Search

The advancement of medical imaging has profoundly impacted our understanding of the human body and various diseases. It has led to the continuous refinement of related technologies over many years. Despite these advancements, several challenges persist in the development of medical imaging, including data shortages characterized by low contrast, high noise levels, and limited image resolution. The U-Net architecture has significantly evolved to address these challenges, becoming a staple in medical imaging due to its effective performance and numerous updated versions. However, the emergence of Transformer-based models marks a new era in deep learning for medical imaging. These models and their variants promise substantial progress, necessitating a comparative analysis to comprehend recent advancements. This review begins by exploring the fundamental U-Net architecture and its variants, then examines the limitations encountered during its evolution. It then introduces the Transformer-based self-attention mechanism and investigates how modern models incorporate positional information. The review emphasizes the revolutionary potential of Transformer-based techniques, discusses their limitations, and outlines potential avenues for future research.

The left ventricle ejection fraction is an important index for assessing cardiac function and diagnosing cardiac diseases. At present, EchoNet-Dynamic dataset is the unique large-scale resource for studying ejection fraction estimation by echocardiography. Through segmentation of the end-systolic and end-diastolic frames, the ejection fraction can be calculated based on the volumes at these phases. However, existing segmentation methods either mostly focus on single-frame segmentation and rarely consider information across consecutive frames, or they fail to effectively exploit temporal information between consecutive frames, resulting in suboptimal segmentation performance. In our study, we constructed a dual-branch spatial-temporal feature extraction model for achieving echocardiogram video segmentation. One branch was dedicated to extracting semantic features of frames under supervision, while the other branch learned the optical flows between frames in an unsupervised manner. Subsequently, we jointly trained these two branches using a temporal consistency mechanism to acquire spatial-temporal features of the frames. This approach enhances both video segmentation performance and the consistency of transition frame segmentation. Experimental results demonstrate that our proposed model achieves promising segmentation performance compared to existing methods.

Ultrasound volume projection imaging has shown great promise to visualize spine features and diagnose scoliosis thanks to its harmlessness cheapness and efficiency The key to measuring spine deformity and assessing scoliosis is to accurately segment the spine bone features In this paper we propose a novel structure affinity dual attention based network SADANet for effective spine segmentation Global channel attention module and spatial criss cross attention module are combined in a parallel manner to generate rich global context of spine images Meanwhile we present a structure affinity strategy to encode the structural knowledge of spine bones into the semantic representations By this means the network can capture both contextual and structural information Experiments show that our proposed algorithm achieves promising performance on spine segmentation as compared with other state of the art candidates which makes it an appealing approach for intelligent scoliosis assessment

OBJECTIVES: Vertebral fracture is both common and serious among adults, yet it often goes undiagnosed. This study aimed to develop a shape-based algorithm (SBA) for the automatic identification of vertebral fractures. METHODS: The study included 144 participants (50 individuals with a fracture and 94 without a fracture) whose plain thoracolumbar spine X-rays were taken. Clinical diagnosis of vertebral fracture (grade 0 to 3) was made by rheumatologists using Genant's semiquantitative method. The SBA algorithm was developed to determine the ratio of vertebral body height loss. Based on the ratio, SBA classifies a vertebra into 4 classes: 0 = normal, 1 = mild fracture, 2 = moderate fracture, 3 = severe fracture). The concordance between clinical diagnosis and SBA-based classification was assessed at both person and vertebra levels. RESULTS: At the person level, the SBA achieved a sensitivity of 100% and specificity of 62% (95% CI, 51%-72%). At the vertebra level, the SBA achieved a sensitivity of 84% (95% CI, 72%-93%), and a specificity of 88% (95% CI, 85%-90%). On average, the SBA took 0.3 s to assess each X-ray. CONCLUSIONS: The SBA developed here is a fast and efficient tool that can be used to systematically screen for asymptomatic vertebral fractures and reduce the workload of healthcare professionals.

A growing body of literature has proved that general type-2 fuzzy control systems (GT2 FCSs) are reliable, robust, and safe control systems against severe external disturbances, high levels of noise, and uncertainty that are inevitable in real-world applications. Further studies on the GT2 FCSs are therefore needed to provide new insights into these control systems, in particular over their stability and computational complexity problems. Unlike the existing works on stability analysis of GT2 FCSs in the time domain, the aim of this article is to assess the stability properties of these systems in the frequency domain through a novel intuitive method. Before delving into stability analysis, an initial step involves reducing computational complexity. This is achieved by introducing a streamlined version of the GT2 fuzzy controller (GT2 FC). This simplified architecture is constructed using a series of zSlices-based interval type-2 fuzzy-logic controls (zIT2 FLCs) situated at specific zLevels. Each zIT2 FLC is composed of two embedded type-1 fuzzy FLCs (T1 FLCs). The subsequent phase entails a methodical procedure for assessing stability based on the existence of limit cycles. The initial stage involves the linearization of the simplified GT2 FC through the derivation of its describing function (DF). Next, a combination of the parameter plane approach and the particle swarm optimization (PSO) technique is leveraged. These techniques serve the purpose of pinpointing the regions corresponding to limit cycles and asymptotic stability with a focus on improving the stability boundary. Following this, the analysis shifts toward quantifying the system’s resilience in the face of uncertainty. Stability margins required to generate a limit cycle are calculated using stability equations. This step provides a measure of how robust the closed-loop system remains under varying degrees of uncertainty. Finally, three simulation examples are presented to justify the advantages of the

