopy. The structure provides insights into the mechanical coupling of the transmembrane proton motive force across mitochondrial membranes in the synthesis of ATP. This mechanism requires a strong and integral stator, consisting of the catalytic α3β3-domain, peripheral stalk, and, in the membrane domain, subunit a and associated supernumerary subunits, kept in contact with the rotor turning at speeds up to 350 Hz. The stator's integrity is ensured by robust attachment of both the oligomycin sensitivity conferral protein (OSCP) to the catalytic domain and the membrane domain of subunit b to subunit a. The ATP8 subunit provides an additional brace between the peripheral stalk and subunit a. At the junction between the OSCP and the apparently stiff, elongated α-helical b-subunit and associated d- and h-subunits, an elbow or joint allows the stator to bend to accommodate lateral movements during the activity of the catalytic domain. The stator may also apply lateral force to help keep the static a-subunit and rotating c10-ring together. The interface between the c10-ring and the a-subunit contains the transmembrane pathway for protons, and their passage across the membrane generates the turning of the rotor. The pathway has two half-channels containing conserved polar residues provided by a bundle of four α-helices inclined at ~30° to the plane of the membrane, similar to those described in other species. The structure provides more insights into the workings of this amazing machine. [ABSTRACT FROM AUTHOR]

Neuroimaging has played an important role in non-invasive diagnosis and differentiation of neurodegenerative disorders, such as Alzheimer's disease and Mild Cognitive Impairment. Various features have been extracted from the neuroimaging data to characterize the disorders, and these features can be roughly divided into global and local features. Recent studies show a tendency of using local features in disease characterization, since they are capable of identifying the subtle disease-specific patterns associated with the effects of the disease on human brain. However, problems arise if the neuroimaging database involved multiple disorders or progressive disorders, as disorders of different types or at different progressive stages might exhibit different degenerative patterns. It is difficult for the researchers to reach consensus on what brain regions could effectively distinguish multiple disorders or multiple progression stages. In this study we proposed a Multi-Channel pattern analysis approach to identify the most discriminative local brain metabolism features for neurodegenerative disorder characterization. We compared our method to global methods and other pattern analysis methods based on clinical expertise or statistics tests. The preliminary results suggested that the proposed Multi-Channel pattern analysis method outperformed other approaches in Alzheimer's disease characterization, and meanwhile provided important insights into the underlying pathology of Alzheimer's disease and Mild Cognitive Impairment. [ABSTRACT FROM AUTHOR]

Using first-principles calculations in the framework of density functional theory, we studied the electronic structure and optical performance of TiN. It was found that the calculated structure parameter and optical performance are in better agreement with the latest relevant experimental data, and our theoretical studies showed that TiN is a perfect near infrared absorber with high visible light transmittance and could serve as references for future experimental study and its applications as solar radiation shielding material for windows. [ABSTRACT FROM AUTHOR]

In semi-supervised learning (SSL) for medical image classification, model performance is often hindered by the scarcity of labeled data and the complexity of unlabeled data. This paper proposes an enhanced SSL approach to address these challenges by effectively utilizing unlabeled data through a combination of pseudo-labeling and contrastive learning. The key contribution of our method is the introduction of a Dynamic Sample Reweighting strategy to select reliable unlabeled samples, thereby improving the model's utilization of unlabeled data. Additionally, we incorporate multiple data augmentation strategies based on the Mean Teacher (MT) model to ensure consistent outputs across different perturbations. To better capture and integrate multi-scale features, we propose a novel feature fusion network, the Medical Multi-scale Feature Fusion Network (MedFuseNet), which enhances the model's ability to classify complex medical images. Finally, we introduce a pseudo-label guided contrastive learning (PGC) loss function that improves intra-class compactness and inter-class separability of the model's feature representations. Extensive experiments on three public medical image datasets demonstrate that our method outperforms existing SSL approaches, achieving 93.16% accuracy on the ISIC2018 dataset using only 20% labeled data, highlighting the potential of our approach to advance medical image classification under limited supervision. [ABSTRACT FROM AUTHOR]

The development of medical image classification models necessitates a substantial number of labeled images for model training. In real-world scenarios, sample sizes are typically limited and labeled samples often constitute only a small portion of the dataset. This paper aims to investigate a collaborative similarity learning strategy that optimizes pseudo-labels to enhance model accuracy and expedite its convergence, known as the joint similarity learning framework. By integrating semantic similarity and instance similarity, the pseudo-labels are mutually refined to ensure their quality during initial training. Furthermore, the similarity score is utilized as a weight to guide samples away from misclassification predictions during the classification process. To enhance the model's generalization ability, an adaptive consistency constraint is introduced into the loss function to improve performance on untrained datasets. The model achieved a satisfactory accuracy of 93.65% at 80% labeling ratio, comparable to supervised learning methods' performance. Even with very low labeling ratio (e.g., 5%), the model still attained an accuracy of 74.28%. Comparison with other techniques such as Mean Teacher and FixMatch revealed that our approach significantly outperforms them in medical image classification tasks through improving accuracy by approximately 2%, demonstrating this framework's leadership in medical image classification. [ABSTRACT FROM AUTHOR]

