Orthopedics

Sharper insights: Adaptive ellipse-template for robust fovea localization in challenging retinal landscapes.

Automated identification of retinal landmarks, particularly the fovea is crucial for diagnosing diabetic retinopathy and other ocular diseases. But accurate identification is challenging due to varying contrast, color irregularities, anatomical structure and the presence of lesions near the macula in fundus images. Existing methods often struggle to maintain accuracy in these complex conditions, p...

Outer lumen arterial imaging with CTA: A potential tool to diagnose vertebral artery dissection.

Differentiating vertebral artery dissection (VAD) from vertebral artery hypoplasia (VAH) can be difficult with standard CT/CTA imaging. However, making this distinction is critical to providing appropriate patient management. In this brief report/technical note, we describe a new 3D CTA postprocessing technique to potentially distinguish VAD from VAH. We describe a case of right-sided VAD, where t...

From marker to markerless: Validating DeepLabCut for 2D sagittal plane gait analysis in adults and newly walking toddlers.

The use of 3D marker-based motion analysis systems is considered the gold standard for tracking limb movements. However, these systems are expensive, ...

Multiscale metal-based nanocomposites for bone and joint disease therapies.

Bone and joint diseases are debilitating conditions that can result in significant functional impairment or even permanent disability. Multiscale meta...

Predicting lung cancer bone metastasis using CT and pathological imaging with a Swin Transformer model.

Bone metastasis is a common and serious complication in lung cancer patients, leading to severe pain, pathological fractures, and reduced quality of l...

Automated opportunistic screening for osteoporosis using deep learning-based automatic segmentation and radiomics on proximal femur images from low-dose abdominal CT.

RATIONALE AND OBJECTIVES: To establish an automated osteoporosis detection model based on low-dose abdominal CT (LDCT). This model combined a deep lea...

Feasibility of U-Net model for cerebral arteries segmentation with low-dose computed tomography angiographic images with pre-processing methods.

Subtraction computed tomography angiography (sCTA) can effectively separate enhanced cerebral arteries from similar signal intensity and proximity (i....

Molecular features and diagnostic modeling of synovium- and IPFP-derived OA macrophages in the inflammatory microenvironment via scRNA-seq and machine learning.

BACKGROUND: Osteoarthritis (OA) is the leading cause of degenerative joint disease, with total joint replacement as the only definitive cure. However,...

Classification of Grades of Subchondral Sclerosis from Knee Radiographic Images Using Artificial Intelligence.

Osteoarthritis (OA) is the most common joint disease, affecting over 300 million people worldwide. Subchondral sclerosis is a key indicator of OA. Cur...

Optimal structural characteristics of osteoinductivity in bioceramics derived from a novel high-throughput screening plus machine learning approach.

Osteoinduction is an important feature of the next generation of bone repair materials. But the key structural factors and parameters of osteoinductiv...

Comparison of CNNs and Transformer Models in Diagnosing Bone Metastases in Bone Scans Using Grad-CAM.

PURPOSE: Convolutional neural networks (CNNs) have been studied for detecting bone metastases on bone scans; however, the application of ConvNeXt and ...

Attention LinkNet-152: a novel encoder-decoder based deep learning network for automated spine segmentation.

Segmenting the spine from CT images is crucial for diagnosing and treating spine-related conditions but remains challenging due to the spine's complex...

Comparing machine learning models for predicting preoperative DVT incidence in elderly hypertensive patients with hip fractures: a retrospective analysis.

Hip fractures in the elderly present a significant public health challenge globally, especially among patients with hypertension, who are at an increa...

Comparative analysis of ChatGPT-4o mini, ChatGPT-4o and Gemini Advanced in the treatment of postmenopausal osteoporosis.

BACKGROUND: Osteoporosis is a sex-specific disease. Postmenopausal osteoporosis (PMOP) has been the focus of public health research worldwide. The pur...

Use of Artificial Intelligence on Imaging and Preoperatory Planning of the Knee Joint: A Scoping Review.

: This scoping review explores the current state of the art of AI-based applications in the field of orthopedics, focusing on its implementation in di...

A prediction model of pediatric bone density from plain spine radiographs using deep learning.

Osteoporosis, a bone disease characterized by decreased bone mineral density (BMD) resulting in decreased mechanical strength and an increased fractur...

Identification of aging-related biomarkers for intervertebral disc degeneration in whole blood samples based on bioinformatics and machine learning.

INTRODUCTION: Aging is characterized by gradual structural and functional changes in the body over time, with intervertebral disc degeneration (IVDD) ...

Exploratory cluster analysis of IL2Ra and associated biomarkers and complications after blunt chest trauma.

BACKGROUND: Rib fractures compromise approximately 40% of all fractures in the United States. Despite their prevalence, the relationship between rib f...

Identification and Validation of Circadian Rhythm-Related Genes Involved in Intervertebral Disc Degeneration and Analysis of Immune Cell Infiltration via Machine Learning.

BACKGROUND: Low back pain is a significant burden worldwide, and intervertebral disc degeneration (IVDD) is identified as the primary cause. Recent re...

Learning-based 3D human kinematics estimation using behavioral constraints from activity classification.

Inertial measurement units offer a cost-effective, portable alternative to lab-based motion capture systems. However, measuring joint angles and movem...