Hyperparameter optimization plays a crucial role in maximizing the performance of Deep Learning (DL) models, particularly in the medical field. In this study, we propose a novel hybrid approach called GS-TPE, which combines Grid Search (GS) and Tree Parzen Estimator (TPE) for optimizing the hyperparameters of DL architectures in order to enhance the vigilance states classification from the EEG signals. Our experiments demonstrate that the GS-TPE approach competes with the state of the art on multiple performance metrics, leading to significantly improved classification results. The obtained accuracy with combined one-Dimensional Convolutional Neural Network and Long Short-Term Memory (1D-CNN-LSTM) and with combined Auto-Encoder and LSTM (AE-LSTM) architectures reach 93.74 and 93.53%, respectively. The proposed GS-TPE approach shows great promise for advancing the field of medical signal analysis and enhancing the accuracy of EEG-based diagnostic systems.

This study investigates the dynamic causal connectivity between EEG and ECG signals in patients with Temporal Lobe Epilepsy (TLE), emphasizing temporal and frequency analyses during pre-ictal and inter-ictal periods. Employing Granger causality, the research uncovers significant bidirectional causal relations, with a particularly robust causal effect observed in the direction of the brain influencing the heart. Analyzing various EEG frequency bands on the ECG signal across different electrodes in TLE patients reveals distinctive patterns. Results indicate a substantial increase in the causal effect of the EEG on the ECG during the pre-ictal period compared to the inter-ictal period. These findings provide valuable insights into the complex interactions between brain and heart signals in TLE, underscoring the dynamic nature of these interactions.

The retinal vascular tree (RVT) is crucial for the diagnosis of various ophthalmological diseases. Efficient segmentation of the RVT with reduced runtime is essential for clinical purposes. Recently, convolutional neural networks (CNNs) have been used for RVT segmentation. However, these architectures typically apply fixed and standard size of convolution kernels for all blocks, which may be unsuitable for accurately capturing vessel scales. In addition, these kernels are applied using 3D convolution layers across all channel depths, leading to higher computational complexity. In this work, we propose a novel deep learning architecture. The main contribution consists of performing a convolution processing where kernel size is chosen with respect to vessel scale variation, in order to enhance the quality of the segmentation of vascular trees. In addition, the convolution processing is insured through several layers with 2D kernels, to reduce the computational complexity. The proposed architecture is evaluated on DRIVE database reaching an average accuracy and sensitivity respectively in the order of 97.69%and 91.69% in 0.75 second per fundus image.

Advancements in deep learning algorithms for medical imaging, combined with the integration of cyberworlds, have shown great promise in providing precise diagnostic results. One area of interest is the application of these advancements in enhancing personalized treatment of gliomas, a particularly challenging type of brain tumor, by providing more reliable information on a clinical biomarker Oxygen 6-methylguanineDNA methyltransferas (MGMT). To achieve accurate results, a MobileNetV2 model was employed, utilizing transfer learning method and a mechanism spatial attention with correlation was added to further enhance the model’s performance. The model was trained using a private dataset of annotated images and evaluated using cross-validation. Results showed high precision and recall in predicting MGMT status, indicating its potential to improve the efficiency of this prediction. The model’s ability to predict MGMT promoter methylation status can help clinicians make more informed decisions, which has the potential to improve personalized treatment planning, ultimately leading to better patient outcomes.

Lung cancer remains a significant global cause of mortality, affecting populations worldwide. Deep Learning (DL) systems show promise in early detection using clinical data to reduce mortality rates. However, these systems heavily rely on large amounts of annotated anomalous data, and heavily depends on selecting appropriate hyperparameters that define the network’s structure and learning process.In this study, we propose an optimization scheme based on Tree Parzen Estimator (TPE) and Bayesian optimization (BO) algorithms for hyperparameter optimization in unsupervised lung cancer detection. First, we used a fast residual attention GAN-based model. Then, we employed the Mixup consistency regularization technique to encourage the discriminator to attend the pixel-level details of the input data. Furthermore, a new cost function for the discriminator is defined based on the mixup to enhance the output. This study is evaluated in the context of lung cancer detection. When compared to empirical optimization, both TPE and Bayesian optimization demonstrate significant improvements in the precision of the fast Residual Attention GAN model used in this study. Various metrics, including precision, f1-score, and the area under the curve (AUC) are employed to assess the system’s efficiency.

