Search Results (27)

Microwave devices based on microstrip resonators are widely used today in communication, radar, and navigation systems. The requirements to these devices may include specific frequency-selective properties, as well as size and production costs. The design of resonators and filters are mostly performed manually, as the process requires expert knowledge and computationally expensive modeling, so practitioners are usually limited to tuning a chosen example from a set of known, typical topologies. However, the set of possible topologies remains unexplored and may contain specific constructions, which have not been discovered yet. In this study we propose an approach to automatically search the space multimode resonator topologies using a zero-order optimization algorithm and numerous computational experiments. In particular, a family of symmetrical resonators constructed out of four rectangles is considered, and the parameters are tuned by the recently proposed L-SRTDE algorithm. We state the problem of building the topology of a microwave device conductor with specified frequency-selective characteristics as an optimization problem, and the minimized function (target function) in this problem is based on the evaluation of the deviation between the specified frequency-selective characteristics and their values obtained via electrodynamic modeling. The experiments with two target function formulations have shown that the proposed approach allows finding novel topologies and automatically tune them according to the required frequency-selective properties. It is shown that some of the topologies are different from the known ones but still demonstrate high-quality properties. Full article

Major depressive disorder is a mental health condition characterized by ongoing feelings of sadness, trouble focusing or making decisions, and a frequent sense of fatigue or hopelessness that lasts for a prolonged period. If left undiagnosed, it can have serious consequences, including suicide. This study proposes a 3D convolutional neural network model to detect major depressive disorder using 3D grey matter images from magnetic resonance imaging. The proposed 3D convolutional architecture comprises multiple hierarchical convolutional and pooling layers, designed to automatically learn spatial patterns from magnetic resonance imaging data. The model was optimized via Bayesian hyperparameter tuning, achieving an accuracy of 72.26%, an area under the receiver operating characteristic curve of 0.80, and an area under the precision–recall curve of 0.81 on a large multisite dataset comprising 1276 patients and 1104 healthy controls. Gradient-weighted class activation mapping is utilized to find brain regions associated with major depressive disorder. From this study, six regions were identified, namely, the frontal lobe, parietal lobe, temporal lobe, thalamus, insular cortex and corpus callosum which may be affected by major depressive disorder. Full article

Early and accurate identification of brain tumors is essential for determining effective treatment strategies and improving patient outcomes. Artificial intelligence (AI) and deep learning (DL) techniques have shown promise in automating diagnostic tasks based on magnetic resonance imaging (MRI). This study evaluates the performance of four pre-trained deep convolutional neural network (CNN) architectures for the automatic multi-class classification of brain tumors into four categories: Glioma, Meningioma, Pituitary, and No Tumor. The proposed approach utilizes the publicly accessible Brain Tumor MRI Msoud dataset, consisting of 7023 images, with 5712 provided for training and 1311 for testing. To assess the impact of data availability, subsets containing 25%, 50%, 75%, and 100% of the training data were used. A stratified five-fold cross-validation technique was applied. The CNN architectures evaluated include DeiT3_base_patch16_224, Xception41, Inception_v4, and Swin_Tiny_Patch4_Window7_224, all fine-tuned using transfer learning. The training pipeline incorporated advanced preprocessing and image data augmentation techniques to enhance robustness and mitigate overfitting. Among the models tested, Swin_Tiny_Patch4_Window7_224 achieved the highest classification Accuracy of 99.24% on the test set using 75% of the training data. This model demonstrated superior generalization across all tumor classes and effectively addressed class imbalance issues. Furthermore, we deployed and benchmarked the best-performing DL model on embedded AI platforms (Jetson AGX Xavier and Orin Nano), demonstrating their capability for real-time inference and highlighting their feasibility for edge-based clinical deployment. The results highlight the strong potential of pre-trained deep CNN and transformer-based architectures in medical image analysis. The proposed approach provides a scalable and energy-efficient solution for automated brain tumor diagnosis, facilitating the integration of AI into clinical workflows. Full article

