Результаты поиска

Peripheral arterial disease classification using machine learning and multi-point photoplethysmography.

OBJECTIVE: The current proof-of-concept study aimed to classify peripheral arterial disease (PAD) using machine learning (ML) based on single-point and multi-point photoplethysmography (PPG) signals. The aims were: 1) Identifying the most informative feature categories for PAD classification and 2) Evaluating whether multi-point PPG improves diagnostic accuracy by capturing vascular differences across limb sites. METHODS: PPG data were collected from 60 subjects at 12 anatomical sites on both feet, resulting in 36 features for single-point and 336 features for multi-point analysis. Feature ca…

Molecular classification of primary Sjögren's syndrome based on salivary gland omics.

Primary Sjögren's syndrome is a complex and heterogeneous disease, often involving multiple organ systems and carrying an increased risk of lymphoma development. In this study, we integrated single-cell RNA sequencing and bulk RNA-seq data to deconvolute the disease heterogeneity using non-negative matrix factorization.This analysis identified four distinct molecular subtypes, which we designated as the Classical Immune Type, Ion Channel Type, Fibrotic Senescent Type, and Immune Desert Type. Through differential expression analysis, we further identified characteristic gene sets for each of th

Understanding cholangiocarcinoma: molecular landscape, pathological classification, and challenges in biopsy diagnosis.

Characterization of molecular features of cholangiocarcinoma (CCA) has questioned the traditional, anatomy-based classification scheme and has alternatively suggested biology-based classifications. Intrahepatic CCA has been classified into small-duct and large-duct types, and the latter is histologically and molecularly almost identical to perihilar CCA. Although distal and perihilar CCA have been classified together, they have different molecular abnormalities, with MDM2 amplification observed in 15% of perihilar CCA cases but in none of the distal CCA cases. FGFR2 and IDH1 are two main drug …

Revised porcine IgG subclass classification based on innate immune cell activation.

The current classification of porcine immunoglobulin G (IgG) subclasses relies on phylogenetic analysis of gene sequences, resulting in a nomenclature that is inapt to predict biological function. Here, we propose a revised, functionality-based nomenclature derived from a comprehensive re-analysis of Fc domain interaction motifs and in vitro effector function assays. We produced twelve recombinant porcine IgG subclasses and evaluated their ability to induce reactive oxygen species (ROS) production in porcine monocytes and neutrophils. Our results reveal a striking functional dichotomy: only th…

EGID: A Comprehensive Multi-label Endoscopic Image Dataset for Gastritis Classification.

Chronic atrophic gastritis is a well-recognized precancerous condition, emphasizing the need for accurate endoscopic classification. However, existing endoscopic datasets lack comprehensive multi-dimensional annotations for systematic gastritis classification. We present the Endoscopic Gastritis Image Dataset (EGID), comprising 5,883 high-quality white-light endoscopic images from 229 patients retrospectively collected at Renji Hospital, Shanghai, using the Olympus CV-290 system between March and November 2024. Each patient's images are systematically annotated across four independent clinical…

From Sjögren syndrome to Sjögren disease: rethinking classification and diagnostic complexity.

Sjögren syndrome (SS), traditionally regarded as a sicca-predominant condition, is now recognized as a systemic autoimmune disease characterized by type I interferon activation, B-cell hyperactivity, and periepithelial lymphocytic infiltration. This conceptual shift has prompted changes in terminology, with "SS" increasingly replaced by "Sjögren disease (SjD)" and "secondary SS" by "associated SjD," reflecting the concept of polyautoimmunity and ensuring equal clinical standing. In this review, we trace the historical evolution of SS classification criteria and examine their limitations in rea…

Classification of bacterial images obtained optically using some pre-trained models.

Rapid and accurate detection of water-borne bacteria is critical for safeguarding public health and preventing the spread of infections. Conventional bacterial identification techniques are often time-consuming, resource-intensive, and require specialized personnel, limiting their suitability for automated water-quality monitoring. This study presents an optical detection and classification framework that uses some pre-trained architectures to automatically classify optically acquired images of water-borne bacterial pathogens. The system distinguishes among four classes: Escherichia coli (E. c…

Genomic and Phenotypic Classification of Staphylococcus Species Isolated From Delhi Air.

To understand the prevalence of opportunistic bacterial pathogens in the bioaerosols, outdoor air-sampling was performed during the peak season of air pollution prior to the onslaught of the COVID-19 pandemic in the national capital of India, Delhi, during the month of November 2019. Employing a sophisticated plate exposure technique using the Merck Mas Eco-100 instrument, culturable bacterial samples were collected from six locations in Delhi. Among the identified bacterial samples, multiple species of the opportunistic pathogen Staphylococcus, namely, S. gallinarum, S. haemolyticus, and S. a

Rapid classification of live bacteria in blood using antimicrobial peptide microarrays.

The growing threat of antimicrobial resistance has made rapid and sensitive detection of bacterial pathogens in human samples an urgent need … crobial peptides (AMPs) and designed de novo peptides as powerful ligands for single-step bacterial classification using surface plasmon resonance imaging (SPRi). Human blood samples were spiked with low levels (less than 30 CFU ml-1) of clinically relevant pathogens: E. coli O157:H7 and E. coli O1:K1:H7 as Gram-negative species, as well as methicillin-resistant …

Тенсорная диффузия МРТ и NODDI в классификации множественных склерозов.