The Retinal Vascular Tree (RVT) segmentation is required to diagnose various ocular pathologies.Recently, fundus images are acquired with higher resolution, which allows representing a large range of vessel thickness.However, standard Deep Learning (DL) architectures with static and small convolution size have failed to achieve higher segmentation performance.In this paper, we propose a novel DL architecture for RVT segmentation dedicated for high resolution fundus images.The idea consists at extending the U-net architecture by increasing (e.g.decreasing) convolution kernel size through convolution blocs, in correlation with downscale (e.g.upscale) of feature map dimensions.The proposed architecture is validated on HRF database, where average sensitivity is increased from 56% to 84%.

Knee osteoarthritis (KOA) is a debilitating disease that greatly impacts the quality of life, particularly among the elderly population. Conventional subjective assessment methods for KOA have limitations in terms of accuracy and objective diagnosis. This paper proposes an innovative approach by integrating advanced technologies, specifically the Spatio-Temporal Graph Convolutional Network (STGCN), applied to gait analysis from markerless videos, for precise and quantitative assessment of KOA. The STGCN network is applied to normalized data obtained from Blazepose, a markerless pose estimation technique. Evaluated on an academic dataset of 80 RGB videos, it provides an accuracy of 93.75%. By leveraging the capabilities of the STGCN network, this study significantly enhances the classification of KOA based on gait patterns, offering promising prospects for improved diagnosis and treatment strategies for individuals with KOA.

Accurate segmentation of blood vessels can make an important and effective contribution to the identification and diagnosis of ocular diseases such as diabetic retinopathy, glaucoma, and hypertension. Contrast enhancement is an essential component of any retinal blood vessel segmentation process. The consistency of contrast within an image will define the reliability of the segmentation. A new approach to dynamic segmentation of retinal blood vessels is proposed in this paper. Preprocessing, vessel segmentation, and post-processing are the three main stages of this method. The enhancement technique was integrated with dynamic preprocessing to improve segmentation performance. The DRIVE database was used to test the proposed method and analyze the results. The experimental results confirmed an improvement in segmentation where the use of dynamic processing increased the accuracy from 91.65% to 93.23%.

The number of LoRaWAN networks have grown worldwide last years, offering a solution for the integration of the Internet of Things in rural and urban areas. After years of development, several performance issues and scalability limitations require to be enhanced for LoRa such as high collision rates and duty cycle limitations. Machine learning offers a chance for LoRaWAN to rise as the reference communication technology that offers the adequate communication performances for IoT. In this paper, our goal is to optimize the LoRaWAN network performances using detection mechanism and artificial intelli-gence to predict its behavior. first, we evaluate the full potential of the LoRaWAN factory setting, and we introduced a Quality of Service demanding application. Second, we constructed our proper database using available application criteria, we included a quality of service mechanism to simulate the effect of a new application connecting to a stable network and the perturbing causes. Then, we used two different methods one for classification, the second for prediction, and then the optimization. For clas-sification using Auto-Regressive and optimization it using burg algorithm and firefly algorithm, then we used the support vector machine for traffic classification, results are very promising, we were able to detect normal traffic, a normal surge, and an abnormal surge of network traffic with up to 99% accuracy. For prediction, we used a new algorithm developed by google Temporal Fusion Transformer. We were able to predict the network behaviour ahead with 14 days with 95% accuracy and up to 30 days with 80% accuracy. We were able to optimize the network to absorb the abnormal surge and return to normal in less than 60% of the normal time, uplifting the packet delivery ratio for uplink traffic by 20% and downlink traffic by 50%.

