magnetic resonance imaging
PulseAugur coverage of magnetic resonance imaging — every cluster mentioning magnetic resonance imaging across labs, papers, and developer communities, ranked by signal.
- used by Tau PET Imaging in the NACC Study Cohort 90%
- instance of magnetic resonance imaging of the brain 90%
- used by brain tumor 90%
- used by Radiotherapy 80%
- used by Fastmri 70%
- used by TotalSegmentator 70%
- used by Influence Flower 70%
- used by Diffusion Models 70%
- used by peak signal-to-noise ratio 70%
- instance of Fastmri 70%
- used by Flair 70%
- used by nnU-Netv2 70%
- 2026-05-19 research_milestone Publication of a research paper detailing a new browser-native GPU architecture for MRI digital twins. source
18 day(s) with sentiment data
Emerging trend: State-space models and self-supervised learning gaining traction in MRI image processing
Recent evidence highlights the successful application of both state-space models (SO-Mamba) for reconstruction and self-supervised learning (SMIT) for segmentation in MRI. This suggests a broader shift towards more advanced AI architectures beyond traditional CNNs and Transformers for improving MRI data quality and analysis.
SO-Mamba to be integrated into commercial MRI reconstruction software within 18 months
The SO-Mamba model shows significant performance improvements over existing CNN, Transformer, and Mamba approaches for MRI reconstruction. Given its demonstrated superiority on public benchmarks and efficient computation, it is likely to be adopted by commercial MRI vendors for integration into their reconstruction software to enhance scan speed and image quality.
AI-driven real-time MRI of speech production to enable new diagnostic tools for speech disorders
The integration of acoustic data with visual MRI for real-time speech production analysis represents a significant leap in understanding vocal tract dynamics. This advancement could lead to the development of novel diagnostic tools for various speech and swallowing disorders, allowing for more precise assessment and personalized treatment plans.
-
Generative AI enhances dementia diagnosis accuracy
Researchers are exploring the use of generative models, specifically variational autoencoders and generative adversarial networks, to improve the accuracy of diagnosing dementia and its subtypes. These models are being …
-
AI model predicts Alzheimer's conversion using multi-modal data
Researchers have developed a deep learning model to predict the conversion time to Dementia of Alzheimer's Type (DAT) using multi-modal data. The study analyzed MRI, genetic, and cognitive/demographic/cerebrospinal flui…
-
New MRI Reconstruction Method Enhances Image Quality Without Full Training Data
Researchers have developed a new self-supervised reconstruction framework called MSPR-GRE for accelerated multi-echo gradient-echo MRI. This method aims to preserve anatomical detail and complex echo information for qua…
-
New framework QueryREPA enhances multimodality medical object detection
Researchers have developed a new framework called QueryREPA to improve multimodality medical object detection. This approach addresses the challenge of training a single detector on diverse medical imaging types like X-…
-
AI enhances MRI brain tumor detection with deep learning and SHAP analysis
Researchers have developed an enhanced method for detecting brain tumors using Magnetic Resonance Imaging (MRI) by combining deep learning techniques with explainable AI. The study explored various feature representatio…
-
New TACT-KV method compresses 3D medical VLM caches, boosting batch size 8x
Researchers have developed TACT-KV, a novel method for compressing the key-value (KV) cache in vision-language models (VLMs) that process 3D medical imaging data. Unlike previous methods that only consider 1D or 2D tran…
-
AI enhances NMR structure elucidation with contextual chemical data
Researchers have developed a new method that combines machine learning with contextual chemical data to improve the accuracy of NMR structure elucidation. This approach uses automated retrosynthetic analysis to generate…
-
Deep learning and SHAP analysis enhance MRI brain tumor detection
Researchers have developed an enhanced method for detecting brain tumors using Magnetic Resonance Imaging (MRI) combined with deep learning and explainable AI. The study explored various feature representation schemes, …
-
SSFMamba framework enhances 3D medical image segmentation using symmetry and frequency modeling
Researchers have developed SSFMamba, a novel framework for 3D medical image segmentation that integrates spatial and frequency domain modeling. This approach, based on Mamba, incorporates Hermitian symmetry and a Multi-…
-
AI synthesizes controllable glioblastoma MRI scans using latent diffusion models
Researchers have developed a novel two-stage latent diffusion model (LDM) framework designed to synthesize controllable 2D glioblastoma MRI scans. The first stage generates tumor segmentation maps based on specified loc…
-
New ME^2FDiff model enhances brain tumor MRI segmentation
Researchers have developed ME^2FDiff, a novel single-model architecture designed to improve the segmentation of post-treatment glioma from MRI scans. This new model addresses limitations in existing architectures by ref…
-
Remene helps patients understand MRI scans and reports
Remene is a new web-based tool designed to help patients understand their MRI scans and radiology reports. It allows users to upload their MRI data and reports, providing plain-language explanations of medical terms and…
-
Nonlinear registration improves rodent stroke PET analysis accuracy
A new study published on Hugging Face explores the impact of different registration pipelines on longitudinal PET analysis in a rodent stroke model. Researchers compared a two-stage pipeline involving both affine and no…
-
VariaFlow method improves anomaly detection in brain MRI scans
Researchers have developed VariaFlow, a novel unsupervised anomaly detection method designed for medical imaging, specifically magnetic resonance imaging (MRI). This approach addresses a key challenge in anomaly detecti…
-
New unified model segments pancreatic tumors and organs from MRI scans
Researchers have developed Pancreas-MedNeXt, a unified model designed to segment pancreatic tumors and surrounding organs at risk from MRI scans. This model utilizes a shared encoder-decoder architecture with multitask …
-
Deep learning framework detects neonatal brain pathologies from MRI
Researchers have developed a novel two-stage deep learning framework designed to identify neonatal brain pathologies from magnetic resonance imaging (MRI) data. This advanced system aims to improve the accuracy and effi…
-
New IBCD method enables single-step bidirectional unpaired image translation
Researchers have developed a new method called Implicit Bridge Consistency Distillation (IBCD) for single-step bidirectional unpaired image translation. This technique reformulates consistency distillation using a diffu…
-
Deep learning framework estimates MPF from standard clinical MRI scans
Researchers have developed a novel deep learning framework that can estimate macromolecular pool fraction (MPF) from conventional clinical MRI scans. This method, which is guided by physics and uses self-supervision, do…
-
AI translates spinal MRI to CT for surgical planning
Researchers have developed a novel three-stage framework to synthesize Computed Tomography (CT) images from Magnetic Resonance Imaging (MRI) scans of the spine. This method aims to improve surgical planning by providing…
-
PropTech Newsletter Highlights AI, Yardi, UiPath, and Procore Innovations
This item is an advertisement for a newsletter focused on the rapid advancements in property technology (PropTech). It highlights key areas such as AI, Yardi, MRI, UiPath, and Procore innovations within Assetsoft Matrix…