OBJECTIVE: Scoliosis is a spinal deformation in which the spine takes a lateral curvature, generating an angle in the coronal plane. The conventional method for detecting scoliosis is measurement of the Cobb angle in spine images obtained by anterior X-ray scanning. Ultrasound imaging of the spine is found to be less ionising than traditional radiographic modalities. For posterior ultrasound scanning, alternate indices of the spinous process angle (SPA) and ultrasound curve angle (UCA) were developed and have proven comparable to those of the traditional Cobb angle. In SPA, the measurements are made using the spinous processes as an anatomical reference, leading to an underestimation of the traditionally used Cobb angles. Alternatively, in UCA, more lateral features of the spine are employed for measurement of the main thoracic and thoracolumbar angles; however, clear identification of bony features is required. The current practice of UCA angle measurement is manual. This research attempts to automate the process so that the errors related to human intervention can be avoided and the scalability of ultrasound scoliosis diagnosis can be improved. The key objective is to develop an automatic scoliosis diagnosis system using 3-D ultrasound imaging. METHODS: The novel diagnosis system is a three-step process: (i) finding the ultrasound spine image with the most visible lateral features using the convolutional RankNet algorithm; (ii) segmenting the bony features from the noisy ultrasound images using joint spine segmentation and noise removal; and (iii) calculating the UCA automatically using a newly developed centroid pairing and inscribed rectangle slope method. RESULTS: The proposed method was evaluated on 109 patients with scoliosis of different severity. The results obtained had a good correlation with manually measured UCAs (R2=0.9784 for the main thoracic angle andR2=0.9671 for the thoracolumbar angle) and a clinically acceptable mean absolute difference of the m

In medical image analysis, anatomical landmarks usually contain strong prior knowledge of their structural information. In this paper, we propose to promote medical landmark localization by modeling the underlying landmark distribution via normalizing flows. Specifically, we introduce the flow-based landmark distribution prior as a learnable objective function into a regression-based landmark localization framework. Moreover, we employ an integral operation to make the mapping from heatmaps to coordinates differentiable to further enhance heatmap-based localization with the learned distribution prior. Our proposed Normalizing Flow-based Distribution Prior (NFDP) employs a straightforward backbone and non-problem-tailored architecture (i.e., ResNet18), which delivers high-fidelity outputs across three X-ray-based landmark localization datasets. Remarkably, the proposed NFDP can do the job with minimal additional computational burden as the normalizing flows module is detached from the framework on inferencing. As compared to existing techniques, our proposed NFDP provides a superior balance between prediction accuracy and inference speed, making it a highly efficient and effective approach. The source code of this paper is available at https://github.com/jacksonhzx95/NFDP.

The Brain Computer Interface (BCI) is the communication between the human brain and the computer. Electroencephalogram (EEG) is one of the biomedical signals which can be obtained by attaching electrodes to the scalp. Some EEG related applications can be developed to help disabled people, such as EEG based wheelchair or robotic arm. A hybrid BCI real-time control system is proposed to control a multi-tasks BCI robot. In this system, a sliding window based online data segmentation strategy is proposed to segment training data, which enable the system to learn the dynamic features when the subject's brain state transfer from a rest state to a task execution state. The features help the system achieve real-time control and ensure the continuity of executing actions. In addition, Common Spatial Pattern (CSP) can better extract the spatial features of these continuous actions from the dynamic data to ensure that multiple control commands are accurately classified. In the experiment, three subjects' EEG data is collected, trained and tested the performance and reliability of the proposed control system. The system records the robot's spending time, moving distance, and the number of objects pushing down. Experimental results are given to show the feasibility of the real-time control system. Compared to real-time remote controller, the proposed system can achieve similar performance. Thus, the proposed hybrid BCI real-time control system is able to control the robot in the real-time environment and can be used to develop robot-aided arm training methods based on neurological rehabilitation principles for stroke and brain injury patients.

Preventing living tissues’ direct exposure to ionising radiation has resulted in tremendous growth in medical imaging and e-health, enhancing intensive care of perilous patients and helping to improve quality of life. Moreover, the practice of image-reconstruction instruments that utilise ionising radiation significantly impacts the patient’s health. Prolonged or frequent exposure to ionising radiation is linked to several illnesses like cancer. These factors urged the advancement of non-invasive approaches, for instance, Electrical Impedance Tomography (EIT), a portable, non-invasive, low-cost, and safe imaging method. EIT image reconstruction still demands more exploitation, as it is an inverse and ill-conditioned problem. Numerous numerical techniques are used to answer this problem without producing anatomically unpredictable outcomes. Evolutionary Computational techniques can substitute conventional methods that usually create low-resolution blurry images. EIT reconstruction techniques optimise the relative error of reconstruction using population-based optimisation methods presented in this work. Three advanced optimisation methods have been developed to facilitate the iterative procedure for avoiding anatomically erratic solutions. Three different optimising techniques, namely, (a) Advanced Particle Swarm Optimisation Algorithm, (b) Advanced Gravitational Search Algorithm, and (c) Hybrid Gravitational Search Particle Swarm Optimization Algorithm (HGSPSO), are used. By utilising the advantages of these proposed techniques, the convergence and solution stability performance is improved. EIT images were obtained from the EIDORS library database for two case studies. The image reconstruction was optimised using the three proposed algorithms. EIDORS library was used for generating and solving forward and reverse problems. Two case studies were undertaken, i.e. circular tank simulation and gastric emptying. Thus, the results are analysed and presented as a real-wor

In recent years, there has been a renewal of interest in brain–computer interface (BCI). One of the BCI tasks is to classify the EEG motor imagery (MI). A great deal of effort has been made on MI classification. What seems to be lacking, however, is multiple MI classification. This paper develops a single-channel-based convolutional neural network to tackle multi-classification motor imagery tasks. For multi-classification, a single-channel learning strategy can extract effective information from each independent channel, making the information between adjacent channels not affect each other. A data evaluation method and a mutual information-based regularization parameters auto-selection algorithm are also proposed to generate effective spatial filters. The proposed method can be used to tackle the problem of an inaccurate mixed covariance matrix caused by fixed regularization parameters and invalid training data. To illustrate the merits of the proposed methods, we used the tenfold cross-validation accuracy and kappa as the evaluation measures to test two data sets. BCI4-2a and BCI3a data sets have four mental classes. For the BCI4-2a data set, the average accuracy is 79.01%, and the kappa is 0.7202 using data evaluation-based auto-selected filter bank regularized common spatial pattern voting (D-ACSP-V) and single-channel series convolutional neural network (SCS-CNN). Compared to traditional FBRCSP, the proposed method improved accuracy by 7.14% for the BCI4-2a data set. By using the BCI3a data set, the proposed method improved accuracy by 9.54% compared with traditional FBRCSP, the average accuracy of the proposed method is 83.70%, and the kappa is 0.7827.

