Privacy-preserving dementia classification from EEG via hybrid-fusion EEGNetv4 and federated learning.

As global life expectancy rises, a growing proportion of the population is affected by dementia, particularly Alzheimer's disease (AD) and Frontotemporal dementia (FTD). Electroencephalography (EEG) based diagnosis presents a non-invasive, cost effective alternative for early detection, yet existing methods are challenged by data scarcity, inter-subject variability, and privacy concerns. This study proposes lightweight and privacy-preserving EEG classification framework combining deep learning and Federated Learning (FL).

Detection and Recognition of Bilingual Urdu and English Text in Natural Scene Images Using a Convolutional Neural Network-Recurrent Neural Network Combination with a Connectionist Temporal Classification Decoder.

Urdu and English are widely used for visual text communications worldwide in public spaces such as signboards and navigation boards. Text in such natural scenes contains useful information for modern-era applications such as language translation for foreign visitors, robot navigation, and autonomous vehicles, highlighting the importance of extracting these texts. Previous studies focused on Urdu alone or printed text pasted manually on images and lacked sufficiently large datasets for effective model training.

Prognostic value of CMR parametric mapping in cardiac amyloidosis: an updated systematic review and meta-analysis.

Background: Cardiac amyloidosis (CA) is the leading cause of mortality in systemic amyloidosis, highlighting the need for accurate risk assessment to guide patient management. While the diagnostic value of cardiac MR (CMR) parametric mapping is well established, its prognostic utility remains inconsistent across studies. To perform a systematic review and meta-analysis to evaluate the prognostic value of CMR parametric mapping in predicting all-cause mortality, heart failure hospitalisation and major adverse cardiovascular events in patients with CA.

A programmed decline in ribosome levels governs human early neurodevelopment.

Many neurodevelopmental defects are linked to genes involved in housekeeping functions, such as those encoding ribosome biogenesis factors. How reductions in ribosome biogenesis can result in tissue- and developmental-specific defects remains unclear. Here we describe variants in the ribosome biogenesis factor AIRIM/C1orf109 that are primarily associated with neurodevelopmental disorders.

NAV3 Missense Variant in a Homozygous State: Strengthening Links to Neurodevelopmental Disorder.

Introduction: Neurodevelopmental disorders (NDDs) represent a diverse and heterogeneous group of conditions, including neurodevelopmental delay (NDD), autism spectrum disorder (ASD), and neurodevelopmental encephalopathy with epilepsy (NDEE). While these disorders often share phenotypic similarities, their underlying genetic causes can vary widely, making clinical diagnosis challenging.

Methods: In this study, we performed whole-genome sequencing (WGS) on a family having an autosomal recessive neurodevelopmental disorder.

OculusNet: Detection of retinal diseases using a tailored web-deployed neural network and saliency maps for explainable AI.

Retinal diseases are among the leading causes of blindness worldwide, requiring early detection for effective treatment. Manual interpretation of ophthalmic imaging, such as optical coherence tomography (OCT), is traditionally time-consuming, prone to inconsistencies, and requires specialized expertise in ophthalmology. This study introduces OculusNet, an efficient and explainable deep learning (DL) approach for detecting retinal diseases using OCT images.

Retraction notice to "The potential impact of digital economy on energy poverty in the context of Chinese provinces" [Heliyon 10 (2024) e30140].

[This retracts the article DOI: 10.1016/j.heliyon.

Diagnostic performance of cardiovascular magnetic resonance parametric mapping as per modified Lake Louise Criteria in acute myocarditis: an updated systematic review and meta-analysis.

Background: Cardiovascular magnetic resonance mapping parameters-native T1 mapping, T2 mapping, and extracellular volume (ECV)-are key for diagnosing acute myocarditis under the modified 2018 Lake Louise Criteria (mLLC). This systematic review and meta-analysis evaluated their diagnostic performance and established optimal thresholds for acute myocarditis.

Methods: We reviewed articles published in the past decade utilizing parametric mapping for myocarditis diagnosis.

Case Report: Hypomyelinating Leukodystrophy Type 20 (HLD20) With Novel CNP Gene Variant.

This case report describes a child with hypomyelinating leukodystrophy type 20 (HLD20), a rare neurodegenerative disorder characterized by impaired myelin formation. The patient presented with multiple neurodevelopmental abnormalities, including delayed motor milestones, seizures, and abnormal facial features. Genetic analysis identified a novel homozygous variant, c.

Enhanced glaucoma classification through advanced segmentation by integrating cup-to-disc ratio and neuro-retinal rim features.

Glaucoma is a progressive eye condition caused by high intraocular fluid pressure, damaging the optic nerve, leading to gradual, irreversible vision loss, often without noticeable symptoms. Subtle signs like mild eye redness, slightly blurred vision, and eye pain may go unnoticed, earning it the nickname "silent thief of sight." Its prevalence is rising with an aging population, driven by increased life expectancy.

Decentralized EEG-based detection of major depressive disorder via transformer architectures and split learning.

Introduction: Major Depressive Disorder (MDD) remains a critical mental health concern, necessitating accurate detection. Traditional approaches to diagnosing MDD often rely on manual Electroencephalography (EEG) analysis to identify potential disorders. However, the inherent complexity of EEG signals along with the human error in interpreting these readings requires the need for more reliable, automated methods of detection.

Plasma loaded uniaxial chiral slab waveguide.

In this study, numerical analysis has been carried out at plasma loaded uniaxial chiral slab waveguide. The formulation is based on differential form of Maxwell's equations and characteristics equation is obtained by employing boundary conditions at uniaxial chiral-plasma-uniaxial. Two cases of uniaxial chiral media i.

A Novel Loss of Function Variant in Gene Underlies Early Infantile Epileptic Encephalopathy 24 [EIEE24].

