SpectroCVT-Net: A convolutional vision transformer architecture and channel attention for classifying Alzheimer's disease using spectrograms.

Dementia arises from various brain-affecting diseases and injuries, with Alzheimer's disease being the most prevalent, impacting around 55 million people globally. Current clinical diagnosis often relies on biomarkers indicative of Alzheimer's distinctive features. Electroencephalography (EEG) serves as a cost-effective, user-friendly, and safe biomarker for early Alzheimer's detection. This study utilizes EEG signals processed with Short-Time Fourier Transform (STFT) to generate spectrograms, facilitating visualization of EEG signal properties. Leveraging the Brainlat database, we propose SpectroCVT-Net, a novel convolutional vision transformer architecture incorporating channel attention mechanisms. SpectroCVT-Net integrates convolutional and attention mechanisms to capture local and global dependencies within spectrograms. Comprising feature extraction and classification stages, the model enhances Alzheimer's disease classification accuracy compared to transfer learning methods, achieving 92.59 ± 2.3% accuracy across Alzheimer's, healthy controls, and behavioral variant frontotemporal dementia (bvFTD). This article introduces a new architecture and evaluates its efficacy with unconventional data for Alzheimer's diagnosis, contributing: SpectroCVT-Net, tailored for EEG spectrogram classification without reliance on transfer learning; a convolutional vision transformer (CVT) module in the classification stage, integrating local feature extraction with attention heads for global context analysis; Grad-CAM analysis for network decision insight, identifying critical layers, frequencies, and electrodes influencing classification; and enhanced interpretability through spectrograms, illuminating key brain wave contributions to Alzheimer's, frontotemporal dementia, and healthy control classifications, potentially aiding clinical diagnosis and management.

Chitosan coated selenium: A versatile nano-delivery system for molecular cargoes.

The use of nanoscale delivery platforms holds tremendous potential to overcome the current limitations associated with the conventional delivery of genetic materials and hydrophobic compounds. Therefore, there is an imperative need to develop a suitable alternative nano-enabled delivery platform to overcome these limitations. This work reports the first one-step hydrothermal synthesis of chitosan functionalized selenium nanoparticles (Selenium-chitosan, SeNP) that are capable of serving as a versatile nanodelivery platform for different types of active ingredients. The chitosan functionalization modified the surface charge to allow the loading of active ingredients and improve biocompatibility. The effective loading of the SeNP was demonstrated using genetic material, a hydrophobic small molecule, and an antibiotic. Furthermore, the loading of active ingredients showed no detrimental effect on the specific properties (fluorescence and bactericidal) of the studied active ingredients. In vitro antimicrobial inhibitory studies exhibited good compatibility between the SeNP delivery platform and Penicillin G (Pen), resulting in a reduction of the minimum inhibitory concentration (MIC) from 32 to 16 ppm. Confocal microscopy images showed the uptake of the SeNP by a macrophage cell line (J774A.1), demonstrating trackability and intracellular delivery of an active ingredient. In summary, the present work demonstrates the potential of SeNP as a suitable delivery platform for biomedical and agricultural applications.

Microwave Imaging System Based on Signal Analysis in a Planar Environment for Detection of Abdominal Aortic Aneurysms.

A proof-of-concept of a microwave imaging system for the fast detection of abdominal aortic aneurysms is shown. This experimental technology seeks to overcome the factors hampering the fast screening for these aneurysms with the usual equipment, such as high cost, long-time operation or hazardous exposure to chemical substances. The hardware system is composed of 16 twin antennas mastered by a microcontroller through a switching network, which connects the antennas to the measurement instrument for sequential measurement. The software system is run by a computer, mastering the whole system, automatizing the measurement process and running the signal processing and medical image generation algorithms. Two image generation algorithms are tested: Delay-and-Sum (DAS) and Improved Delay-and-Sum (IDAS). Own-modified versions of these algorithms adapted to the requirements of our system are proposed. The system is carefully calibrated and fine-tuned with known objects placed at known distances. An experimental proof-of-concept is shown with a human torso phantom, including an aorta phantom and an aneurysm phantom placed in different positions. The results show good imaging capabilities with the potential for detecting and locating possible abdominal aortic aneurysms and reporting acceptable errors.

A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure.

INTRODUCTION: Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy. METHOD: To optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis. RESULT: In this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%. CONCLUSION: Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models.

An ML-Based Approach to Reconstruct Heart Rate from PPG in Presence of Motion Artifacts.

The heart rate (HR) is a widely used clinical variable that provides important information on a physical user's state. One of the most commonly used methods for ambulatory HR monitoring is photoplethysmography (PPG). The PPG signal retrieved from wearable devices positioned on the user's wrist can be corrupted when the user is performing tasks involving the motion of the arms, wrist, and fingers. In these cases, the obtained HR is altered as well. This problem increases when trying to monitor people with autism spectrum disorder (ASD), who are very reluctant to use foreign bodies, notably hindering the adequate attachment of the device to the user. This work presents a machine learning approach to reconstruct the user's HR signal using an own monitoring wristband especially developed for people with ASD. An experiment is carried out, with users performing different daily life activities in order to build a dataset with the measured signals from the monitoring wristband. From these data, an algorithm is applied to obtain a reliable HR value when these people are performing skill improvement activities where intensive wrist movement may corrupt the PPG.