In recent years, cardiovascular diseases (CVDs) have become one of the leading causes of mortality globally. At early stages, CVDs appear with minor symptoms and progressively get worse. The majority of people experience symptoms such as exhaustion, shortness of breath, ankle swelling, fluid retention, and other symptoms when starting CVD. Coronary artery disease (CAD), arrhythmia, cardiomyopathy, congenital heart defect (CHD), mitral regurgitation, and angina are the most common CVDs. Clinical methods such as blood tests, electrocardiography (ECG) signals, and medical imaging are the most effective methods used for the detection of CVDs. Among the diagnostic methods, cardiac magnetic resonance imaging (CMRI) is increasingly used to diagnose, monitor the disease, plan treatment and predict CVDs. Coupled with all the advantages of CMR data, CVDs diagnosis is challenging for physicians as each scan has many slices of data, and the contrast of it might be low. To address these issues, deep learning (DL) techniques have been employed in the diagnosis of CVDs using CMR data, and much research is currently being conducted in this field. This review provides an overview of the studies performed in CVDs detection using CMR images and DL techniques. The introduction section examined CVDs types, diagnostic methods, and the most important medical imaging techniques. The following presents research to detect CVDs using CMR images and the most significant DL methods. Another section discussed the challenges in diagnosing CVDs from CMRI data. Next, the discussion section discusses the results of this review, and future work in CVDs diagnosis from CMR images and DL techniques are outlined. Finally, the most important findings of this study are presented in the conclusion section.

A recommender system not only “gains users’ confidence” but also helps them in other ways, such as reducing their time spent and effort. To gain users’ confidence, one of the main goals of recommender systems in an e-commerce industry is to estimate the users’ interest by tracking the users’ transactional behavior to provide a fast and highly related set of top recommendations out of thousands of products. The standard ranking-based models, i.e., the denoising auto-encoder (DAE) and collaborative denoising auto-encoder (CDAE), exploit positive-only feedback without utilizing the ratings’ ranks for the full set of observed ratings. To confirm the rank of observed ratings (either low or high), a confidence value for each rating is required. Hence, an improved, confidence-integrated DAE is proposed to enhance the performance of the standard DAE for solving recommender systems problems. The correctness of the proposed method is authenticated using two standard MovieLens datasets such as ML-1M and ML-100K. The proposed study acts as a vital contribution for the design of an efficient, robust, and accurate algorithm by learning prominent latent features used for fast and accurate recommendations. The proposed model outperforms the state-of-the-art methods by achieving improved P@10, R@10, NDCG@10, and MAP scores.

Brain diseases, including tumors and mental and neurological disorders, seriously threaten the health and well-being of millions of people worldwide. Structural and functional neuroimaging modalities are commonly used by physicians to aid the diagnosis of brain diseases. In clinical settings, specialist doctors typically fuse the magnetic resonance imaging (MRI) data with other neuroimaging modalities for brain disease detection. As these two approaches offer complementary information, fusing these neuroimaging modalities helps physicians accurately diagnose brain diseases. Typically, fusion is performed between a functional and a structural neuroimaging modality. Because the functional modality can complement the structural modality information, thus improving the performance for the diagnosis of brain diseases by specialists. However, analyzing the fusion of neuroimaging modalities is difficult for specialist doctors. Deep Learning (DL) is a branch of artificial intelligence that has shown superior performances compared to more conventional methods in tasks such as brain disease detection from neuroimaging modalities. This work presents a comprehensive review paper in the field of brain disease detection from the fusion of neuroimaging modalities using DL models like convolutional neural networks (CNNs), recurrent neural networks (RNNs), pretrained, generative adversarial networks (GANs), and Autoencoders (AEs). First, neuroimaging modalities and the need for fusion are discussed. Then, review papers published in the field of neuroimaging multimodalities using AI techniques are explored. Moreover, fusion levels based on DL methods, including input, layer, and decision, with related studies conducted on diagnosing brain diseases, are discussed. Other sections present the most important challenges for diagnosing brain diseases from the fusion of neuroimaging modalities. In the discussion section, the details of previous research on the fusion of neuroimaging modalit

AbstractThe growth of population and the various intensive life pressures everyday deepen the competitions among people. Tens of millions of people each year suffer from depression and only a fraction receives adequate treatment. The development of social networks such as Facebook, Twitter, Weibo, and QQ provides more convenient communication and provides a new emotional vent window. People communicate with their friends, sharing their opinions, and shooting videos to reflect their feelings. It provides an opportunity to detect depression in social networks. Although depression detection using social networks has reflected the established connectivity across users, fewer researchers consider the data security and privacy-preserving schemes. Therefore, we advocate the federated learning technique as an efficient and scalable method, where it enables the handling of a massive number of edge devices in parallel. In this study, we conduct the depression analysis on the basis of an online microblog called Weibo. A novel algorithm termed as CNN Asynchronous Federated optimization (CAFed) is proposed based on federated learning to improve the communication cost and convergence rate. It is shown that our proposed method can effectively protect users' privacy under the premise of ensuring the accuracy of prediction. The proposed method converges faster than the Federated Averaging (FedAvg) for non-convex problems. Federated learning techniques can identify quality solutions of mental health problems among Weibo users.

Apnea is a sleep disorder that stops or reduces airflow for a short time during sleep. Sleep apnea may last for a few seconds and happen for many while sleeping. This reduction in breathing is associated with loud snoring, which may awaken the person with a feeling of suffocation. So far, a variety of methods have been introduced by researchers to diagnose sleep apnea, among which the polysomnography (PSG) method is known to be the best. Analysis of PSG signals is very complicated. Many studies have been conducted on the automatic diagnosis of sleep apnea from biological signals using artificial intelligence (AI), including machine learning (ML) and deep learning (DL) methods. This research reviews and investigates the studies on the diagnosis of sleep apnea using AI methods. First, computer aided diagnosis system (CADS) for sleep apnea using ML and DL techniques along with its parts including dataset, preprocessing, and ML and DL methods are introduced. This research also summarizes the important specifications of the studies on the diagnosis of sleep apnea using ML and DL methods in a table. In the following, a comprehensive discussion is made on the studies carried out in this field. The challenges in the diagnosis of sleep apnea using AI methods are of paramount importance for researchers. Accordingly, these obstacles are elaborately addressed. In another section, the most important future works for studies on sleep apnea detection from PSG signals and AI techniques are presented. Ultimately, the essential findings of this study are provided in the conclusion section. This article is categorized under: Technologies > Artificial Intelligence Application Areas > Data Mining Software Tools Algorithmic Development > Biological Data Mining.