Cardiovascular Disease (CVD) remains the number one cause of morbidity and mortality, accounting for 17.9 million deaths every year. Precise and early diagnosis is therefore critical to the betterment of the patient’s outcomes and the many burdens that weigh on the healthcare systems. This work presents for the first time an innovative approach using the DenseNet architecture that allows for the automatic recognition of CVD from clinical data. The data is preprocessed and augmented, with a heterogeneous dataset of cardiovascular-related images like angiograms, echocardiograms, and magnetic resonance images used. Optimizing the deep features for robust model performance is conducted through fine-tuning a custom DenseNet architecture along with rigorous hyper parameter tuning and sophisticated strategies to handle class imbalance. The DenseNet model, after training, shows high accuracy, sensitivity, and specificity in the identification of CVD compared to baseline approaches. Apart from the quantitative measures, detailed visualizations are conducted to show that the model is able to localize and classify pathological areas within an image. The accuracy of the model was found to be 0.92, precision 0.91, and recall 0.95 for class 1, and an overall weighted average F1-score of 0.93, which establishes the efficacy of the model. There is great clinical applicability in this research in terms of accurate detection of CVD to provide time-interventional personalized treatments. This DenseNet-based approach advances the improvement on the diagnosis of CVD through state-of-the-art technology to be used by radiologists and clinicians. Future work, therefore, would probably focus on improving the model’s interpretability towards a broader population of patients and its generalization towards it, revolutionizing the diagnosis and management of CVD. Full article

Because of their potential “smart” applications, multifunctional stimuli-responsive polymers are gaining increasing scientific interest. The present work explores the possibility of developing such materials based on the hydrolytically stable N-3-dimethylamino propyl methacrylamide), DMAPMA. To this end, the properties in aqueous solution of the homopolymer PDMAPMA and copolymers P(DMAPMA-co-MMA_x) of DMAPMA with the hydrophobic monomer methyl methacrylate, MMA, were explored. Two copolymers were prepared with a molar content x = 20% and 35%, as determined by Proton Nuclear Magnetic Resonance (¹H NMR). Turbidimetry studies revealed that, in contrast to the homopolymer exhibiting a lower critical solution temperature (LCST) behavior only at pH 14 in the absence of salt, the LCST of the copolymers covers a wider pH range (pH > 8.5) and can be tuned within the whole temperature range studied (from room temperature up to ~70 °C) through the use of salt. The copolymers self-assemble in water above a critical aggregation Concentration (CAC), as determined by Nile Red probing, and form nanostructures with a size of ~15 nm (for P(DMAPMA-co-MMA₃₅)), as revealed by transmission electron microscopy (TEM) and dynamic light scattering (DLS). The combination of turbidimetry with ¹H NMR and automatic total organic carbon/total nitrogen (TOC/TN) results revealed the potential of the copolymers as visual CO₂ sensors. Finally, the alkylation of the copolymers with dodecyl groups lead to cationic amphiphilic materials with an order of magnitude lower CAC (as compared to the unmodified precursor), effectively stabilized in water as larger aggregates (~200 nm) over a wide temperature range, due to their increased ζ potential (+15 mV). Such alkylated products show promising biocidal properties against microorganisms such as Escherichia coli and Staphylococcus aureus. Full article

Processing errors can result in an asymmetric stiffness distribution within a microelectromechanical system (MEMS) disk resonator gyroscope (DRG) and thereby cause a mode mismatch and reduce the mechanical sensitivity and closed-loop scale factor stability. This paper proposes an automatic mode-matching method that utilizes mode reversal to obtain the true resonant frequency of the operating state of a gyroscope for high-precision matching. This method constructs a gyroscope control system that contains a drive closed loop, sense force-to-rebalance (FTR) closed loop, and quadrature error correction closed loop. After the gyroscope was powered on and started up, the x- and y-axes were quickly switched to obtain the resonant frequencies of the two axes through a phase-locked loop (PLL), and the x-axis tuning voltage was automatically adjusted to match the two-axis frequency. The experimental results show that the method takes only 5 s to execute, the frequency matching accuracy reaches 0.01 Hz, the matching state can be maintained in the temperature range of −20 to 60 °C, and the fluctuation of the frequency split does not exceed 0.005 Hz. Full article

Nuclear magnetic resonance relaxation of the proton spins of liquid molecules and their evolution during processes such as drying, fluid flow, and phase change of a sample can be monitored in a nondestructive way. A unilateral ¹H NMR sensor made with a permanent magnet array, inspired by the NMR MOUSE, with an RF coil tuned to 11.71 MHz was developed. This creates a sensitive homogeneous measuring volume parallel to the sensor surface and located 14 mm from its surface, allowing contactless measurements from the sample’s interior. As this sensitive volume is moved across the sample using a semi-automatic linear displacement mechanism with millimetric precision, spatial T₂ lifetime and signal intensity 1D profiles can be obtained. To characterize the sensor’s sensitive volume, eraser samples were used. To evaluate the sensor’s ability to characterize different materials, cement paste samples containing ordinary and white Portland cement were prepared and measured at seven days of age. In addition, measurements were made on organic samples such as a Hass avocado and beef steak. Based on the results, a 1 mm spatial resolution of the sensor was achieved. The sensor was able to detect differences in T₂ lifetimes in eraser specimens composed of layers of three different erasers. Also, a clear difference in T₂ lifetimes and signal intensities was observed in cement pastes composed of white and ordinary Portland cement. On the other hand, it was possible to obtain signals from the peel and pulp of the avocado fruit, as well as from the fat and meat in a beef steak in a nondestructive way. The T₂ lifetimes of the different materials agreed with those obtained using a commercial NMR spectrometer. Full article