Abstract The present work develops a novel hybrid method for ocular and muscular artifact removal from electroencephalography (EEG) signals, EFICA-TQWT. It is a combination of efficient fast independent component analysis (EFICA) method with the tunable Q-factor wavelet transform (TQWT). The main contribution of this paper is to apply the 3D interpolation method in the filtering system. Three EEG datasets are used in this work, two healthy and one epileptic. The choice of subjects for each dataset is made with the help of an expert in physiology. The selection criterion adopted is the presence of muscular and ocular artifacts in the processed recordings. First, a noisy channel automatic classification is performed by the support vector machine (SVM) with radial basis function in order to delete the signal(s) corresponding to the noisiest channel(s) from each EEG recording. The results of the automatic classification by the SVM were compared with those found by the expert’s classification. An accuracy of 97.45%, a sensitivity of 86.66% and a 100% specificity are provided by the SVM classification. The hybrid method of artifact removal will be applied on the rest of the EEG channels of international 10/20 system for each subject. Then, a reconstruction of the eliminated channel signal(s) will be performed in order to obtain a well-filtered signal. The proposed filtering process is evaluated by calculating the mean squared error (MSE) and the signal to noise ratio (SNR). Both for the healthy and pathological EEG datasets, a comparative study of the proposed method (EFICA-TQWT) and other filtering techniques (Fast-ICA, DWT, TQWT and EFICA) is generated. The EFICA-TQWT method gave the best results with a minimum of MSE and a maximum of SNR, more particularly in the case of the application of the 3D interpolation method. Besides, in order to optimize the computing time of the proposed system, a parallel implementation of this filtering system is developed based on graphical processing units using compute unified device architecture.

The cardiac right ventricle has a vital role in the cardiac cycle. To assess its function using Magnetic Resonance Imaging (MRI), the segmentation is an important task, but it is challenged by the complex shape of this cavity, its thin borders, and shape variability. Accordingly, several approaches have been proposed to overcome these issues. Yet, a significant divergence of precision still appears among the spatial slices. In this paper, we attempt to study the impact of short-axis slices from base to apex on the segmentation process. First, a comparative study is enabled to assess the segmentation quality among these slices using a U-Net- based convolutional neural network. Two public labelled datasets are exploited with our prepared data to allow the training process. The dice-coefficient assessment of each slice-level exhibits a significant accuracy decrease for the basal and apical slices. Next, a personalized investigation is carried out for each slice level apart. Accordingly, three sub-sets are retrieved from the initial training set regrouping slices into basal, central, and apical. Furthermore, to monitor the segmentation behaviour using these sub-datasets, different U-Net-based models are trained and evaluated. The obtained results show that the central slices scores enhanced from 0.87 to 0.92 using slice-level based. On the other hand, basal and apical slices obtained higher results using the global dataset.

Over the past few years, osteoarthritis is one of the most common knee diseases. The diagnosis and treatment of this disease is a vital importance. Furthermore, Deep Learning (DL) approaches have shown a good performance in learning the high-level features and in resolving segmentation issues. In this paper, we propose a new model of DL 3D-Res-UNet in order to accurately segment the knee cartilage from a Magnetic Resonance Imaging (MRI) 3D construction that allows perfectly visualizing the anatomical structure of this organ. This model is a combination of an architecture widely known in the literature for its segmentation efficiency (3D-UNet) with a residual architecture (3D-ResNet). The experimental results reveal that the suggested model can stabilize the training model, segment the cartilage from MRI very well and compete with the state of art on multiple performance metrics. The gain of precision and recall with 3DRes-UNet is given up to 15% and 26% compared to 3D-ResNet and 3D-UNet, respectively, hence the effectiveness of the suggested method.

In conventional X-ray coronary angiography, accurate coronary artery segmentation is a crucial and challenging step in the assessment of coronary artery disease.In this paper, we propose a new architecture (CAS-Net) for coronary artery segmentation.It is based on Residual U-Net and it includes both channel and spatial attention mechanism in the center part to generate hierarchical rich features of coronary arteries.Experiments are conducted on a private dataset of 150 images.The results show that CAS-Net outperforms the state-of-the-art methods achieving the highest accuracy of 96.91% and Dice of 82.70%.