Apnea is a sleep disorder that stops or reduces airflow for a short time during sleep. Sleep apnea may last for a few seconds and happen for many while sleeping. This reduction in breathing is associated with loud snoring, which may awaken the person with a feeling of suffocation. So far, a variety of methods have been introduced by researchers to diagnose sleep apnea, among which the polysomnography (PSG) method is known to be the best. Analysis of PSG signals is very complicated. Many studies have been conducted on the automatic diagnosis of sleep apnea from biological signals using artificial intelligence (AI), including machine learning (ML) and deep learning (DL) methods. This research reviews and investigates the studies on the diagnosis of sleep apnea using AI methods. First, computer aided diagnosis system (CADS) for sleep apnea using ML and DL techniques along with its parts including dataset, preprocessing, and ML and DL methods are introduced. This research also summarizes the important specifications of the studies on the diagnosis of sleep apnea using ML and DL methods in a table. In the following, a comprehensive discussion is made on the studies carried out in this field. The challenges in the diagnosis of sleep apnea using AI methods are of paramount importance for researchers. Accordingly, these obstacles are elaborately addressed. In another section, the most important future works for studies on sleep apnea detection from PSG signals and AI techniques are presented. Ultimately, the essential findings of this study are provided in the conclusion section. This article is categorized under: Technologies > Artificial Intelligence Application Areas > Data Mining Software Tools Algorithmic Development > Biological Data Mining.

Autism spectrum disorder (ASD) is a brain condition characterized by diverse signs and symptoms that appear in early childhood. ASD is also associated with communication deficits and repetitive behavior in affected individuals. Various ASD detection methods have been developed, including neuroimaging modalities and psychological tests. Among these methods, magnetic resonance imaging (MRI) imaging modalities are of paramount importance to physicians. Clinicians rely on MRI modalities to diagnose ASD accurately. The MRI modalities are non-invasive methods that include functional (fMRI) and structural (sMRI) neuroimaging methods. However, diagnosing ASD with fMRI and sMRI for specialists is often laborious and time-consuming; therefore, several computer-aided design systems (CADS) based on artificial intelligence (AI) have been developed to assist specialist physicians. Conventional machine learning (ML) and deep learning (DL) are the most popular schemes of AI used for diagnosing ASD. This study aims to review the automated detection of ASD using AI. We review several CADS that have been developed using ML techniques for the automated diagnosis of ASD using MRI modalities. There has been very limited work on the use of DL techniques to develop automated diagnostic models for ASD. A summary of the studies developed using DL is provided in the Supplementary Appendix. Then, the challenges encountered during the automated diagnosis of ASD using MRI and AI techniques are described in detail. Additionally, a graphical comparison of studies using ML and DL to diagnose ASD automatically is discussed. We suggest future approaches to detecting ASDs using AI techniques and MRI neuroimaging.

Apnea is a sleep disorder that stops or reduces airflow for a short time during sleep. Sleep apnea may last for a few seconds and happen for many while sleeping. This reduction in breathing is associated with loud snoring, which may awaken the person with a feeling of suffocation. So far, a variety of methods have been introduced by researchers to diagnose sleep apnea, among which the polysomnography (PSG) method is known to be the best. Analysis of PSG signals is very complicated. Many studies have been conducted on the automatic diagnosis of sleep apnea from biological signals using artificial intelligence (AI), including machine learning (ML) and deep learning (DL) methods. This research reviews and investigates the studies on the diagnosis of sleep apnea using AI methods. First, computer aided diagnosis system (CADS) for sleep apnea using ML and DL techniques along with its parts including dataset, preprocessing, and ML and DL methods are introduced. This research also summarizes the important specifications of the studies on the diagnosis of sleep apnea using ML and DL methods in a table. In the following, a comprehensive discussion is made on the studies carried out in this field. The challenges in the diagnosis of sleep apnea using AI methods are of paramount importance for researchers. Accordingly, these obstacles are elaborately addressed. In another section, the most important future works for studies on sleep apnea detection from PSG signals and AI techniques are presented. Ultimately, the essential findings of this study are provided in the conclusion section. This article is categorized under: Technologies > Artificial Intelligence Application Areas > Data Mining Software Tools Algorithmic Development > Biological Data Mining.

Parkinson's disease (PD) is the most common form of Parkinsonism, which is a group of neurological disorders with PD-like motor impairments. The disease affects over 6 million people worldwide and is characterized by motor and non-motor symptoms. The affected person has trouble in controlling movements, which may affect simple daily-life tasks, such as typing on a computer. We propose the application of a modified SqueezeNet convolutional neural network (CNN) for detecting PD based on the subject's key-typing patterns. First, the data are pre-processed using data standardization and the Synthetic Minority Oversampling Technique (SMOTE), and then a Continuous Wavelet Transformation is applied to generate spectrograms used for training and testing a modified SqueezeNet model. The modified SqueezeNet model achieved an accuracy of 90%, representing a noticeable improvement in comparison to other approaches.

Objective. Sleep apnea is a common sleep breathing disorder that can significantly decrease sleep quality and have major health consequences. It is diagnosed based on the apnea hypopnea index (AHI). This study explored a novel, generalized algorithm for the automatic diagnosis of sleep apnea employing airflow (AF) and oximetry (SpO2) signals.Approach. Of the 988 polysomnography records, 45 were randomly selected for developing the automatic algorithm and the remainder 943 for validating purposes. The algorithm detects apnea events by a per-sample encoding process applied to the peak excursion of AF signal. Hypopnea events were detected from the per-sample encoding of AF and SpO2with an adjustment to time lag in SpO2. Total recording time was automatically processed and optimized for computation of total sleep time (TST). Total number of detected events and computed TST were used to estimate AHI. The estimated AHI was validated against the scored data from the Sleep Heart Health Study.Main results. Intraclass correlation coefficient of 0.94 was obtained between estimated and scored AHIs. The diagnostic accuracies were 93.5%, 92.4%, and 96.6% for AHI cut-off values of ≥5, ≥15, and ≥30 respectively. The overall accuracy for the combined severity categories (normal, mild, moderate, and severe) and kappa were 83.4% and 0.77 respectively.Significance. This new automatic technique was found to be superior to the other existing methods and can be applied to any portable sleep devices especially for home sleep apnea tests.