Background: In this study, we examined the effectiveness of transfer learning in improving automatic segmentation of brain metastases on magnetic resonance imaging scans, with potential applications in preventive exams and remote diagnostics. Methods: We trained three deep learning models on a public dataset from the ASNR-MICCAI Brain Metastasis Challenge 2024, fine-tuned them on a small private dataset, and compared their performance to models trained from scratch. Results: Results showed that models using transfer learning performed better than scratch-trained models, though the improvement was not statistically substantial. The custom Tversky and Binary Cross-Entropy loss function helped manage class imbalance and reduce false negatives, limiting missed tumor regions. Medical experts noted that, while fine-tuned models worked well with larger, well-defined tumors, they struggled with tiny, scattered tumors in complex cases. Conclusions: This study highlights the potential of transfer learning and tailored loss functions in medical imaging, while also pointing out the models’ limitations in detecting very small tumors in challenging cases. Full article

The automatic segmentation of cardiac computed tomography (CT) and magnetic resonance imaging (MRI) plays a pivotal role in the prevention and treatment of cardiovascular diseases. In this study, we propose an efficient network based on the multi-scale, multi-head self-attention (MSMHSA) mechanism. The incorporation of this mechanism enables us to achieve larger receptive fields, facilitating the accurate segmentation of whole heart structures in both CT and MRI images. Within this network, features extracted from the shallow feature extraction network undergo a MHSA mechanism that closely aligns with human vision, resulting in the extraction of contextual semantic information more comprehensively and accurately. To improve the precision of cardiac substructure segmentation across varying sizes, our proposed method introduces three MHSA networks at distinct scales. This approach allows for fine-tuning the accuracy of micro-object segmentation by adapting the size of the segmented images. The efficacy of our method is rigorously validated on the Multi-Modality Whole Heart Segmentation (MM-WHS) Challenge 2017 dataset, demonstrating competitive results and the accurate segmentation of seven cardiac substructures in both cardiac CT and MRI images. Through comparative experiments with advanced transformer-based models, our study provides compelling evidence that despite the remarkable achievements of transformer-based models, the fusion of CNN models and self-attention remains a simple yet highly effective approach for dual-modality whole heart segmentation. Full article

To train an automatic brain tumor segmentation model, a large amount of data is required. In this paper, we proposed a strategy to overcome the limited amount of clinically collected magnetic resonance image (MRI) data regarding meningiomas by pre-training a model using a larger public dataset of MRIs of gliomas and augmenting our meningioma training set with normal brain MRIs. Pre-operative MRIs of 91 meningioma patients (171 MRIs) and 10 non-meningioma patients (normal brains) were collected between 2016 and 2019. Three-dimensional (3D) U-Net was used as the base architecture. The model was pre-trained with BraTS 2019 data, then fine-tuned with our datasets consisting of 154 meningioma MRIs and 10 normal brain MRIs. To increase the utility of the normal brain MRIs, a novel balanced Dice loss (BDL) function was used instead of the conventional soft Dice loss function. The model performance was evaluated using the Dice scores across the remaining 17 meningioma MRIs. The segmentation performance of the model was sequentially improved via the pre-training and inclusion of normal brain images. The Dice scores improved from 0.72 to 0.76 when the model was pre-trained. The inclusion of normal brain MRIs to fine-tune the model improved the Dice score; it increased to 0.79. When employing BDL as the loss function, the Dice score reached 0.84. The proposed learning strategy for U-net showed potential for use in segmenting meningioma lesions. Full article

The Gleason score was originally formulated to represent the heterogeneity of prostate cancer and helps to stratify the risk of patients affected by this tumor. The Gleason score assigning represents an on H&E stain task performed by pathologists upon histopathological examination of needle biopsies or surgical specimens. In this paper, we propose an approach focused on the automatic Gleason score classification. We exploit a set of 18 radiomic features. The radiomic feature set is directly obtainable from segmented magnetic resonance images. We build several models considering supervised machine learning techniques, obtaining with the RandomForest classification algorithm a precision ranging from 0.803 to 0.888 and a recall from to 0.873 to 0.899. Moreover, with the aim to increase the never seen instance detection, we exploit the sigmoid calibration to better tune the built model. Full article

