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.

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.

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%.

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%.

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.