All stories

1338 published stories · page 32 of 90

HealthEvidence-backed gain

EndoVLM: A Vision-Language Assistant for Gastrointestinal Endoscopy

Gastrointestinal endoscopy generates extensive high-resolution video data, posing significant challenges for efficient and accurate computer-aided diagnosis of gastrointestinal diseases. To address this, we propose EndoVLM (Endoscopy Vision-Language Model), a specialized visual question-answering assistant for gastroenterology. EndoVLM introduces ConvNeXt as a hierarchical visual encoder to replace traditional ViTs (Vision Transformers), inherently compressing high-resolution gastrointestinal endoscopy images in…

Journal of Imaging Informatics in Medicine

Evidence-backed gain

Deep Learning-Based Classification of NIFTP and Invasive Encapsulated Follicular Variant of Papillary Thyroid Carcinoma Using Gross Pathology Images

Evidence-backed gain

AI-Enabled Real-World Evidence in Oncology: A Statistical Perspective for Regulatory Decisions

Both readings

Reinventing the echocardiography workflow: from manual quantification to artificial intelligence-driven comprehensive interpretation

Both readings

Naïve adaptive immune receptor repertoires in celiac disease assessed by machine learning; impact of the HLA-DQ2.5 allotype on the TCR repertoire

The adaptive immune receptor repertoire (AIRR) - the collection of an individual's B-cell and T-cell receptors (BCRs and TCRs, respectively) - encodes cumulative immune history and is shaped by both germline genetics and environmental exposures. Skewed repertoires have been linked to infections, vaccination responses and autoimmune diseases such as celiac disease (CeD) where biased usage of immunoglobulin and T-cell receptor genes reactive to disease relevant antigens has been reported. Motivated by evidence tha…

Evidence-backed problem

Surprising AI breakthroughs raise soul-searching questions for mathematicians | Letter

I share Kasra Rafi and Bruce Schneier’s impression that recent mathematical breakthroughs by AI consist in clever recombination of existing ideas, not development of truly novel theory (No, AI doesn’t mean the end of mathematics – at least not yet, 25 August). The question is: what happens to mathematics if this changes? Like many mathematicians, I have done much soul-searching in recent weeks, especially since a key problem in my own field of group theory (the existence of non-sofic groups) was solved this mont…

Evidence-backed problem

HARMONY IN THE SCALE: PROTECTION OF MUSICAL WORKS IN THE DIGITAL AGE

The article is devoted to a comprehensive analysis of modern problems of protecting musical works in the context of the rapid development of digital technologies. The author considers the transformation of the music industry from analog media to online platforms, focusing on the scale of legal and illegal distribution of content, as well as the emergence of new threats in the form of streaming piracy, illegal copying, the use of AI, and digital remixing. The work presents the evolution of the copyright system —…

Evidence-backed gain

Pulmonary Artery-to-Vein Volume Difference: A New Imaging Biomarker for Risk Stratification in Acute Pulmonary Embolism

Rationale and objectives To propose a new imaging biomarker, the pulmonary artery-to-vein volume difference (PAVVD), and evaluate its efficacy in risk stratification of acute pulmonary embolism (APE) compared with traditional computed tomography pulmonary angiography (CTPA) parameters, as well as the impact of chronic pulmonary disease (CPD). Materials and methods This retrospective study included 134 patients with APE (high/intermediate-high risk, n = 46; intermediate-low/low risk, n = 88) from April 2023 to Ma…

Health

International Application of Artificial Intelligence for Lesion Detection on Digital Breast Tomosynthesis: Comparing Western and Eastern Databases

Rationale and objectives The international application of artificial intelligence (AI) for lesion detection based on digital breast tomosynthesis (DBT) is limited due to disease variations among populations. We hypothesized that lesion detection models trained on either the Western or Eastern DBT dataset would exhibit reduced performance on another dataset. We proposed transfer learning to enhance lesion detection across DBT databases. Materials and methods The Western database (94 patients) was obtained from th…

Health

Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach

Rationale and objectives To address the challenge of preoperative prediction of synchronous liver metastasis (LM) in pancreatic cancer (PC), we developed and validated machine learning models integrating clinical and computed tomography (CT) radiomics features, and compared the performance and interpretability of linear (linear discriminant analysis [LDA]) versus nonlinear (multilayer perceptron [MLP]) architectures. Materials and methods This retrospective study enrolled 340 patients with pancreatic ductal aden…

Health

Attitudes, perceptions, and UTAUT-based factors influencing the acceptance of medical artificial intelligence among Chinese oncology healthcare professionals: a national cross-sectional survey

Objectives To conduct a nationwide survey among professionals working in oncology departments in China to investigate their attitudes, perceptions, and experiences regarding medical artificial intelligence (AI), and to explore and compare the factors influencing AI behavioral intention (BI; willingness to adopt AI) between physicians and nurses using the Unified Theory of Acceptance and Use of Technology (UTAUT). Materials and methods A nationwide cross-sectional survey was conducted among professionals in oncol…

Health

An Explainable Computer-Aided Framework for Skin Lesion Classification Using Deep Learning

The utilization of deep convolutional neural networks for the purpose of diagnosing diseases in the skin area has proven to yield similar accuracy levels to those obtained by dermatologists in different studies. Nevertheless, many challenges are still present, including underperformance and poor generalization in some cases, as well as low interpretability related to the use of black box models. This creates major obstacles for practical implementation since it requires explainability in addition to accurate dia…

Health

Deep Learning for Synthetic Postcontrast T1-Weighted MRI: A Systematic Review With Targeted Meta-Analysis of Brain Tumor Studies

BACKGROUND . Gadolinium-based contrast agents remain essential for MRI but carry risks. Deep learning (DL) methods have emerged as a potential approach for synthesizing postcontrast T1-weighted images from precontrast sequences alone. OBJECTIVE . The objective of the present study was to systematically review DL-based synthesis of postcontrast T1-weighted MRI, characterize model architectures and evaluation practices across subspecialties, and perform targeted meta-analysis where sufficient literature existed. E…

Science

Separation of coeluted compounds in capillary gas chromatography: customization via machine learning retention time prediction

Gas Chromatography is a versatile separation technique widely used in analytical chemistry for constituent determination. However, gas chromatography compound identification is not directly feasible unless the method is coupled with complementary techniques such as mass spectrometry or with referencing methods like retention indices. Statistical retention time prediction of compounds based on the gas chromatography experimental and instrumental parameters could facilitate the gas chromatography characterization…

Health

AI-ICE Guided Pulsed Field Ablation of Atrial Fibrillation with Variable Loop Circular Catheter

Background Intracardiac echocardiography (ICE) facilitates left atrial (LA) reconstruction during atrial fibrillation (AF) ablation. The artificial intelligence-based CARTOSOUND FAM (AIFAM) module enables automated three-dimensional LA reconstruction without the need for a dedicated pre-ablation mapping catheter. While this workflow has been described previously in radiofrequency ablation, its application and outcome in pulsed field ablation (PFA) remains limited. Objective To evaluate the feasibility, safety, a…