Radiology

Point-of-care ultrasound in the modern era of emergency medicine: a narrative review of the recent literature.

PURPOSE OF REVIEW: Point-of-care ultrasound (POCUS) has transformed emergency medicine by providing a noninvasive, accessible, repeatable, efficient, and cost-effective imaging tool to the bedside. This article is a narrative review of the most impactful POCUS literature over the past 18 months, identifying and highlighting the most common emerging themes. RECENT FINDINGS: We identified five main ...

Fuzzy rough set loss for deep learning-based precise medical image segmentation.

Accurate segmentation of medical images is crucial for diagnosis and treatment planning, yet it remains challenging due to ambiguous lesion boundaries, class imbalance, and complex anatomical structures. We propose a novel Fuzzy Rough Set-inspired (FRS) loss function that addresses these challenges by integrating pixels' fuzzy similarity relations with a boundary uncertainty model in a convex comb...

A Multimodal Neuro-Demographic Signature for Immuno-Metabolic Depression.

BACKGROUND: The underlying neurobiology of a recently described immuno-metabolic depression (IMD) subtype of major depressive disorder (MDD), characte...

Dosimetric assessment of deep learning based organ-at-risk segmentation: insights from the HaN-Seg challenge.

BACKGROUND AND PURPOSE: To extend the previously reported geometric analysis of HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challe...

Aperiodic parameters of the fMRI power spectrum associate with preterm birth and neonatal age.

Perinatal period is a critical time for brain development and premature-born children have an elevated likelihood for neurodevelopmental conditions. W...

Are diagnostic technologies for alzheimer's disease and dementia cost-effective? A systematic review of economic evaluations.

BACKGROUND: Alzheimer's disease (AD) and dementia pose a significant clinical and economic burden globally. Early diagnosis and intervention can poten...

Full-Endoscopic Spine Surgery for Adjacent Segment Disease Using Artificial Intelligence-Assisted 3-Dimensional MRI/CT Fusion Imaging: A Case Report.

CASE: An 82-year-old woman presented with right medial thigh pain. Her medical history included multiple lumbar decompression and fusion surgeries. Sh...

Channel-wise joint disentanglement representation learning for B-mode and super-resolution ultrasound based CAD of breast cancer.

B-mode ultrasound (BUS) is widely used in breast cancer diagnosis, while the emerging super-resolution ultrasound (SRUS) provides microvascular inform...

Imaging mammalian lipids using desorption electrospray ionization mass spectrometry: A review.

Desorption electrospray ionization mass spectrometry imaging (DESI-MSI) has become an essential tool for spatial lipidomic profiling since its introdu...

On the transfer learning behavior of domain-specific vision-language models in screening mammography.

Vision-Language models have shown remarkable performance for natural images and text. Given the homology of the anatomy, high gray-scale image dimensi...

Haar-initialized parametric wavelet compression with attention-driven lightweight CNN for brain tumor classification on edge devices.

This paper presents a lightweight hybrid framework that integrates a Haar-initialized Parametric Wavelet Transform (PWT) with a Convolutional Neural N...

The application of artificial intelligence in blind ultrasound sweep diagnostics for prenatal medicine: A systematic literature review.

INTRODUCTION: Obstetric ultrasound is fundamental in prenatal care for gestational age (GA) estimation, fetal monitoring, and complication screening. ...

A review of current applications of photon-counting CT in musculoskeletal imaging.

Photon-counting computed tomography (PCCT) is a significant technological advancement in musculoskeletal imaging. Unlike traditional CT detectors, whi...

Machine Learning Prediction of Incomplete Hysteroscopic Myomectomy Using Preoperative Clinical and Imaging Variables.

STUDY OBJECTIVE: To develop and validate a machine-learning (ML) model using preoperative clinical and imaging variables including ultrasound and diag...

Refined query network (RQNet) for precise MRI segmentation and robust TED activity assessment.

Objective.To develop an efficient deep learning framework for precise three-dimensional (3D) segmentation of complex orbital structures in multi-seque...

Radiological and biological dictionary of radiomics features: addressing understandable AI issues in personalized breast cancer; dictionary version BM1.0.

Objective.Radiomics-based artificial intelligence (AI) models show potential in breast cancer diagnosis but lack interpretability. This study bridges ...

Machine learning-based prediction of central lymph node metastasis in unifocal papillary thyroid microcarcinoma.

OBJECTIVE: This study aims to develop a machine learning (ML) model to predict the risk of central lymph node metastasis (CLNM) in patients with papil...

Artificial intelligence-based software to support mechanical thrombectomy transfer decision in low-volume primary stroke centers: a multicenter, retrospective study.

INTRODUCTION: To assess the potential benefit of artificial intelligence (AI) based imaging software in supporting mechanical thrombectomy (MT) transf...

Lung scintigraphy for the diagnosis of acute pulmonary embolism.

Pulmonary embolism (PE) remains a major diagnostic challenge due to its potentially life-threatening nature and the clinical burden associated with an...

Contemporary implantable cardiac device trials for sudden cardiac death and future guidelines: how can we shape the future?

INTRODUCTION: Sudden cardiac death (SCD) remains a major cause of mortality despite substantial progress in heart failure management and arrhythmia pr...