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.

In Tunisian agriculture, olive tree cultivation plays an important role. It is affected by different stresses that jeopardize its sustainability. In this context, our objective is to enhance the resilience of this crop. To achieve this goal, our work consists of detecting anomalies at early stage starting from the tree to the field scale. The proposed solution takes advantage of the emergence of satellites with high spatial and temporal resolution. In particular, the Sentinel-2 sensor which is well-adapted to monitor the vegetation. It is characterized by ten spectral bands allowing to access to key vegetation properties such as leaf area index (LAI), chlorophyll content (Cab) and water content (Cw), etc. Direct estimation of these parameters for the image is not practical as the signal is convolved. For that, we use artificial intelligence techniques to separate the effects of the different properties. We develop an Artificial Neural Network (ANN) that learn to estimate the vegetation properties given the pixel signature. The learning is done using a database of simulated data produced by a radiative transfer model that simulates the satellite image given the vegetation cover properties. The stress detection is based on a threshold on tree LAI and Cab. Comparison with ground truth with healthy and stressed plots has shown the validity of our approach.

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%.

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 an approach to quantify the effect of surface re-meshing on hemodynamic modeling. This work is organized in three parts. First, we briefly present the basic concepts inherent in hemodynamic modeling. Then, we detail the approach of triangular surface re-meshing: simplification and local densification based on discrete curvature analysis. The re-meshed triangular surfaces are used as input as well as a parabolic inlet velocity profile to the hemodynamic modeling procedure. As a validation, the third part will be focused on two examples: carotid blood flow characterization for a healthy patient and one with stenosis in the carotid artery. We quantified the differences between the generated models by evaluating the Eucledean similarity, rate of change and RMSE between the measured and modeled velocity obtained with different mesh densities. We conclude with the important effect of re-meshing on the modeled results and we propose to adapt the choice of the localization and the proportion of re-meshing to the local deformation of arterial structure.

This paper deals with the hemodynamic modeling in a carotid artery bifurcation with two laws - the laminar Newtonian and non Newtonian blood flow models- and two velocity inlet conditions - uniform and parabolic -. We assumed that blood flow is laminar and incompressible and the wall is rigid. From the artery geometry and the inlet velocity profile, four hemodynamic models of pulsatile flow were performed. These models were tested on a healthy subject data. The vascular model was reconstructed from Computed Tomography Angiography acquisition. The Doppler Ultrasound velocity data provided were considered as references. As a first conclusion, in the internal carotid artery, simulated velocities with non Newtonian law and uniform velocity inlet were the closest to US-Doppler measurements. However, in the external carotid artery, the closest model to US-Doppler measurements was non Newtonian law with parabolic inlet. Overall, Newtonian and non Newtonian blood flow models had a close behavior.

During the last decade, the need for visual content applications over mobile wireless environments have been progressively widespread. Motivated by the OSI layered approach, most visual applications make separation between content compression, and data transmission. Then, the received multimedia quality is degraded because of the sensitivity of the compressed stream to the transmission errors. In this paper, we propose a solution where the physical layer is scaled according to the compressed stream importance. The target application, which is visual multimedia sensor networks, motivated the use of the high-rate Ultra Wide Band (UWB) Audio Visual (AV) PHY IEEE 802.15.3c standard. We consider an embedded image compression scheme where bits are hierarchically organized, and we make different modulation, error-protection and sub-carrier assignments to them to improve the reconstructed image quality while keeping the same data-rate performance. We investigate the performance of the adaptive approach in terms of Peak Signal-to-Noise Ratio (PSNR) against Signal-to-Noise Ratio (SNR) for UWB-modeled channels. Moreover, we emphasize the gains induced by the adaptive UWB on the reconstructed image quality. It is demonstrated that dynamically assigning the symbols to sub-carriers allows a 0.5dB PSNR quality improvement while keeping the same rate is the same. Allocating different channel codes and different modulation orders improves the reconstructed PSNR by 3.SdB when Eb/N0= 5dB.

In order to retrieve multimedia content like video and audio at indoor environments, wireless multimedia sensor networks have recently emerged as a good solution. Moreover, Ultra Wide Band technology (UWB) can provide high data rates to transfer the multimedia content in a point-to-point mode. In this paper, we explain the features of UWB technology and investigate the performance of the IEEE 802.15.3c standard in terms of Bit Error Rate (BER) against Signal to Noise Ratio (SNR). The Audio Visual Physical (AV PHY) mode has been implemented and simulated and our results show that encoded AV PHY outperforms the uncoded AV PHY for high and low Convolutional encoder rates. Finally, we emphasized the quality improvements with different UWB standard parameters (coding and modulation) in the context of JPEG image compression.