Detecting pulmonary nodules early significantly contributes to the treatment success of lung cancer. Several deep learning models for medical image analysis have been developed to help classify pulmonary nodules. The design of convolutional neural network (CNN) architectures, however, is still heavily reliant on human domain knowledge. Manually designing CNN design solutions has been shown to limit the data’s utility by creating a co-dependency on the creator’s cognitive bias, which urges the development of smart CNN architecture design solutions. In this paper, an evolutionary algorithm is used to optimise the classification of pulmonary nodules with CNNs. The implementation of a genetic algorithm (GA) for CNN architectures design and hyperparameter optimisation is proposed, which approximates optimal solutions by implementing a range of bio-inspired mechanisms of natural selection and Darwinism. For comparison purposes, two manually designed deep learning models, FractalNet and Deep Local-Global Network, were trained. The results show an outstanding classification accuracy of the fittest GA-CNN (91.3%), which outperformed both manually designed models. The findings indicate that GAs pose advantageous solutions for diagnostic challenges, the development of which may to be fully automated in the future using GAs to design and optimise CNN architectures for various clinical applications.

Scoliosis is a 3D spinal deformation where the spine takes a lateral curvature, forming an angle in the coronal plane. Diagnosis of scoliosis requires periodic detection, and frequent exposure to radiative imaging may cause cancer. A safer and more economical alternative imaging, i.e., 3D ultrasound imaging modality, is being explored. However, unlike other radiative modalities, an ultrasound image is noisy, which often suppresses the image's useful information. Through this research, a novel hybridized CNN architecture, multi-scale feature fusion Skip-Inception U-Net (SIU-Net), is proposed for a fully automatic bony feature detection, which can be further used to assess the severity of scoliosis safely and automatically. The proposed architecture, SIU-Net, incorporates two novel features into the basic U-Net architecture: (a) an improvised Inception block and (b) newly designed decoder-side dense skip pathways. The proposed model is tested on 109 spine ultrasound image datasets. The architecture is evaluated using the popular (i) Jaccard Index (ii) Dice Coefficient and (iii) Euclidean distance, and compared with (a) the basic U-net segmentation model, (b) a more evolved UNet++ model, and (c) a newly developed MultiResUNet model. The results show that SIU-Net gives the clearest segmentation output, especially in the important regions of interest such as thoracic and lumbar bony features. The method also gives the highest average Jaccard score of 0.781 and Dice score of 0.883 and the lowest histogram Euclidean distance of 0.011 than the other three models. SIU-Net looks promising to meet the objectives of a fully automatic scoliosis detection system.

INTRODUCTION: Obstructive sleep apnea (OSA) can cause serious health problems such as hypertension or cardiovascular disease. The manual detection of apnea is a time-consuming task, and automatic diagnosis is much more desirable. The contribution of this work is to detect OSA using a multi-error-reduction (MER) classification system with multi-domain features from bio-signals. METHODS: Time-domain, frequency-domain, and non-linear analysis features are extracted from oxygen saturation (SaO2), ECG, airflow, thoracic, and abdominal signals. To analyse the significance of each feature, we design a two-stage feature selection. Stage 1 is the statistical analysis stage, and Stage 2 is the final feature subset selection stage using machine learning methods. In Stage 1, two statistical analyses (the one-way analysis of variance (ANOVA) and the rank-sum test) provide a list of the significance level of each kind of feature. Then, in Stage 2, the support vector machine (SVM) algorithm is used to select a final feature subset based on the significance list. Next, an MER classification system is constructed, which applies a stacking with a structure that consists of base learners and an artificial neural network (ANN) meta-learner. RESULTS: The Sleep Heart Health Study (SHHS) database is used to provide bio-signals. A total of 66 features are extracted. In the experiment that involves a duration parameter, 19 features are selected as the final feature subset because they provide a better and more stable performance. The SVM model shows good performance (accuracy = 81.68%, sensitivity = 97.05%, and specificity = 66.54%). It is also found that classifiers have poor performance when they predict normal events in less than 60 s. In the next experiment stage, the time-window segmentation method with a length of 60s is used. After the above two-stage feature selection procedure, 48 features are selected as the final feature subset that give good performance (accuracy = 90.80%, sensi

The brain-computer interface (BCI) has many applications in various fields. In EEG-based research, an essential step is signal denoising. In this paper, a generative adversarial network (GAN)-based denoising method is proposed to denoise the multichannel EEG signal automatically. A new loss function is defined to ensure that the filtered signal can retain as much effective original information and energy as possible. This model can imitate and integrate artificial denoising methods, which reduces processing time; hence it can be used for a large amount of data processing. Compared to other neural network denoising models, the proposed model has one more discriminator, which always judges whether the noise is filtered out. The generator is constantly changing the denoising way. To ensure the GAN model generates EEG signals stably, a new normalization method called sample entropy threshold and energy threshold-based (SETET) normalization is proposed to check the abnormal signals and limit the range of EEG signals. After the denoising system is established, although the denoising model uses the different subjects' data for training, it can still apply to the new subjects' data denoising. The experiments discussed in this paper employ the HaLT public dataset. Correlation and root mean square error (RMSE) are used as evaluation criteria. Results reveal that the proposed automatic GAN denoising network achieves the same performance as the manual hybrid artificial denoising method. Moreover, the GAN network makes the denoising process automatic, representing a significant reduction in time.