The design optimization of the grading of a resonator array for energy harvesting in sensors is described. Attention is paid to set the resonator heights, possibly removing resonators whenever convenient. Instead of employing time-consuming heuristic approaches that require verifying the physical understanding of the problem and tuning the design ruling parameters, the optimization task is treated as a Markov decision process, in which states describe specific system configurations, and actions represent the modifications to the current design. The physics-based understanding of the problem is exploited to constrain the set of possible modifications to the mechanical system. Finite elements simulations are exploited to evaluate the action effects and to inform the reinforcement learning agent. The proximal policy optimization algorithm is employed to solve the Markov decision problem. The procedure is demonstrated to be able to automatically produce configurations, enhancing the mechanical system performance. The proposed framework is generalizable to a large class of problems involving the design optimization of sensors. Full article

The main drawback of energy harvesting using the piezoelectric direct effect is that the maximum electric power is generated at the fundamental resonance frequency. This can clearly be observed in the size and dimensions of the components of any particular energy harvester. In this paper, we are investigating a new proposed energy harvesting device that employs the Automatic Resonance Tuning (ART) technique to enhance the energy harvesting mechanism. The proposed harvester is composed of a cantilever beam and sliding masse with varying locations. ART automatically adjusts the energy harvester’s natural frequency according to the ambient vibration natural frequency. The ART energy harvester modifies the natural frequency of the harvester using the motion of the mobile (sliding) mass. An analytical model of the proposed model is presented. The investigation is conducted using the Finite Element Method (FEM). THE FEM COMSOL model is successfully validated using previously published experimental results. The results of the FEM were compared with the experimental and analytical results. The validated model is then used to demonstrate the displacement profile, the output voltage response, and the natural frequency for the harvester at different mass positions. The bandwidth of the ART harvester (17 Hz) is found to be 1130% larger compared to the fixed resonance energy harvester. It is observed that the proposed broadband design provides a high-power density of 0.05 mW mm⁻³. The piezoelectric dimensions and load resistance are also optimized to maximize the output voltage output power. Full article

Starting from Quartz-Enhanced Photo-Acoustic Spectroscopy (QEPAS), we have explored the potential of a tightly linked method of gas/vapor sensing, from now on referred to as Tuning-Fork-Enhanced Photo-Acoustic Spectroscopy (TFEPAS). TFEPAS utilizes a non-piezoelectric metal or dielectric tuning fork to transduce the photoacoustic excitation and an optical interferometric readout to measure the amplitude of the tuning fork vibration. In particular, we have devised a solution based on Additive Manufacturing (AM) for the Absorption Detection Module (ADM). The novelty of our solution is that the ADM is entirely built monolithically by Micro-Metal Laser Sintering (MMLS) or other AM techniques to achieve easier and more cost-effective customization, extreme miniaturization of internal volumes, automatic alignment of the tuning fork with the acoustic micro-resonators, and operation at high temperature. This paper reports on preliminary experimental results achieved with ammonia at parts-per-million concentration in nitrogen to demonstrate the feasibility of the proposed solution. Prospectively, the proposed TFEPAS solution appears particularly suited for hyphenation to micro-Gas Chromatography and for the analysis of complex solid and liquid traces samples, including compounds with low volatility such as illicit drugs, explosives, and persistent chemical warfare agents. Full article

Blood vessels of the brain provide the human brain with the required nutrients and oxygen. As a vulnerable part of the cerebral blood supply, pathology of small vessels can cause serious problems such as Cerebral Small Vessel Diseases (CSVD). It has also been shown that CSVD is related to neurodegeneration, such as Alzheimer’s disease. With the advancement of 7 Tesla MRI systems, higher spatial image resolution can be achieved, enabling the depiction of very small vessels in the brain. Non-Deep Learning-based approaches for vessel segmentation, e.g., Frangi’s vessel enhancement with subsequent thresholding, are capable of segmenting medium to large vessels but often fail to segment small vessels. The sensitivity of these methods to small vessels can be increased by extensive parameter tuning or by manual corrections, albeit making them time-consuming, laborious, and not feasible for larger datasets. This paper proposes a deep learning architecture to automatically segment small vessels in 7 Tesla 3D Time-of-Flight (ToF) Magnetic Resonance Angiography (MRA) data. The algorithm was trained and evaluated on a small imperfect semi-automatically segmented dataset of only 11 subjects; using six for training, two for validation, and three for testing. The deep learning model based on U-Net Multi-Scale Supervision was trained using the training subset and was made equivariant to elastic deformations in a self-supervised manner using deformation-aware learning to improve the generalisation performance. The proposed technique was evaluated quantitatively and qualitatively against the test set and achieved a Dice score of 80.44 ± 0.83. Furthermore, the result of the proposed method was compared against a selected manually segmented region (62.07 resultant Dice) and has shown a considerable improvement (18.98%) with deformation-aware learning. Full article