With the evaluation of Artificial Intelligence (AI), there has been a resurgence of interest in how to use AI algorithms on low-power embedded systems to broaden potential use cases of the Internet of Things (IoT). To mimic multimodal human perception, multimodal deep neural networks (M-DNN) have recently become very popular with the classification task due to their impressive performance for computer vision and audio processing tasks. This article presents TinyM2Net-V2—a compact low-power software hardware architecture for multimodal deep neural networks for resource-constrained tiny devices. To compress the models to implement on tiny devices, cyclicly sparsification and hybrid quantization (4-bits weights and 8-bits activations) methods are used. Although model compression techniques are an active research area, we are the first to demonstrate their efficacy for multimodal deep neural networks, using cyclicly sparsification and hybrid quantization of weights/activations. TinyM2Net-V2 shows that even a tiny multimodal deep neural network model can improve the classification accuracy more than that of any unimodal counterparts. Parameterized M-DNN model architecture was designed to be evaluated in two different case-studies: vehicle detection from multimodal images and audios and COVID-19 detection from multimodal audio recordings. The most compressed TinyM2Net-V2 achieves 92.5% COVID-19 detection accuracy (6.8% improvement from the unimodal full precision model) and 90.6% vehicle classification accuracy (7.7% improvement from the unimodal full precision model). A parameterized and flexible FPGA hardware accelerator was designed as well for TinyM2Net-V2 models. To the best of our knowledge, this is the first work accelerating multimodal deep neural network models on low-power Artix-7 FPGA hardware. We achieved energy efficiency of 9.04 GOP/s/W and 15.38 GOP/s/W for case-study 1 and case-study 2, respectively, which is comparable to the state-of-the-art results. Finally, we compared our tiny FPGA hardware implementation results with off-the-shelf resource-constrained devices and showed our implementation is faster and consumed less power compared to the off-the-shelf resource-constrained devices. [ABSTRACT FROM AUTHOR]

The article discusses the growing use of artificial intelligence (AI) in healthcare and its potential to revolutionize the field. It highlights various applications of AI, such as disease screening and diagnosis, COVID-19 patient management, and public health research. The article also acknowledges the challenges in implementing AI in healthcare, including issues with generalization and patient safety. Overall, the article provides a comprehensive overview of the advancements, benefits, and obstacles associated with AI in healthcare. [Extracted from the article]

Background: Previous in vitro and animal experiments have shown that copper plays an important role in cardiovascular health. Dietary copper is the main source of copper in the human body and the association between dietary copper and cardiovascular disease remains unclear. Our study aimed to investigate the associations of dietary copper intake with the risk of major cardiovascular disease incidence, cardiovascular disease mortality, and all-cause mortality in Chinese adults. Methods: Our study is based on Prospective Urban Rural Epidemiology China (PURE-China), a large prospective cohort study of 47 931 individuals aged 35–70 years from 12 provinces in China. Dietary intake was recorded using a validated semi-quantitative food frequency questionnaire designed specifically for the Chinese population. The daily intake of copper was obtained by multiplying the daily food intake with the nutrient content provided in the Chinese Food Composition Table (2002). Cox frailty proportional hazards models were developed to evaluate the association between dietary copper intake with mortality, major cardiovascular disease events, and their composite. Results: A total of 45 101 participants (mean age: 51.1 ± 9.7 years old) with complete information were included in the current study. The mean dietary copper intake was 2.6 ± 1.1 mg/d. During the 482 833 person-years of follow-up, 2 644(5.9%) participants died, 4 012(8.9%) developed new cardiovascular diseases, and 5 608(12.4%) participants experienced the composite endpoint. Compared with those in the first and second quartile of dietary copper intake, individuals in the third and fourth quantile had higher risk of composite outcomes, all-cause death, cardiovascular disease death, major cardiovascular disease and stroke occurrences. The associations remained similar in the subgroup and sensitivity analyses. Conclusions: Our findings demonstrated that excessive dietary copper intake was associated with higher risks of death and cardiovascular diseases in Chinese adults. Further studies in populations with different dietary characteristics are needed to obtain dose–response relationships and to refine global dietary recommendations. [ABSTRACT FROM AUTHOR]