Lung cancer is the leading cause of cancer death worldwide. The critical reason for the deaths is delayed diagnosis and poor prognosis. With the accelerated development of deep learning techniques, it has been successfully applied extensively in many real-world applications, including health sectors such as medical image interpretation and disease diagnosis. By combining more modalities that being engaged in the processing of information, multimodal learning can extract better features and improve the predictive ability. The conventional methods for lung cancer survival analysis normally utilize clinical data and only provide a statistical probability. To improve the survival prediction accuracy and help prognostic decision-making in clinical practice for medical experts, we for the first time propose a multimodal deep learning framework for non-small cell lung cancer (NSCLC) survival analysis, named DeepMMSA. This framework leverages CT images in combination with clinical data, enabling the abundant information held within medical images to be associate with lung cancer survival information. We validate our model on the data of 422 NSCLC patients from The Cancer Imaging Archive (TCIA). Experimental results support our hypothesis that there is an underlying relationship between prognostic information and radiomic images. Besides, quantitative results show that our method could surpass the state-of-the-art methods by 4% on concordance.

The growth of population and the various intensive life pressures everyday deepen the competitions among people. Tens of millions of people each year suffer from depression and only a fraction receives adequate treatment. The development of social networks such as Facebook, Twitter, Weibo, and QQ provides more convenient communication and provides a new emotional vent window. People communicate with their friends, sharing their opinions, and shooting videos to reflect their feelings. It provides an opportunity to detect depression in social networks. Although depression detection using social networks has reflected the established connectivity across users, fewer researchers consider the data security and privacy-preserving schemes. Therefore, we advocate the federated learning technique as an efficient and scalable method, where it enables the handling of a massive number of edge devices in parallel. In this study, we conduct the depression analysis on the basis of an online microblog called Weibo. A novel algorithm termed as CNN Asynchronous Federated optimization (CAFed) is proposed based on federated learning to improve the communication cost and convergence rate. It is shown that our proposed method can effectively protect users' privacy under the premise of ensuring the accuracy of prediction. The proposed method converges faster than the Federated Averaging (FedAvg) for non-convex problems. Federated learning techniques can identify quality solutions of mental health problems among Weibo users.

Molecular communication is an emerging communication paradigm that allows bio-nanomachines to communicate using biochemical molecules as information carriers. It can be used in many promising biomedical applications such as the Internet of Bio-Nano Things (IoBNT) for targeted drug delivery and healthcare applications. In particular, the blood-tissue barrier inside the body forms the main communication pathway for molecular information exchange between the nanomachines as well as between the intra-body nanonetwork and the Bio-Cyber interface in the IoBNT network. However, overcoming this barrier by the molecules is one of the main challenges for molecular communication in the body. Therefore, spatiotemporal modeling of molecular communication across the blood-tissue barrier is of particular interest. In this paper, we develop a mathematical model and stochastic particle-based simulator for molecular communication over high spatiotemporal resolution between mobile bio-nanomachines in the blood capillary and the surrounding tissue. The transmitting bio-nanomachine is modeled as a moving sphere with a continuous emission pattern over a specific duration. In this work, the blood capillary characteristics including the blood-tissue barrier and blood flow are modelled and their effect is examined on the molecular received signal. In addition, we examined the impact of the emission duration, the elimination rate, and the separation distance on the molecular received signal. The numerical results are verified using the developed particle-based simulator. This work can help in the optimum design and development of the IoBNT systems based on molecular communication for biomedical applications such as smart drug delivery and health monitoring systems.

Accurate nuclear and cell segmentations plays an important role in improving the accuracy of target recognition in microscopic cell images. As the traditional SLIC (Simple Linear Iterative Clustering) algorithm cannot segment microscopic cell images well, an improved SLIC superpixel segmentation algorithm based on gray scale enhancement and regional equalization is proposed. According to the characteristics of microscopic cell images, selecting different transformation parameters with the conditional iterative algorithm, the best classification multi-threshold method based on maximum entropy criterion is used to nonlinearly enhance the gray scale of the original images, while enhancing the contrast of the image, it also greatly improves the balance of each classification region. Then the gray distance and spatial distance are calculated respectively in the circle neighborhood of the cluster center to realize the superpixel segmentation of the image. Finally, the improved SLIC algorithm and the comparison algorithm are tested and evaluated. The experimental results show that our improved SLIC algorithm model has higher segmentation accuracy and is more suitable for cell segmentation in microscopic cell images than original SLIC algorithm.

Volume Projection Imaging from ultrasound data is a promising technique to visualize spine features and diagnose Adolescent Idiopathic Scoliosis. In this paper, we present a novel multi-task framework to reduce the scan noise in volume projection images and to segment different spine features simultaneously, which provides an appealing alternative for intelligent scoliosis assessment in clinical applications. Our proposed framework consists of two streams: 1) A noise removal stream based on generative adversarial networks, which aims to achieve effective scan noise removal in a weakly-supervised manner, i.e., without paired noisy-clean samples for learning; 2) A spine segmentation stream, which aims to predict accurate bone masks. To establish the interaction between these two tasks, we propose a selective feature-sharing strategy to transfer only the beneficial features, while filtering out the useless or harmful information. We evaluate our proposed framework on both scan noise removal and spine segmentation tasks. The experimental results demonstrate that our proposed method achieves promising performance on both tasks, which provides an appealing approach to facilitating clinical diagnosis.

Automatic spine segmentation, based on ultrasound volume projection imaging (VPI), is of great value in clinical applications to diagnose scoliosis in teenagers. In this paper, we propose a novel framework to improve the segmentation accuracy on spine images via structure-enhanced attentive learning. Since the spine bones contain strong prior knowledge of their shapes and positions in ultrasound VPI images, we propose to encode this information into the semantic representations in an attentive manner. We first revisit the self-attention mechanism in representation learning, and then present a strategy to introduce the structural knowledge into the key representation in self-attention. By this means, the network explores both the contextual and structural information in the learned features, and consequently improves the segmentation accuracy. We conduct various experiments to demonstrate that our proposed method achieves promising performance on spine image segmentation, which shows great potential in clinical diagnosis.

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.