Abstract The right ventricular assessment is crucial to heart disease diagnosis. Unfortunately, its segmentation is quite challenging due to its intricate shape, ill‐defined thin edges, large variability among patients, and pathologies. Besides, it is a very laborious and time‐consuming task to be done manually. Therefore, automated segmentation techniques are very suitable to reduce the strain on the expert. Here, it is attempted to review the taxonomy of the current RV segmentation approaches adopted to handle the afore‐mentioned issues. Enhanced by our expert's interpretation, the results of over forty research papers were evaluated based on several metrics such as the dice metric and the Hausdorff distance. Synthetic tables and charts were also used to discuss the reviewed approaches. The following study shows that none of the existing methods has proved accurate enough to meet all the RV challenging issues. Many misestimated results were reported for several cases. Eventually, global guidance is outlined, which supports combining different methods to enhance the expected results during the MRI short‐axis slice processing.

The Diabetic Retinopathy (DR) is a worldwide eye disease that causes visual damages and can leads to blindness. Therefore, the detection of the DR in the early stages is highly recommended. However, a delay is registered for ensuring early DR diagnosis which caused by the low-rate of the ophthalmologists, the deficiency of diagnosis equipment and the lack of mobility of elderly patients. In this paper, the main objective is to provide a mobile-aided screening system of moderate DR. Within this aim, we propose a classifier-based method which is based on detecting the Hard Exudate (HE) lesions that occur in moderate DR stage. A set of features are extracted to ensure an accurate and robust detection with respect to modest quality of fundus images. Moreover, the detection is provided in a low complexity processing to be suitable for mobile device. The aimed system corresponds to the implementation of the method on a smartphone associated to an optical lens for capturing fundus image. The system reached satisfactory screening performance where an accuracy of 98.36%, a sensitivity of 100% and specificity of 96.45% are registered using the DIARETDB1 fundus image databases. Moreover, the screening is performed in an average execution time of 2.68 seconds.

The LoRaWAN technology is today the object of great interest in the Internet of Things context. It defines a simple network architecture offering a wide-area wireless coverage for low rate IoT applications with low power consumption for devices. The LoRaWan class A is designed for sensor networks with a focus on the uplink. LoRaWan defines an optional MAC operation, Class B, that provides the network server with the opportunities to initiate a downlink, which can be a real solution for actuators focus network. Today, Performances of Class B are not quantified and compared to default LoRaWAN class. In this paper, we propose an evaluation of Class B performance. We offer a set of realistic evaluation scenarios based on an NS-3 simulation module that we have developed for this purpose. Results show that Class B reduces the delivery delay of downlink traffic in comparison to Class A. Class B operation significantly reduces the percentage of packet loss for downlink traffic even in congested contexts. We conclude that a trade off should be made between having low access delay or packet loss. Both the NS-3 module and data are released as an open-source to the research community.

Magnetic resonance imaging (MRI) has emerged as the golden reference for cardiac examination. This modality allows the assessment of human cardiovascular morphology, functioning, and perfusion. Although a couple of challenging issues, such as the cardiac magnetic resonance (MR) image's features and the large variability of images among several patients, still influences the cardiac cavities’ segmentation and needs to be carried out. In this study, the authors have profoundly reviewed and fully compared semi‐automated segmentation methods performed on cardiac cine‐MR short‐axis images for the evaluation of the left ventricular functions. However, the number of parameters handled by the synthesised works is limited if not null. For the sake of ensuring the highest coverage of the left ventricle parameters computing, they have introduced a parallel watershed‐based approach to segment the left ventricular allowing hence the computation of six parameters (end‐diastolic volume, end‐systolic volume, ejection fraction, cardiac output, stroke volume, and left ventricular mass). An algorithm is associated with the main considered measurements. The experimental results that were obtained through studying 20 patients’ MRI data base demonstrate their approach's accuracy in estimating real values of the parameters’ set thanks to a faithful segmentation of the myocardium.