Non-Invasive Microwave-Based Imaging System for Early Detection of Breast Tumours.

This work introduces a microwave-based system able to detect tumours in breast phantoms in a non-invasive way. The data acquisition system is composed of a hardware system which involves high-frequency components (antennas, switches and cables), a microcontroller, a vector network analyser used as measurement instrument and a computer devoted to the control and automation of the operation of the system. Concerning the software system, the computer runs a Python script which is in charge of mastering and automatising all the required stages for the data acquisition, from initialisation of the hardware system to performing and saving the measurements. We also report on the design of the high-performance broadband antenna used to carry out the measurements, as well as on the algorithm employed to build the final medical images, based on an adapted version of the so-called Improved Delay-and-Sum (IDAS) algorithm improved by a Hamming window filter and averaging preprocessing. The calibration and start-up of the system are also described. The experimental validation includes the use of different tumour models with different dielectric properties inside the breast phantom. The results show promising tumour detection capabilities, even when there is low dielectric contrast between the tumoural and healthy tissues, as is the usual case for dense breasts in young women.

Validation of an RF Image System for Real-Time Tracking Neurosurgical Tools.

A radio frequency (RF)-based system for surgical navigation is presented. Surgical navigation technologies are widely used nowadays for aiding the surgical team with many interventions. However, the currently available options still pose considerable limitations, such as line-of-sight occlusion prevention or restricted materials and equipment allowance. In this work, we suggest a different approach based on a microwave broadband antenna system. We combine techniques from microwave medical imaging, which can overcome the current limitations in surgical navigation technologies, and we propose methods to develop RF-based systems for real-time tracking neurosurgical tools. The design of the RF system to perform the measurements is shown and discussed, and two methods (Multiply and Sum and Delay Multiply and Sum) for building the medical images are analyzed. From these measurements, a surgical tool's position tracking system is developed and experimentally assessed in an emulated surgical scenario. The reported results are coherent with other approaches found in the literature, while overcoming their main practical limitations. The discussion of the results discloses some hints on the validity of the system, the optimal configurations depending on the requirements, and the possibilities for future enhancements.

[Vitamin D deficiency/insufficiency on healthy infants receiving standard supplementation]. / Deficiencia e insuficiencia de vitamina D en lactantes sanos recibiendo suplementación estándar.

Vitamin D (VD) is essential for calcium and phosphorus metabolism. Its deficiency can cause rickets. In Chile, newborns receive 400UI/day supplementation from the first day of age until the first year. OBJECTIVE: To describe the VD plasma levels in healthy infants who received supplementation and secondarily to correlate this with seasonality and nutritional status. SUBJECTS AND METHOD: Cross sectional study. Infants on exclusive or mixed breastfeeding, with monthly pediatric checkups recei ving 400 UI VD supplementation were evaluated, measuring VD plasma levels at 6 months of age, weight, and length, and their nutritional status was classified according to the WHO growth referen ces (weight/age and weight/length). The VD cut-off concentration values were < 20 ng/ml, 21- 29 ng/ ml, and ≥ 30 ng/ml considered as deficiency, insufficiency, and sufficiency, respectively. RESULTS: 40 infants were studied, 40% had insufficient levels and 40% presented deficiency. Season and nutritio nal status were variables significantly related to lower VD values (Winter-Spring p = 0.007; at risk of malnutrition p = 0.038). CONCLUSIONS: The population who received supplementation presented a high frequency of VD deficiency and insufficiency which increases during winter and spring and in subjects at risk of malnutrition.

Implementation of Microwave Circuits Using Stereolithography.

In this work, the use of additive manufacturing techniques through stereolithography for the manufacture of high-frequency circuits and devices is presented. Both the resin and the 3D printer used in this research are general-purpose commercial materials, not specifically intended for the implementation of microwave networks. The manufacturing and metallization procedures used to produce substrates for the design of planar microwave circuits are described, introducing the characterization process carried out to determine the electrical properties of the resin used. The ultrasonic techniques that allow the structural analysis of the manufactured substrates are also described. The electrical characterization provides a relative dielectric permittivity of 3.25 and a loss tangent of 0.03 for the resin used. In addition, the structural analysis shows a homogeneity and a finish of the manufactured parts that is not achievable using fused deposition modeling techniques. Finally, as a proof of concept, the design and manufacture of a complex geometry stepped impedance filter on a multi-height substrate using stereolithography techniques is presented, which allows for reducing the size of the traditional implementation of the same filter while maintaining its high-frequency response performance.

Low-Cost Additive Manufacturing Techniques Applied to the Design of Planar Microwave Circuits by Fused Deposition Modeling.