Background: Early infantile epileptic encephalopathy (EIEE) is a rare neurological condition characterized by frequent seizures in the early stages of life, resulting in severely impaired cognitive and motor development. Although the specific causes of EIEE remain unknown, one of the primary causes is gene pathogenicity (even in the absence of consanguinity). Hyperpolarization-activated cyclic nucleotide-gated channels (HCNs) are essential for proper brain function.

Development of New Dual-Purpose Environmental Strategies for Effective Antibiotic Degradation Using Red Mud-Based Fenton Oxidation Catalysts.

Mitigating antibiotic pollution is essential to combating antibiotic resistance, safeguarding ecosystems, ensuring food and water safety, and preserving the efficacy of antibiotics. Simultaneously, the comprehensive utilization of red mud is a key approach to reducing resource waste and ecological damage. This study investigates the use of iron components from red mud to prepare RM-nZVI/Ni for Fenton-like reactions, aimed at degrading antibiotics in water.

Eco-friendly hemp woven (two-dimensional and three-dimensional) fabrics for tear and puncture protection; an approach for comfort and ergonomics.

. Two-dimensional (2D) woven fabrics are inefficient in exhibiting viable thermal comfort and protective function in high-tech applications that govern a need for three-dimensional (3D) weaves. Such 3D fabrics offer superior performance over 2D fabrics; however, no study has reported the simultaneous comparison of thermal and protective performance properties of 2D and 3D structures with equal thread densities.

Management Algorithm for Atypical Lipomatous Tumours: A Retrospective Case Series.

Introduction: Atypical lipomatous tumours (ALTs), or low-grade well-differentiated liposarcomas (WDLs), can be identified using radiological complex septations and histological atypia. In our view, this is a confusing name that underestimates the risk of local recurrence of such tumours. Defining a management algorithm for differentiating a lipoma from an ALT is important for considering the best management of these patients.

Cross-Platform Analysis of Mammography Narratives: A Comparative Study on Social Media Engagement.

Purpose: This study examines the representation of mammography on social media platforms, specifically, X (Twitter), Facebook, TikTok, and Instagram, from 2006 to 2023. X (Twitter) went public in 2006, Facebook in 2004, Instagram in 2012, and TikTok in 2018 (after merging with Musical.ly).

Leveraging deep learning for toxic comment detection in cursive languages.

Social media platforms enable individuals to publicly express opinions, support, and criticism. Influencers can launch campaigns to promote ideas. Most people can now share their views and feelings through visual or textual comments, which can range from appreciation to hate speech, potentially inciting societal violence and hatred.

Extracellular volume fraction and native T1 mapping in diabetic cardiomyopathy: a comprehensive meta-analysis.

Background: Type 2 diabetes mellitus (T2DM) is associated with myocardial fibrosis (MF), a major contributor to adverse cardiovascular outcomes. Cardiovascular magnetic resonance (CMR), specifically extracellular volume fraction (ECV) and native T1 mapping, offers a non-invasive approach to quantify MF. This study aims to evaluate the utility of ECV and native T1 mapping as biomarkers for cardiac fibrosis and to assess their relationship with diabetes severity, measured by hemoglobin A1C (HbA1C), in patients with T2DM.

Cardiac Amyloidosis: A Comprehensive Review of Imaging Findings.

Cardiac amyloidosis is an infiltrative cardiomyopathy caused by the deposition of insoluble amyloid fibrils in the myocardium, leading to abnormal cardiac function and heart failure. Diagnosis is often challenging due to its diverse symptoms and related comorbidities. Although endomyocardial biopsy is the gold standard for diagnosis, a complete diagnostic approach often includes non-invasive methods such as Cardiac Magnetic Resonance (CMR) and nuclear medicine techniques.

Nutraceutical Impact of Pumpkin Seed Oil on Expression Levels of EZH-2 and KRT-14 Genes against DSS-induced Inflammatory Bowel Disease in the Rat Model.

Inflammatory bowel disease is a collection of intestinal disorders that cause inflammation in the digestive tract. Prolonged inflammation in the gastrointestinal tract is a major risk factor for colorectal cancer. The objective of this study was to fucus on gene expression levels of (KRT-14; associated with epithelial cell integrity) and enhancer of zeste homolog-1 (EZH-2; involved in cellular proliferation) in a IBD rat model in order to rule out impact of nutraceuticals (pumpkin seed oil; PSO) as a complementary approach to conventional treatments of IBD.

Truncated SPAG9 as a novel candidate gene for a new syndrome: Coarse facial features, albinism, cataract and developmental delay (CACD syndrome).

Sperm-associated antigen 9 (SPAG9) is a member of cancer-testis antigen, having characteristics of a scaffold protein, which is involved in the c-Jun N-terminal kinase JNK signaling pathway, suggesting its key involvement in different physiological processes, such as survival, apoptosis, tumorigenesis, and cell proliferation. We identified two families (A and B) having multisystem features like coarse facial features, albinism, cataracts, skeletal abnormalities, and developmental delay. Whole genome sequencing (WGS) in families A and B revealed a homozygous frameshift variant (c.

Pixels to precision: Neuroradiology's leap into 3D printing for personalized medicine.

The realm of precision medicine, particularly its application within various sectors, shines notably in neuroradiology, where it leverages the advancements of three-dimensional (3D) printing technology. This synergy has significantly enhanced surgical planning, fostered the creation of tailor-made medical apparatus, bolstered medical pedagogy, and refined targeted therapeutic delivery. This review delves into the contemporary advancements and applications of 3D printing in neuroradiology, underscoring its pivotal role in refining surgical strategies, augmenting patient outcomes, and diminishing procedural risks.