Accurate Pulmonary Artery and Vein Segmentation from Non-Contrast CT Scans Reveals Demographic Associations in Pulmonary Vasculature Anatomy
Accurate and abundant segmentation of pulmonary arteries and veins can be achieved from non-contrast CT scans using the proposed HiPaS framework, enabling contrast-agent-free diagnosis and revealing novel associations between pulmonary vessel abundance and sex and age.
CopilotCAD: Empowering Radiologists with AI-Assisted Diagnostic Reporting and Quantitative Imaging Analysis
CopilotCAD introduces a collaborative framework that integrates large language models and medical image analysis tools to empower radiologists in the diagnostic process, enhancing report quality, efficiency, and trust in AI-supported systems.
Leveraging Longitudinal Representation Learning and Neural Ordinary Differential Equations to Predict Disease Progression
This work proposes a novel framework that integrates self-supervised learning with neural ordinary differential equations (NODEs) to effectively model and predict disease progression, specifically focusing on diabetic retinopathy.
Comparative Analysis of Deep Learning Models for Robust Lung Segmentation on Diverse X-Ray Images
This study evaluates and compares the performance of three prominent deep learning models - Lung VAE, TransResUNet, and CE-Net - for the task of lung segmentation on X-ray images, including their robustness to various image augmentations.
Leveraging Self-Supervision and Limited Data for Accurate Differential Diagnosis of Alzheimer's and Frontotemporal Dementia
Triplet Training, a novel approach combining self-supervised learning, self-distillation, and fine-tuning, significantly outperforms traditional training strategies for differentiating Alzheimer's disease and frontotemporal dementia using limited target data.
Separating Pathological Patterns from Healthy Factors in Medical Imaging using a Contrastive Variational Autoencoder (SepVAE)
SepVAE, a contrastive variational autoencoder, effectively separates the common factors of variation between a background (healthy) dataset and a target (pathological) dataset from the target-specific factors of variation.
Automated Lung X-Ray Abnormality Detection System: A Deep Dive into Efficient COVID-19 and Pneumonia Diagnosis
The core message of this article is to develop a highly efficient and interpretable deep learning-based system, called V-BreathNet, that can accurately classify lung X-ray images into normal, COVID-19, and pneumonia categories, enabling early and cost-effective detection of respiratory diseases.
Adaptive Wavelet Transform Integrated Convolutional Neural Network for Accurate Ultrasound Texture Classification of Graves' Disease
A convolutional neural network that integrates an adaptive wavelet transform module can effectively learn features in both spatial and frequency domains, leading to optimized classification accuracy for ultrasound diagnosis of Graves' disease.
Enhancing Chest CT Image Understanding by Distilling Knowledge from Extensive X-ray Expert Models
The core message of this paper is to enhance the understanding of 3D chest CT images by distilling knowledge from a pre-trained 2D chest X-ray expert model, leveraging language as a high-quality supervision signal to address the limited availability of paired CT-report data.
ProtoAL: Integrating Interpretable Deep Learning with Active Learning for Efficient Medical Image Analysis
ProtoAL integrates an interpretable deep learning model based on prototypes into a deep active learning framework to address challenges of interpretability and data scarcity in medical imaging applications.
© 2024 by Linnk AI