In this work, a scalable and adaptable hardware SOM architecture allowing to execute multiple applications in parallel is presented. The proposed architecture allows to use simultaneously multiple SOM structures with different parameters in order to satisfy multiple applications with different needs. The application switching is done within a clock cycle at the neuron’s level at run time only by analyzing the received input data. The proposed architecture was tested and validated in an image quantization experiment where 6 quantization applications with different parameters (from 6 × 6 to 15 × 15 SOMs with inputs varying from 3 to 12 elements) were performed simultaneously.

In this paper, electrocardiogram (ECG) analyses were used as valuable a tool in the evaluation of cognitive tasks also given by the electroencephalograms (EEG). By taking and analyzing measurements in large quantities, we tried to better understand the functioning of human physiological systems. This study examined the cognitive and cardiovascular system function simultaneously. The purpose of this paper was to seek statistical causality in the sense of Granger between the EEG and ECG signals based on time series and autoregressive vector processes (VAR). For this purpose, 24 hours were recorded and during the tests, random and non-stationary portions of the ECG and EEG were extracted. The results indicated that there was Granger causality between the signals. This allowed us to forecast and predict traffic spots within and between the ECG and EEG signals.

In this work, a new method for removal of ocular and muscular artifacts from Multi-channel electroencephalogram (EEG) is presented in order to obtain a 3D filtered cerebral mapping images. First, a FastICA algorithm of Independent Component Analysis (ICA) is applied in combination with the tunable Q-factor wavelet transform (TQWT), FastICA-TQWT. Then, to show the robustness of this method, a comparison was made between the proposed FastICA-TQWT method and the classical one FastICA-DWT based on three criteria: Mean Squared Error (MSE), correlation coefficient and Signal Noise Ratio (SNR). The results showed that the FastICA-TQWT method gave the highest Signal Noise Ratio and correlation coefficient and the minimum Mean Squared Error. However, the FastICA-TQWT algorithm requires an extremely high computing power. Therefore, the second contribution of this paper is to provide an EEG signal treatment by implementing the hybrid FastICA-TQWT algorithm using a new computing technology designed for a high-performance computing, called Graphical Processing Units (GPUs) using the Compute Unified Device Architecture (CUDA) technology. The performance of the parallel approach running along the GPU was compared to a CPU implementation.

Heart rates have normal values ranging from 60 to 80 beats per minute (bpm) for adults. RR distances have normal durations between 0.75 and 1 second. The complexes QRS durations have normal durations of less than 0.1 second. However, heart rate and RR distances also depend on age (adult or child), the patient's status (rest or stress), sex (male or female) and the patient's conditions (healthy or pathological). Heart rates, RR distances and QRS durations are not sufficient to determine whether ECGs are normal or pathological. Recently, two novel metrics have been calculated to reflect the regularity of RR distances and the QRS complexes durations irrespective of the patient's age, sex and heart rate. In this paper, these novel parameters were tested and validated on the arrhythmia (MIT-BIH), Abdominal and Direct Fetal ECG (ADFECGDB) and BIDMC Congestive Heart Failure (CHFDB) databases.

In this paper we present a new architectural approach of a Self-Organizing Map (SOM). The proposed architecture, called Systolic-SOM (SSOM), is based on a generic formalism that exploits two levels of nested parallelism of neurons and connections. Thus, this solution provides a distributed set of independent computations between the neuroprocessors that define the SSOM architecture. To validate our approach, we evaluate the performance of several SOM network architectures after their integration on FPGA support. This architecture has achieved a performance almost twice as fast as that obtained in recent literature.

This paper presents an optimizing methodology for the implementation of a Learning Vector Quantization (LVQ) Artificial Neural Network (ANN). Starting from a highlevel algorithmic specification, we suggest a design methodology of the LVQ-dedicated architecture. Our approach is based on the creation of partially parallel architectures to optimize the performance of our ANN for different topologies. In this manuscript, we used parallelism for the supervisor part of the application, which is responsible for calculating minimum distances, weights and labels, to solve the problems of application delay and the power consumed. In this work we integrate the Partial Dynamic Reconfiguration (PDR) to facilitate the use of different architectures by the user. The latter can implement the architecture and performance that suits their need. Therefore, our approach has reduced the latency of parallel architectures with respect to the sequential architecture of an LVQ for variable topologies. To validate our approach, the optimized LVQ implementation was tried on the Zynq device.

