Publications by authors named "B Stoel"
Explainable fully automated CT scoring of interstitial lung disease for patients suspected of systemic sclerosis by cascaded regression neural networks and its comparison with experts.
Sci Rep
November 2024
Visual scoring of interstitial lung disease in systemic sclerosis (SSc-ILD) from CT scans is laborious, subjective and time-consuming. This study aims to develop a deep learning framework to automate SSc-ILD scoring. The automated framework is a cascade of two neural networks.
View Article and Find Full Text PDFRadiostereometric analysis (RSA) is the current gold standard to determine implant migration, but it requires bone markers and special equipment. Therefore, we developed VoluMetric Matching Micromotion Analysis (V3MA), a software program for Computed Tomography-based radiostereometric analysis (CT-RSA). This study aimed to determine the accuracy and precision of V3MA in vitro compared to RSA and provide a clinical proof of concept.
View Article and Find Full Text PDFArticle Synopsis
- - Pulmonary function tests (PFTs) are crucial for assessing interstitial lung disease in systemic sclerosis patients, but they can be challenging to perform due to risks and contraindications, leading to the exploration of alternative methods like convolution neural networks (CNNs) with chest CT scans.
- - This study introduces point cloud neural networks (PNN) and graph neural networks (GNN) to better estimate PFTs using detailed information about pulmonary vessel centerlines, which enhances accuracy compared to previous CNN methods while also being more efficient in terms of training time and parameters.
- - The combination of CNN-CT, PNN-Vessel, and GNN-Vessel resulted in the highest accuracy for estimating PFTs, indicating that
Article Synopsis
- Artificial intelligence, particularly deep learning, has influenced everyday life and is now being explored in fields like rheumatology for diagnostics and patient monitoring.* -
- Deep learning excels at processing images, outperforming traditional imaging techniques, but its effectiveness may not translate to simpler numerical data analysis.* -
- Rheumatologists and radiologists must understand deep learning's techniques and limitations to incorporate it effectively into their practices, ensuring they leverage its benefits while avoiding potential pitfalls.*
The shape and distribution of vascular lesions in pulmonary embolism (PE) and chronic thromboembolic pulmonary hypertension (CTEPH) are different. We investigated whether automated quantification of pulmonary vascular morphology and densitometry in arteries and veins imaged by computed tomographic pulmonary angiography (CTPA) could distinguish PE from CTEPH. We analyzed CTPA images from a cohort of 16 PE patients, 6 CTEPH patients, and 15 controls.
View Article and Find Full Text PDF