10 stories
Task-specific supervised models dominate neuroimaging ML, but they degrade on real clinical data and on scans from new sites, vendors, or populations. The root issue is a structural mismatch: clinical workflows generate huge volumes of MRI, yet only a tiny, mostly research-grade fraction is ever…
This article aims at reviewing a Alzheimer’s spatiotemporal disease progression predictive model called Brain Latent Progression (BrLP). All in all, this is a diffusion model that takes a T1w image and some particular covariates from some timepoint and predict/generates another T1w image for a…
Large Language Models (LLMs) are increasingly applied to critical domains such as medical report generation, where accuracy and trust are essential. Evaluating the quality of generated text is non-trivial: surface word matches may miss key semantic errors, while semantic metrics may overlook…
As interest in large language models (LLMs) for medical imaging continues to grow, I took a closer look at the practical aspects of using open-source LLMs in radiology. The review by Savage et al.
MemSAM is a new video segmentation model designed for echocardiography, built on top of the SAM architecture. It is designed to address specific issues related to the application of SAM to echocardiography and video segmentation more broadly, versus image segmentation.
tl;dr The authors propose PQN, a simplified deep online Q-Learning that uses very small replay buffers. Normalization and parallelized sampling from vectorized environments stabilizes training without the need for huge replay buffers.
Objective EchoPrime is a foundation model designed for comprehensive echocardiographic interpretation. Unlike previous models that use single views or static images, EchoPrime integrates multi-view echocardiographic videos with corresponding text reports using a vision-language framework.
DeepSeek proposes novel LLM architectures (still based on transformers) and training strategies to create powerful open source LLMs with limited training costs.
Convolutional Variational Autoencoder (CVAE) to generate synthetic tractography-based bundle templates from small population data.
Implicit neural representations (INRs) are a class of neural networks that represent a function instead of solving a task. Their main advantage is that they can represent signals continuously in space, which is useful for tasks such as 3D reconstruction, image generation, and physical simulation.
Showing 10 of 10 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