СПРАВОЧНАЯ ИНФОРМАЦИЯ: Многокамерные модели диффузии и многокамерные приобретения все чаще используются для преодоления ограничений, связанных с обычной диффузионной тенсорной съемкой, но требуют более длительных сканирования и более сложной обработки. В то же время исследования по диффузионной классификации МРТ часто основываются на узком наборе тенсорных метрик, особенно на фракционной анизотропии. Мы изучили вопрос о том, может ли более широкое использование настольных элементов, включая дескрипторы формы, улучшить классификацию без повышения сложности приобретения.МЕТОДЫ: МРИ с несколькими

Совпадение в аннотации оригинала
BACKGROUND: Multi-compartment diffusion models and multi-shell acquisitions are increasingly used to overcome limitations of conventional diffusion tensor imaging, but require longer scans and more complex processing. Meanwhile, diffusion MRI classification studies often rely on a narrow set of tensor-derived metrics, especially fractional anisotropy. We inv…

Histological classification of uterine cervical adenocarcinomas: Its alteration and current status.

Adenocarcinomas (ADCs) of the uterine cervix are relatively minor compared to squamous cell carcinomas. However, ADCs are histologically and … attracted attention since gastric-type ADC (g-ADC) was introduced in the World Health Organization Classification 4th ed. (2014). Occasional HA-ADCs and HI-ADCs, including HA-AIS and HI-AIS, require p16 immunostaining, in situ hybridization, or HPV testing to differentiate between them because morphological features alone cannot often be conclusive for the diag …

Spatio-temporal independent component classification for localization of seizure onset zone.

Localization of the epileptic seizure onset zone (SOZ) as a step in presurgical planning leads to higher efficiency in surgical and stimulation treatments. However, the clinical localization procedure is a difficult, long procedure with increasing challenges in patients with complex epileptic foci. The interictal methods have been proposed to assist in presurgical planning with simpler procedures for data acquisition and higher speeds. In this study, spatio-temporal component classification (STCC) is presented for the localization of epileptic foci using resting-state functional magnetic reson…

Tumor classification of adenoid cystic carcinoma: systematic review and meta-analysis.

Adenoid Cystic Carcinoma - ACC is a common neoplasm in major and minor salivary glands with a high risk of metastasis. Thus, the objective of the present study was to perform an analysis to better understand the histological grading systems of the ACC and its influence on tumor prognosis in terms of overall survival, disease-free and metastasis-free. This is a systematic review, with meta-analysis, based on the PRISMA parameters. The search was carried out by two independent examiners, and searches were performed in the PubMed, Web of Science, Scopus, Science Direct, and Google Scholar databas

Collaborative multitasking framework for enhanced hippocampus segmentation and Alzheimer's disease classification.

The early diagnosis of Alzheimer's disease has faced significant challenges, as the initial patients have hidden symptoms that are difficult to distinguish from conventional symptoms. In view of this, this article designs a collaborative multitasking algorithm framework that implements a positive feedback loop between classification tasks, significantly improving processing accuracy. Specifically, the algorithm consists of three sub networks: the initial segmentation sub network accurately identifies the hippocampus boundary and generates the initial segmentation mask; The classification subne…

Enhanced deep Convolutional Neural Network for SARS-CoV-2 variants classification.

INTRODUCTION: Rapid and scalable classification of SARS-CoV-2 genomes from spike-gene sequences can support real-time genomic surveillance in contexts where whole-genome data or high-end computing resources are limited. METHODS: We curated approximately 35,800 quality-filtered spike sequences spanning multiple clades and lineages and trained a hybrid CNN-BiLSTM model with standard regularization and class-imbalance handling. Model performance was benchmarked against Nextclade assignments and compared with classical machine-learning baselines. RESULTS: Across 10 experimental runs, the model a…

Glaucoformer: Dual-Domain Global Transformer Network for Generalized Glaucoma Stage Classification.

Classification of glaucoma stages remains challenging due to substantial inter-stage similarities, the presence of irrelevant features, and subtle lesion size, shape, and color variations in fundus images. For this purpose, few efforts have recently been made using traditional machine learning and deep learning models, specifically convolutional neural networks (CNN). While the conventional CNN models capture local contextual features within fixed receptive fields, they fail to exploit global contextual dependencies. Transformers, on the other hand, are capable of modeling global contextual in…

Classification of pulmonary diseases from chest radiographs using deep transfer learning.

Pulmonary diseases are the leading causes of disabilities and deaths worldwide. Early diagnosis of pulmonary diseases can reduce the fatality rate. Chest radiographs are commonly used to diagnose pulmonary diseases. In clinical practice, diagnosing pulmonary diseases using chest radiographs is challenging due to Overlapping and complex anatomical Structures, variability in radiographs, and their quality. The availability of a medical specialist with extensive professional experience is profoundly required. With the use of Convolutional Neural Networks in the medical field, diagnosis can be imp

Multi-modal classification of retinal disease based on convolutional neural network.

Retinal diseases such as age-related macular degeneration and diabetic retinopathy will lead to irreversible blindness without timely diagnosis and treatment. Optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) images provide complementary views of the retina, and the integration of the two imaging modalities can improve the accuracy of retinal disease classification. We propose a multi-modal classification model consisting of two branches to automatically diagnose retinal diseases, in which OCT and OCTA images are efficiently integrated to improve both the a…

Dry eye: A hospital-based sociodemographic, risk and clinical classification profile.

BACKGROUND: Dry eye, a multifactorial disease of the tears and ocular surface, is considered a significantly growing public health problem worldwide. AIM: This study aimed to determine the prevalence and risk factors of dry eye disease (DED) in a population attending an eye hospital in KwaZulu-Natal, South Africa. SETTING: The study was conducted at McCord Provincial Eye Hospital in Durban, KwaZulu-Natal, South Africa. METHODS: A cross-sectional hospital-based study was conducted between July 2023 and August 2023. Diagnosis was confirmed with a SPEED score of ≥ 4 and a monocular tear break