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.

Classification of Alzheimer's disease stages from magnetic resonance images using deep learning.

Alzheimer's disease (AD) is a progressive type of dementia characterized by loss of memory and other cognitive abilities, including speech. Since AD is a progressive disease, detection in the early stages is essential for the appropriate care of the patient throughout its development, going from asymptomatic to a stage known as mild cognitive impairment (MCI), and then progressing to dementia and severe dementia; is worth mentioning that everyone suffers from cognitive impairment to some degree as we age, but the relevant task here is to identify which people are most likely to develop AD. Along with cognitive tests, evaluation of the brain morphology is the primary tool for AD diagnosis, where atrophy and loss of volume of the frontotemporal lobe are common features in patients who suffer from the disease. Regarding medical imaging techniques, magnetic resonance imaging (MRI) scans are one of the methods used by specialists to assess brain morphology. Recently, with the rise of deep learning (DL) and its successful implementation in medical imaging applications, it is of growing interest in the research community to develop computer-aided diagnosis systems that can help physicians to detect this disease, especially in the early stages where macroscopic changes are not so easily identified. This article presents a DL-based approach to classifying MRI scans in the different stages of AD, using a curated set of images from Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies databases. Our methodology involves image pre-processing using FreeSurfer, spatial data-augmentation operations, such as rotation, flip, and random zoom during training, and state-of-the-art 3D convolutional neural networks such as EfficientNet, DenseNet, and a custom siamese network, as well as the relatively new approach of vision transformer architecture. With this approach, the best detection percentage among all four architectures was around 89% for AD vs. Control, 80% for Late MCI vs. Control, 66% for MCI vs. Control, and 67% for Early MCI vs. Control.

Cov-caldas: A new COVID-19 chest X-Ray dataset from state of Caldas-Colombia.

The emergence of COVID-19 as a global pandemic forced researchers worldwide in various disciplines to investigate and propose efficient strategies and/or technologies to prevent COVID-19 from further spreading. One of the main challenges to be overcome is the fast and efficient detection of COVID-19 using deep learning approaches and medical images such as Chest Computed Tomography (CT) and Chest X-ray images. In order to contribute to this challenge, a new dataset was collected in collaboration with "S.E.S Hospital Universitario de Caldas" ( https://hospitaldecaldas.com/ ) from Colombia and organized following the Medical Imaging Data Structure (MIDS) format. The dataset contains 7,307 chest X-ray images divided into 3,077 and 4,230 COVID-19 positive and negative images. Images were subjected to a selection and anonymization process to allow the scientific community to use them freely. Finally, different convolutional neural networks were used to perform technical validation. This dataset contributes to the scientific community by tackling significant limitations regarding data quality and availability for the detection of COVID-19.

Machine learning applications to predict two-phase flow patterns.

Recent advances in artificial intelligence with traditional machine learning algorithms and deep learning architectures solve complex classification problems. This work presents the performance of different artificial intelligence models to classify two-phase flow patterns, showing the best alternatives for this specific classification problem using two-phase flow regimes (liquid and gas) in pipes. Flow patterns are affected by physical variables such as superficial velocity, viscosity, density, and superficial tension. They also depend on the construction characteristics of the pipe, such as the angle of inclination and the diameter. We selected 12 databases (9,029 samples) to train and test machine learning models, considering these variables that influence the flow patterns. The primary dataset is Shoham (1982), containing 5,675 samples with six different flow patterns. An extensive set of metrics validated the results obtained. The most relevant characteristics for training the models using Shoham (1982) dataset are gas and liquid superficial velocities, angle of inclination, and diameter. Regarding the algorithms, the Extra Trees model classifies the flow patterns with the highest degree of fidelity, achieving an accuracy of 98.8%.

COVID-19 detection in X-ray images using convolutional neural networks.

COVID-19 global pandemic affects health care and lifestyle worldwide, and its early detection is critical to control cases' spreading and mortality. The actual leader diagnosis test is the Reverse transcription Polymerase chain reaction (RT-PCR), result times and cost of these tests are high, so other fast and accessible diagnostic tools are needed. Inspired by recent research that correlates the presence of COVID-19 to findings in Chest X-ray images, this papers' approach uses existing deep learning models (VGG19 and U-Net) to process these images and classify them as positive or negative for COVID-19. The proposed system involves a preprocessing stage with lung segmentation, removing the surroundings which does not offer relevant information for the task and may produce biased results; after this initial stage comes the classification model trained under the transfer learning scheme; and finally, results analysis and interpretation via heat maps visualization. The best models achieved a detection accuracy of COVID-19 around 97%.

Sensitivity of deep learning applied to spatial image steganalysis.