Neuron image segmentation has wide applications and important potential values for neuroscience research. Due to the complexity of the submicroscopic structure of neurons cells and the defects of the image quality such as anisotropy, boundary loss and blurriness in electron microscopy-based (EM) imaging, and one faces a challenge in efficient automated segmenting large-scale neuron image 3D datasets, which is an essential prerequisite front-end process for the reconstruction of neuron circuits. Here, a neuron image segmentation method by combining Chan-Vest (CV) model with Deep Boltzmann Machine (DBM) is proposed, and a generative model is used to model and generate the target shape, it take this as a prior information to add global target shape feature constraint to the energy function of CV model, and the shape priori information is fused to assist neuron image segmentation. We applied our method to two 3D-EM datasets from different types of nerve tissue and achieved the best performance consistently across two classical evaluation metrics of neuron segmentation accuracy, namely Variation of Information (VoI) and Adaptive Rand Index (ARI). Experimental results show that the fusion algorithm has high segmentation accuracy, strong robustness, and can characterize the sub-microstructure information of neuron images well.

The history of medicine shows that myocardial infarction is one of the significant causes of death in humans. The rapid evolution in autonomous technologies, the rise of computer vision, and edge computing offers intriguing possibilities in healthcare monitoring systems. The major motivation of the work is to improve the survival rate during a cardiac arrest through an automatic emergency recognition system under ambient intelligence. We present a novel approach to chest pain and fall posture-based vital sign detection using an intelligence surveillance camera to address the emergency during myocardial infarction. A real-time embedded solution persuaded from "edge AI"is implemented using the state-of-the-art convolution neural networks: single shot detector Inception V2, single shot detector MobileNet V2, and Internet of Things embedded GPU platform NVIDIA's Jetson Nano. The deep learning algorithm is implemented for 3000 indoor color image datasets: Nanyang Technological University Red Blue Green and Depth, NTU RGB + D dataset, and private RMS dataset. The research mainly pivots on two key factors in creating and training a CNN model to detect the vital signs and evaluate its performance metrics. We propose a model, which is cost-effective and consumes low power for onboard detection of vital signs of myocardial infarction and evaluated the metrics to achieve a mean average precision of 76.4% and an average recall of 80%.

Scoliosis is a widespread medical condition where the spine becomes severely deformed and bends over time. It mostly affects young adults and may have a permanent impact on them. A periodic assessment, using a suitable modality, is necessary for its early detection. Conventionally, the usually employed modalities include X-ray and MRI, which employ ionising radiation and are expensive. Hence, a non-radiating 3D ultrasound imaging technique has been developed as a safe and economic alternative. However, ultrasound produces low-contrast images that are full of speckle noise, and skilled intervention is necessary for their processing. Given the prevalent occurrence of scoliosis and the limitations of scalability of human expert interventions, an automatic, fast, and low-computation assessment technique is being developed for mass scoliosis diagnosis. In this paper, a novel hybridized light-weight convolutional neural network architecture is presented for automatic lateral bony feature identification, which can help to develop a fully-fledged automatic scoliosis detection system. The proposed architecture, Light-convolution Dense Selection U-Net (LDS U-Net), can accurately segment ultrasound spine lateral bony features, from noisy images, thanks to its capabilities of smartly selecting only the useful information and extracting rich deep layer features from the input image. The proposed model is tested using a dataset of 109 spine ultrasound images. The segmentation result of the proposed network is compared with basic U-Net, Attention U-Net, and MultiResUNet using various popular segmentation indices. The results show that LDS U-Net provides a better segmentation performance compared to the other models. Additionally, LDS U-Net requires a smaller number of parameters and less memory, making it suitable for a large-batch screening process of scoliosis without a high computational requirement.

Objective

Approach

Main results

Significance

Particle Swarm Optimization (PSO) algorithm is a member of the swarm computational family and widely used for solving nonlinear optimization problems. But, it tends to suffer from premature stagnation, trapped in the local minimum and loses exploration capability as the iteration progresses. On the contrary, Gravitational Search Algorithm (GSA) is proficient for searching global optimum, however, its drawback is its slow searching speed in the final phase. To overcome these problems in this paper a novel Hybrid Gravitational Search Particle Swarm Optimization Algorithm (HGSPSO) is presented. The key concept behind the proposed method is to merge the local search ability of GSA with the capability for social thinking (gbest) of PSO. To examine the effectiveness of these methods in solving the abovementioned issues of slow convergence rate and trapping in local minima five standard and some modern CEC benchmark functions are used to ensure the efficacy of the presented method. Additionally, a DNA sequence problem is also solved to confirm the proficiency of the proposed method. Different parameters such as Hairpin, Continuity, H-measure, and Similarity are employed as objective functions. A hierarchal approach was used to solve this multi-objective problem where a single objective function is first obtained through a weighted sum method and the results were then empirically validated. The proposed algorithm has demonstrated an extraordinary performance per solution stability and convergence.

3D ultrasound imaging has become one of the common diagnosis ways to assess scoliosis since it is radiation-free, real-time, and low-cost. Spine curvature angle measurement is an important step to assess scoliosis precisely. One way to calculate the angle is using the vertebrae features of the 2-D coronal images to identify the most tilted vertebrae. To do the measurement, the segmentation of the transverse vertebrae is an important step. In this paper, we propose a dual-task ultrasound transverse vertebrae segmentation network (D-TVNet) based on U-Net. First, we arrange an auxiliary shape regularization network to learn the contour segmentation of the bones. It improves the boundary segmentation and anti-interference ability of the U-Net by fusing some of the features of the auxiliary task and the main task. Then, we introduce the atrous spatial pyramid pooling (ASPP) module to the end of the down-sampling stage of the main task stream to improve the relative feature extraction ability. To further improve the boundary segmentation, we extendedly fuse the down-sampling output features of the auxiliary network in the ASPP. The experiment results show that the proposed D-TVNet achieves the best dice score of 86.68% and the mean dice score of 86.17% based on cross-validation, which is an improvement of 5.17% over the baseline U-Net. An automatic ultrasound spine bone segmentation network with promising results has been achieved.

Ultrasound volume projection imaging (VPI) has shown to be appealing from a clinical perspective, because of its harmlessness, flexibility, and efficiency in scoliosis assessment. However, the limitations in hardware devices degrade the resultant image content with strong structured noise. Owing to the unavailability of reference data and the unpredictable degradation model, VPI image recovery is a challenging problem. In this paper, we propose a novel framework to learn the structured noise removal from unpaired samples. We introduce the attention mechanism into the generative adversarial network to enhance the learning by focusing on the salient corrupted patterns. We also present a dual adversarial learning strategy and integrate the denoiser with a segmentation model to produce the task-oriented noiseless estimation. Experimental results show that the proposed method can improve both the visual quality and the segmentation accuracy on spine images.

