Enhancing Image Classification of Esophagogastroduodenoscopy Images through Synthetic Data Augmentation
Synthetic data augmentation using class-specific Variational Autoencoders (VAEs) and latent space interpolation can significantly improve the classification accuracy of esophagogastroduodenoscopy (EGD) images, especially for underrepresented classes, by addressing data scarcity and imbalance.
Automated Segmentation of Skeletal Muscle, Visceral Adipose Tissue, and Subcutaneous Adipose Tissue from 2D MRI Scans at the L3 Vertebral Level
Automated segmentation of skeletal muscle, visceral adipose tissue, and subcutaneous adipose tissue from 2D MRI scans at the L3 vertebral level using DAFS Express software shows high accuracy and reliability compared to manual segmentation.
A Comprehensive Library of Over 2,500 Personalized Digital Twins Derived from CT Scans
A framework for generating a large and diverse library of highly detailed, patient-specific anatomical models, representing human digital twins for research in medical imaging.
Enhancing Synthetic Computed Tomography Generation from Magnetic Resonance Imaging through Subvolume Merging
Subvolume merging technique effectively mitigates stitching artifacts in synthetic computed tomography (sCT) generated from magnetic resonance imaging (MRI), leading to improved image quality.
Nailfold Capillaroscopy Reveals Distinct Capillary Changes in Nail Diseases
Nailfold capillaroscopy can identify specific capillary abnormalities associated with various nail conditions, providing a potential non-invasive diagnostic tool.
Improving Hemarthrosis Detection Accuracy through Data Augmentation: A Comparative Study of Synthetic and Traditional Techniques
Two data augmentation methods, synthetic data generation and traditional image transformations, can improve the accuracy of machine learning models in detecting hemarthrosis, a key symptom of hemophilia.
Optimizing Pancreas Segmentation from Imperfectly Registered Multimodal MRI through Early, Middle, and Late Fusion Strategies
Fusion of complementary information from imperfectly registered multimodal MRI can improve pancreas segmentation, but the optimal fusion location is model-specific and gains are small.
False-Positive Mammogram Results Linked to Reduced Screening Rates in Subsequent Years
False-positive mammogram results can lead to a significant decrease in the likelihood of women returning for future routine breast cancer screenings.
Automated CT Scans Reveal Hidden Diabetes Risks: A Large-Scale Study
Automated analysis of CT-derived body composition parameters, especially the visceral fat index, can predict the new-onset risk for type 2 diabetes better than traditional anthropometric and clinical risk models.
Artificial Intelligence Model Enhances Diagnostic Accuracy for Solid Pancreatic Lesions
An AI model integrating clinical information and endoscopic ultrasonographic images can improve the diagnostic accuracy of solid pancreatic lesions, especially for less experienced endoscopists.