In recent years, the traditional approach to spatial image steganalysis has shifted to deep learning (DL) techniques, which have improved the detection accuracy while combining feature extraction and classification in a single model, usually a convolutional neural network (CNN). The main contribution from researchers in this area is new architectures that further improve detection accuracy. Nevertheless, the preprocessing and partition of the database influence the overall performance of the CNN. This paper presents the results achieved by novel steganalysis networks (Xu-Net, Ye-Net, Yedroudj-Net, SR-Net, Zhu-Net, and GBRAS-Net) using different combinations of image and filter normalization ranges, various database splits, different activation functions for the preprocessing stage, as well as an analysis on the activation maps and how to report accuracy. These results demonstrate how sensible steganalysis systems are to changes in any stage of the process, and how important it is for researchers in this field to register and report their work thoroughly. We also propose a set of recommendations for the design of experiments in steganalysis with DL.

Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain.

In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving steganographic images' detection accuracy, but it is unclear which computational elements are relevant. Here we present a strategy to improve accuracy, convergence, and stability during training. The strategy involves a preprocessing stage with Spatial Rich Models filters, Spatial Dropout, Absolute Value layer, and Batch Normalization. Using the strategy improves the performance of three steganalysis CNNs and two image classification CNNs by enhancing the accuracy from 2% up to 10% while reducing the training time to less than 6 h and improving the networks' stability.

Vitamina D: una estrategia profiláctica en tiempos del SARS-CoV-2. Vitamina D, SARS-CoV-2 y odontología / Vitamin D: A prophylactic strategy in times of SARS-CoV-2. Vitamin D, SARS- CoV-2 and Dentistry

Objetivo: ofrecer a todo el personal de salud oral un resumen narrativo de la literatura sobre la relación entre el uso de la vitamina D y la COVID-19, a través de la presentación de los beneficios de este suplemento. Se espera aportar a ampliar el conocimiento sobre esta sustancia orgánica, en tanto herramienta profiláctica para la salud de todos. Método: La búsqueda bibliográfica se realizó en las bases de datos PubMed, Cochrane, Science Direct y Ebsco, observando los años 2010 a 2020. Se seleccionaron 65 referencias bibliográficas relacionadas con la vitamina D, sus funciones intra y extra esqueléticas y su posible relación con el SARS-CoV-2; además, se incluyeron estudios que evalúan la deficiencia de vitamina D en el personal de salud. Resultados: la revisión narrativa efectuada demuestra que la deficiencia de vitamina D es frecuente en el personal de salud y que esta deficiencia reduce la actividad defensiva inmunológica. Además, se demuestra que existe suficiente evidencia de la relación entre niveles deficientes de vitamina D en plasma y el riesgo de desarrollar formas severas de COVID-19, especialmente en población susceptible. Conclusiones: se recomienda, tanto al personal de la salud como a los pacientes, el consumo de un suplemento de vitamina D como medida profiláctica.

Objective: to provide the clinicians and dental health staff with relevant information about the role of Vitamin D in connection with COVID-19, presenting the needs, benefits and risks of Vit D supplementation in the doses suggested in literature, to indicate preventive actions and provide patients advice to reduce the consequences of COV ID -19. Method: The bibliographic search was carried out in the PubMed, Cochrane, Science Direct and Ebsco databases, observing the years 2010 to 2020. We selected 65 references related to vitamin D and its intra and extra-skeletal functions, its possible relationship to SARS-CoV-2, and also included studies assessing vitamin D deficiency in health care workers. Results: Vitamin D deficiency is frequent in dental staff and this deficiency reduces the efficiency of immunologic defenses. There is evidence regarding a relationship between vitamin D levels and risk of severe forms of COVID-19. Conclusion: It is recommended the prophylactic use of a Vitamin D supplement for both dentists and dental patients.

Efectos de la obesidad materna sobre el patrón de apoptosis en la cardiogénesis tardía / Effects of maternal obesity on the apoptosis pattern in late cardiogenesis / Efeitos da obsedidade materna sobre o padrão de apoptose na cardiogênese tardia