Periodic inspection and assessment are important for scoliosis patients. 3D ultrasound imaging has become an important means of scoliosis assessment as it is a real-time, cost-effective and radiation-free imaging technique. With the generation of a 3D ultrasound volume projection spine image using our Scolioscan system, a series of 2D coronal ultrasound images are produced at different depths with different qualities. Selecting a high quality image from these 2D images is the crucial task for further scoliosis measurement. However, adjacent images are similar and difficult to distinguish. To learn the nuances between these images, we propose selecting the best image automatically, based on their quality rankings. Here, the ranking algorithm we use is a pairwise learning-to-ranking network, RankNet. Then, to extract more efficient features of input images and to improve the discriminative ability of the model, we adopt the convolutional neural network as the backbone due to its high power of image exploration. Finally, by inputting the images in pairs into the proposed convolutional RankNet, we can select the best images from each case based on the output ranking orders. The experimental result shows that convolutional RankNet achieves better than 95.5% top-3 accuracy, and we prove that this performance is beyond the experience of a human expert.

© 2020, Springer Science+Business Media, LLC, part of Springer Nature. The gravitational search algorithm (GSA) is a novel optimization technique that relies upon the law of motion and law of gravity of masses to describe the interaction between the agents. The GSA has shown outstanding performance but suffers from the drawback of a slow process due to the dependence of the fitness function on the masses of the agents. As a result, after each iteration, the masses get heavier, restricting their movement. Due to this effect, the masses cancel out the gravitational forces on each other, preventing them from finding the optimum quickly. To overcome this limitation, an improved GSA based on a modified exploitation strategy is proposed herein. The primary aim of this modification is to enhance the performance of the algorithm in terms of faster convergence and avoidance of premature convergence. An electromagnetic optimization problem is used to validate the performance of the presented method. The simulation results confirm that the proposed method provides outstanding results in solving Loney’s solenoid design problem and that the stability of the solution is much better compared with those obtained using the standard gravitational search algorithm or various other state-of-the-art techniques that have previously been applied to solve this problem.

To solve the real-time complex mission-planning problem for Multiple heterogeneous Unmanned Aerial Vehicles (UAVs) in the dynamic environments, this paper addresses a new approach by effectively adapting the Consensus-Based Bundle Algorithms (CBBA) under the constraints of task timing, limited UAV resources, diverse types of tasks, dynamic addition of tasks, and real-time requirements. We introduce the dynamic task generation mechanism, which satisfied the task timing constraints. The tasks that require the cooperation of multiple UAVs are simplified into multiple sub-tasks to perform by a single UAV independently. We also introduce the asynchronous task allocation mechanism. This mechanism reduces the computational complexity of the algorithm and the communication time between UAVs. The partial task redistribution mechanism has been adopted for achieving the dynamic task allocation. The real-time performance of the algorithm is assured on the premise of optimal results. The feasibility and real-time performance of the algorithm are validated by conducting dynamic simulation experiments.

Computer-aided algorithm plays an important role in disease diagnosis through medical images. As one of the major cancers, lung cancer is commonly detected by computer tomography. To increase the survival rate of lung cancer patients, an early-stage diagnosis is necessary. In this paper, we propose a new structure, multi-level cross residual convolutional neural network (ML-xResNet), to classify the different types of lung nodule malignancies. ML-xResNet is constructed by three-level parallel ResNets with different convolution kernel sizes to extract multi-scale features of the inputs. Moreover, the residuals are connected not only with the current level but also with other levels in a crossover manner. To illustrate the performance of ML-xResNet, we apply the model to process ternary classification (benign, indeterminate, and malignant lung nodules) and binary classification (benign and malignant lung nodules) of lung nodules, respectively. Based on the experiment results, the proposed ML-xResNet achieves the best results of 85.88% accuracy for ternary classification and 92.19% accuracy for binary classification, without any additional handcrafted preprocessing algorithm.

Sleep apnea is a common sleep disorder that can significantly decrease the quality of life. An accurate and early diagnosis of sleep apnea is required before getting proper treatment. A reliable automated detection of sleep apnea can overcome the problems of manual diagnosis (scoring) due to variability in recording and scoring criteria (for example across Europe) and to inter-scorer variability. This study explored a novel automated algorithm to detect apnea and hypopnea events from airflow and pulse oximetry signals, extracted from 30 polysomnography records of the Sleep Heart Health Study. Apneas and hypopneas were manually scored by a trained sleep physiologist according to the updated 2017 American Academy of Sleep Medicine respiratory scoring rules. From pre-processed airflow, the peak signal excursion was precisely determined from the peak-to-trough amplitude using a sliding window, with a per-sample digitized algorithm for detecting apnea and hypopnea. For apnea, the peak signal excursion drop was operationalized at ≥85% and for hypopnea at ≥35% of its pre-event baseline. Using backward shifting of oximetry, hypopneas were filtered with ≥3% oxygen desaturation from its baseline. The performance of the automated algorithm was evaluated by comparing the detection with manual scoring (a standard practice). The sensitivity and positive predictive value of detecting apneas and hypopneas were respectively 98.1% and 95.3%. This automated algorithm is applicable to any portable sleep monitoring device for the accurate detection of sleep apnea.

Scoliosis is a 3D spinal deformation where the spine takes a lateral curvature, which generates an angle in a coronal plane. For periodic detection of scoliosis, safe and economic imaging modality is needed as continuous exposure to radiative imaging may cause cancer. 3D ultrasound imaging is a cost-effective and radiation-free imaging modality which gives volume projection image. Identification of mid-spine line using manual, semi-automatic and automatic methods have been published. Still, there are some difficulties like variations in human measurement, slow processing of data associated with them. In this paper, we propose an unsupervised ground truth generation and automatic spine curvature segmentation using U- Net. This approach of the application of Convolutional Neural Network on ultrasound spine image, to perform automatic detection of scoliosis, is a novel one.