This work presents a study on the implementation and manufacturing of low-cost microwave electronic circuits, made with additive manufacturing techniques using fused deposition modeling (FDM) technology. First, the manufacturing process of substrates with different filaments, using various options offered by additive techniques in the manufacture of 3D printing parts, is described. The implemented substrates are structurally analyzed by ultrasound techniques to verify the correct metallization and fabrication of the substrate, and the characterization of the electrical properties in the microwave frequency range of each filament is performed. Finally, standard and novel microwave filters in microstrip and stripline technology are implemented, making use of the possibilities offered by additive techniques in the manufacturing process. The designed devices were manufactured and measured with good results, which demonstrates the possibility of using low-cost 3D printers in the design process of planar microwave circuits.

Feasibility study of portable microwave microstrip open-loop resonator for non-invasive blood glucose level sensing: proof of concept.

Self-management of blood glucose level is part and parcel of diabetes treatment, which involves invasive, painful, and uncomfortable methods. A proper non-invasive blood glucose monitor (NIBGM) is therefore desirable to deal better with it. Microwave resonators can potentially be used for such a purpose. Following the positive results from an in vitro previous work, a portable device based upon a microwave resonator was developed and assessed in a multicenter proof of concept. Its electrical response was analyzed when an individual's tongue was placed onto it. The study was performed with 352 individuals during their oral glucose tolerance tests, having four measurements per individual. The findings revealed that the accuracy must be improved before the diabetes community can make real use of the device. However, the relationship between the measuring parameter and the individual's blood glucose level is coherent with that from previous works, although with higher data dispersion. This is reflected in correlation coefficients between glycemia and the measuring magnitude consistently negative, although small, for the different datasets analyzed. Further research is proposed, focused on system improvements, individual calibration, and multitechnology approach. The study of the influence of other blood components different to glucose is also advised. Graphical abstract.

Impact of BRCA1/2 gene mutations on survival of patients with pancreatic cancer: A case-series analysis.

BRCA gene mutations are found in up to 10% of pancreatic adenocarcinoma cases. We present a description of 4 cases along with a review of the current literature regarding pathogenesis, target treatment, response and survival rates in these types of malignancies. We describe four cases of pancreatic adenocarcinoma, in three of which the BRCA2 mutation was identified, in one - BRCA1 gene alteration. Two patients underwent surgery following the neoadjuvant treatment with Folfirinox and radiotherapy; in the first case, a distal pancreatectomy with splenectomy was performed and in the second one - the Whipple's procedure. In both cases, a complete pathological response was reported. Other 2 patients were treated with Folfirinox after BRCA mutation identification and acceptable life expectancy was obtained. The association of pathologic complete response (PCR) with lower rates of local recurrence and better survival in patients with various types of adenocarcinomas is well known. Identification of such patients carrying BRCA mutations could provide an application of better personalized treatment. In some patients with pancreatic cancer, especially when there is clinical or demographic reason to suspect a genetic predisposition, a confirmation of the presence of BRCA mutations could provide an opportunity to use target treatment with beneficial outcomes regarding survival.

Portable Device Based on Microwave Resonator for Noninvasive Blood Glucose Monitoring.

A portable device for noninvasive blood glucose monitoring is presented. The device is based on a microwave open-loop microstrip resonator, acting as glucose sensor, following the results of a previous study. This work shows the design and development of the driving electronics, signal generation system, data processing, measurement setup and graphical user interface, to integrate the resonator into a device suitable for further experimentation in clinical scenarios. The measurement principle relies in the idea of relating the unloaded Q factor to the user's blood glucose level. An initial assessment is shown, whose results highlight some successful cases of blood glucose level tracking, and indicate the need for further research in clinical scenarios.

Design of a wearable bio-patch for monitoring patient's temperature.

New communication technologies allow us developing useful and more practical medical applications, in particular for ambulatory monitoring. NFC communication has the advantages of low powering and low influence range area, what makes this technology suitable for health applications. This work presents an explanation of the design process of planar NFC antennas in a wearable biopatch. The problem of optimizing the communication distance is addressed. Design of a biopatch for continuous temperature monitoring and experimental results obtained wearing this biopatch during daily activities are presented.

Mucormicosis cutánea: reporte de 3 pacientes con diabetes mellitus / Cutaneous mucormycosis. A report of three cases in diabetes mellitus patients

Se describen tres mujeres diabéticas que desarrollaron mucormicosis cutánea en la espalda, pierna derecha y pierna izquierda, respectivamente. Las lesiones fueron únicas, entre 12 a 18 cm de diámetro, sin secreciones, con edema, eritema, calor, induración, necrosis importante y zonas isquémicas a su alrededor. Los exámenes histológicos mostraron extensa necrosis y numerosas hifas no septadas; en los cultivos creció Mucor spp. Todas las pacientes recibieron tratamiento con anfotericina B. En la primer paciente la enfermedad no se reconoció tempranamente y la paciente falleció; la segunda paciente requirió amputación de su pierna y la tercer paciente tuvo una buena respuesta. El diagnóstico temprano es primordial para evitar morbilidad y mortalidad por esta rara infección oportunista