RESUMEN I: La ganancia excesiva de peso durante la gestación contribuye a un desbalance en el aporte de nutrientes que influyen en la reprogramación de vías moleculares de la organogénesis, aumentando el riesgo de desarrollar anomalías congénitas en el corazón. O: Determinar el efecto de la obesidad materna sobre el patrón de apoptosis en la cardiogénesis tardía. M: Se estableció un modelo de obesidad materna adquirida por dieta de cafetería tipo snack, en ratas Wistar adultas. Las ratas del grupo obeso y del grupo control se aparearon con machos adultos sanos y fueron sacrificadas el día 16.5 de gestación. Los corazones fueron evaluados macroscópicamente y procesados para el estudio de la apoptosis cardíaca mediante la técnica de TUNEL. R: El 25 % de los corazones procedentes de madres obesas presentaron aumento en el tamaño de atrios, ventrículos y tracto de salida. La apoptosis fue menor en los ventrículos de los corazones fetales procedentes de madres obesas vs control (p<0,05). En el atrio derecho la apoptosis fue mayor en los corazones fetales del grupo obeso vs control (p<0,05). De manera importante se observó un aumento significativo en la cantidad de células en apoptosis presentes en el tabique interventricular del grupo control vs el grupo obeso (p <0.000l). C: El proceso de apoptosis se encontró alterado en los corazones fetales que fueron expuestos a condiciones de obesidad materna.

ABSTRACT I: Excessive weight gain during pregnancy contributes to an imbalance in the contribution of nutrients that influences the reprogramming of molecular pathways of organogenesis, increasing the risk of developing congenital anomalies in the heart. O: To determine the effect of maternal obesity on the pattern of apoptosis in late cardiogenesis. M: A model of maternal obesity acquired by snack diet was established in adult Wistar rats. The rats of the obese group and the control group were mated with healthy adult males and were killed on day l6.5 of gestation. The hearts were evaluated macroscopically and processed for the study of cardiac apoptosis using the TUNEL technique. R: 25% of hearts from obese mothers had an increase in the size of atria, ventricles and outflow tract. Apoptosis was lower in the ventricles of fetal hearts from obese mothers vs control (p <0.05). In the right atrium, apoptosis was higher in the fetal hearts of the obese vs control group (p <0.05). Importantly, there was a significant increase in the number of cells in apoptosis present in the interventricular septum of the control group vs the obese group (p <0.000l). C: The process of apoptosis was found altered in fetal hearts that were exposed to conditions of maternal obesity.

RESUMO I: o ganho excessivo de peso durante a gestação contribui a um desequilibrio no aporte de nutrientes que influenciam a reprogramação das vias moleculares da organogênese, aumentando o risco de deselvolvimento de anomalias congênitas no coração. O: determinar o efeito da obesidade materna sobre o padrão de apoptose na cardiogênese tardia. M: estabeleceu-se um modelo de obesidade materna por meio de dieta de lanches tipo snack, em ratos Wistar adultos. Os ratos do grupo obeso e do grupo controle foram acasalados com machos adultos saudáveis, e sacrificados no dia l 6.5 da gestação. Os corações availaram-se macroscopicamente e processaram-se para o estudo da apoptose cardíaca utilizando a técnica do TUNEL. R: 25% dos corações de mães obesas apresentaram aumento do tamanho dos átrios, ventrículos e via de saida. A apoptose foi menor nos ventrículos dos corações fetais de mães obesas vs controle (p <0,05). No átrio direito, a apoptose foi maior nos corações fetais do grupo obeso vs controle (p <0,05). De uma maneira importante, houve um aumento significativo no número de células em apoptose presentes no septo interventricular do grupo controle vs o grupo obeso (p < 0,000l). C: o processo de apoptose encontrou-se alterado em corações fetais que foram expostos a condições de obesidade materna.

Clinical and systemic effects of periodontally accelerated osteogenic orthodontics: a pilot study / Efectos clínicos y sistémicos de la ortodoncia osteogénica periodontalmente acelerada: un estudio piloto

The aim of this study was to describe periodontal effects and treatment time of Periodontally Accelerated Osteogenic Orthodontics (PAOO) and to determine if Deoxypyridinoline could be used as a biochemical marker of bone turnover in patients undergoing PAOO. We compared 5 patients undergoing PAOO (5 males, mean age: 29.6±9.8 years) with 5 control patients undergoing self-ligating orthodontics (5 males, mean age: 28.5±6.3 years). All patients were evaluated using panoramic and lateral x-rays and CBCT and randomly selected in experimental and control groups. Both groups underwent self-ligating orthodontics using Damon Q braces. Only the experimental group underwent PAOO. The patients were evaluated periodontally at T1 (before surgery and orthodontic movement) and T2 (after orthodontic treatment). The total treatment time for the experimental group was 8.2±3.3 months and for the control group was 13.4±7.3 months. There were no differences between T2-T1 periodontal variables in either of the groups. Gingival recession was 0.49±0.26 mm at T1 and 0.42±0.3 mm at T2 in the experimental group. Gingival recession was 0.55±0.31 mm at T1 and 1.19±0.24 mm at T2 in the control group. Deoxypyridinoline urine levels showed great variance between individuals and between groups. There is a reduction in treatment time for patients undergoing PAOO with DAMON Q braces. There is no difference in the periodontal condition between PAOO and conventional orthodontics.

