Publications by authors named "Tomas Bosschieter"
Recent advances in generative models have paved the way for enhanced generation of natural and medical images, including synthetic brain MRIs. However, the mainstay of current AI research focuses on optimizing synthetic MRIs with respect to visual quality (such as signal-to-noise ratio) while lacking insights into their relevance to neuroscience. To generate high-quality T1-weighted MRIs relevant for neuroscience discovery, we present a two-stage Diffusion Probabilistic Model (called BrainSynth) to synthesize high-resolution MRIs conditionally-dependent on metadata (such as age and sex).
View Article and Find Full Text PDFArticle Synopsis
- Most pregnancies have good outcomes, but complications can still occur and pose risks to mothers and babies.
- Predictive modeling, specifically using Explainable Boosting Machines (EBMs), can help identify important risk factors for complications like severe maternal morbidity and antepartum stillbirth.
- EBMs offer high accuracy and interpretability, revealing unexpected insights that could enhance clinical practices and improve the prediction and prevention of serious pregnancy complications.
Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model.
Med Image Comput Comput Assist Interv
October 2023
As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models. This challenge could be reduced by MRI synthesis, for which Generative Adversarial Networks (GANs) are popular. GANs, however, are commonly unstable and struggle with creating diverse and high-quality data.
View Article and Find Full Text PDF