Watershed transform is widely used in image segmentation. In literature, this transform is computed by various algorithms among which the M-border kernel algorithm [1]. This algorithm computes the watershed transform in the framework of edge weighted graphs. It is based on a local property that makes it adapted to parallelization. In this paper we propose a parallel implementation of this algorithm. We start by studying the data dependencies problematic that it raises. We give then an approach that allows overcoming this problematic based on an alternated edges processing strategy. The implementation of this strategy on a shared memory multicore architecture using a Single Program Multiple Data (SPMD) approach proves its effectiveness. In fact, experimental results show that our implementation achieves a relative speedup factor of 2.8 using 4 processors over the performance of the sequential algorithm using a single processor on the same system.

Image processing technology has grown significantly over the past decade. Its application on low-power mobile devices has been the interest of a wide research group related to newly emerging contexts such as augmented reality, visual search, object recognition, and so on. With the emergence of general-purpose computing on embedded GPUs and their programming models like OpenGL ES 2.0 and OpenCL, mobile processors are gaining a more parallel computing capability. Thereby, the adaptation of these advancements for accelerating mobile image processing algorithms has become actually an important topical issue. In this paper, our interest is based on reviewing recent challenging tasks related to mobile image processing using both serial and parallel computing approaches in several emerging application contexts.

Nested loops present the most critical sections in several embedded real-time applications. To attain a higher performance, several optimization techniques are employed in order to increase parallelism. However, due to the tight requirements, they are either unable to achieve any execution time constraint or achieve it with a high code size, which presents an implementation limiting factor. In this paper, we propose a novel optimization approach that combines two techniques which are the delayed multidimensional retiming and the loop striping. It explores the solution space, which is composed by all parallelism cases proposed by both techniques, in order to provide the implementation that achieves the execution time constraint while using a lower code size which has not been attained by the other two techniques. We propose the theory of combining both techniques and efficient algorithms of selecting the parallelism transformations. The experimental results show that our optimization approach achieves execution times where each technique can not. Moreover, even if they can, it presents average improvements on the code size of 35.21% compared to the delayed multidimensional retiming and 16.38% compared to the loop striping.

Multidimensional retiming is an efficient optimization approach that ensures increasing a parallelism level in order to optimize the execution time. Two existing techniques called incremental and chained multidimensional retiming are based on this approach, which aim at achieving a full parallelism on loop body in order to schedule applications with a minimum cycle period. However, the cycle number increases in terms of parallelism level which presents a limiting factor to respect the execution time constraint of real-time applications. In this paper, we show how the minimal cycle period is achieved in multidimensional applications without applying a full parallelism. We present the theory of a novel technique, called delayed multidimensional retiming. Firstly, two efficient algorithms are presented where the first one insures the extraction of timing and data dependency properties of the application and the second one selects the set of data path for retiming. Then, we propose theorems to deduce a retiming function for the selected paths. Finally, a third algorithm describing the optimization approach is introduced. The experimental results show that our technique improves execution times in comparison to existing techniques. It achieves average improvements on the execution time of 41.57% compared to the Incremental technique and 11.55% compared to the Chained technique.

This paper presents an optimizing methodology for implementing a multi-layer perceptron (MLP) neural network in a Field Programmable Gate Array (FPGA) device. In order to obtain an efficient implementation, a compromise of time and area is needed. Starting from simulation in the learning phase with fixed point operators, we have developed a methodology which allows the automatic generation of a VHDL code within a multi-width encoding of an MLP. The proposed methodology should determine the optimal encoding of various blocks of our Artificial Neural Networks (ANN) to optimize accuracy and minimize the application area. In addition, real-time constraints should be respected to ensure a reliable classification of vigilance states in humans from electroencephalographic signals (EEG). To validate our approach, the optimized MLP implementation has been tried on Virtex devices.