El objetivo de este estudio fue describir los efectos periodontales y el tiempo de tratamiento de ortodoncia osteogénica periodontalmente acelerada (OOPA) y para determinar si desoxipiridinolina podría ser utilizado como un marcador bioquímico de recambio óseo en pacientes sometidos a OOPA. Se estudiaron 5 pacientes sometidos a OOPA (hombres, edad media de 29,6±9,8 años) y 5 pacientes control sometidos a ortodoncia de autoligado (hombres, edad media de 28,5±6,3 años). Todos los pacientes fueron evaluados utilizando radiografías panorámicas y laterales, tomografía computadorizada de haz cónico, y luego distribuidos aleatoriamente en grupos experimentales y de control. Ambos grupos fueron sometidos a la ortodoncia de autoligado utilizando dispositivos ortodónticos Damon Q. Sólo el grupo experimental fue sometido a OOPA. Los pacientes fueron evaluados periodontalmente en T1 (antes de la cirugía y el movimiento de ortodoncia) y T2 (después de un tratamiento de ortodoncia). El tiempo total de tratamiento para el grupo experimental fue de 8,2±3,3 meses y para el grupo control 13,4±7,3 meses. No hubo diferencias entre las variables periodontales T2-T1 en cualquiera de los grupos. La recesión gingival en el grupo experimental fue de 0,49±0,26 mm en T1 y 0,42±0,3 mm en T2. En el grupo control, la recesión gingival fue 0,55±0,31 mm en T1 y 1,19±0,24 mm en T2. Los niveles de desoxipiridinolina en orina mostraron gran variación entre individuos y entre grupos. Hubo una reducción en el tiempo de tratamiento para los pacientes sometidos OOPA con dispositivos ortodónticos Damon Q. No hubo diferencia en la condición periodontal entre pacientes sometidos a OOPA y ortodoncia convencional.

Estudio morfológico de los labios en una población mestiza colombiana / Morphological study of the lips in a colombian population

El objetivo de esta investigación fue determinar diferencias de dimorfismo sexual de las características de labios de hombre y mujeres mestizos colombianos a través de análisis fotogramétrico. Se evaluaron fotografías frontales de 120 individuos mestizos sin alteraciones congénitas o adquiridas de los labios, tomadas en relación 1:1. A través del uso de puntos antropométricos en la vista frontal, se evaluaron las dimensiones: grosor del labio superior (Sn-Stms), grosor del bermellon superior (Stms-Ls), grosor del labio inferior (Stmi-Sml), grosor del bermellon inferior (Stmi-Li) y ancho bicomisural (Chd-Chi), con la ayuda del software J image (NIH). El análisis estadístico utilizó la prueba U Mann-Whitney usando el software SPSS 17.0, para determinar diferencias entre los dos sexos en todas las variables. No se encontraron diferencias estadísticamente significativas en la longitud del bermellón del labio superior (Stms-Ls) ni en la longitud del bermellón del labio inferior (Stmi-Li). Se encontraron diferencias estadísticamente significativas (p<0,001) en grosor del labio superior (Sn-Stms), grosor del labio inferior (Stmi-Sml) y ancho bicomisural (Chd-Chi). Estas medidas fueron mayores en individuos mestizos de género masculino. Existe dimorfismo sexual en el ancho bicomisural, longitud de labio superior e inferior en colombianos mestizos.

The aim of this research was to determine sexual dimorphism in lip characteristic in colombian male and female population through a photogrammetric study. Frontal facial photographs, in 1 to 1 scale, from 120 colombian persons without congenital or acquired lip alterations were evaluated. Using frontal landmarks, longitudinal dimensions of upper lip height (Sn-Stms), vermilion height of the upper lip (Stms-Ls), lower lip height (Stmi-Sml), vermilion height of the lower lip (Stmi-Li) and mouth width (ch-ch). J image software was user for phogrammetric analysis (NIH). For stadistical analysis U mann-whitney test was used with SPSS 17.0, in order to determine sexual dimorphism in lip characteristic. No significant sexual dimorphism was found for vermilion height of the upper lip (Stms-Ls) nor vermillion height of the lower lip (Stmi-Li). Significan sexual dimorphism was found for upper lip height (Sn-Stms), lower lip height (Stmi-Sml) and mouth width (ch-ch). All longitudinal measurements were larger in male than female. There was sexual dimorphism in lip measurements in a colombian population, when evaluated using phoptogrammetric methods.