#FASTMRI
Fast Abdominal #MRI with Deep Learning Image Reconstruction. Cuts scan time, improves image quality & boosts patient comfort. Covers T2WI, #MRCP & DWI.

Read more: marketing.webassets.siemens-healthineers.com/fce0d2bcf600...

#MagnetomWorld #DeepResolve #Radiology #FastMRI #AI #MedSky #OncSky
April 15, 2025 at 7:00 AM
for reconstruction. Experimental results on the NYU fastMRI dataset demonstrate that our method outperforms existing approaches in multiple evaluation metrics. Our code is available at https://anonymous.4open.science/r/DDO-IN-A73B. [5/5 of https://arxiv.org/abs/2503.08056v1]
March 12, 2025 at 5:58 AM
MMRQA combines MRQy metrics and a Qwen LLM model to give scores and explanations for MRI quality. Tested on MR‑ART, FastMRI and MyConnectome, it showed zero‑shot generalisation. https://getnews.me/multimodal-ai-advances-mri-quality-assessment-with-mmrqa-framework/ #mmrqa #mri #ai
October 1, 2025 at 12:53 AM
Patch‑based diffusion model PaDIS‑MRI achieves high‑quality reconstructions with only 25 k‑space scans and a 7× undersampling factor, beating FastMRI‑EDM in PSNR, SSIM and NRMSE. https://getnews.me/patch-based-diffusion-improves-mri-reconstruction-with-minimal-data/ #mri #diffusion #ai
September 29, 2025 at 5:30 PM
Zero-shot Adaptive Diffusion Sampling (ZADS) optimizes fidelity weights at test time, boosting MRI reconstruction quality on the fastMRI knee dataset without retraining the diffusion model. https://getnews.me/zero-shot-adaptive-diffusion-sampling-improves-mri-reconstruction/ #zads #mri
September 17, 2025 at 7:37 AM
“I was so excited to read #FASTMRI found #breastcancers smaller and earlier than mammograms. I wanted to bring it to
Bristol”

9 years on Lyn Jones, the DYAMOND study lead, shares what it has taken to open the trial to patients.

👉 bit.ly/3KkSO1s
The FAST MRI DYAMOND breast cancer screening study – How did we get here? | North Bristol NHS Trust
A new study is investigating whether FAST MRI, a new type of scan, can help detect small but aggressive breast cancers earlier. Now open to patients, the
bit.ly
October 2, 2025 at 9:48 AM
BBC Points West - Dr Lyn Jones, FAST MRI DYAMOND breast cancer screening study lead explains how FAST MRI may help find ‘hard to spot’ cancers earlier

ow.ly/BJxL50Ww3Gx

#breastcancer #screening #FASTMRI #research
July 29, 2025 at 10:35 AM
Another FastMRI dataset!
February 19, 2025 at 1:37 AM
Check out today's #FreeFriday @radiology-ai.bsky.social article from #PubMedCentral!

FastMRI Breast: A Publicly Available Radial k-Space Dataset of Breast Dynamic Contrast-enhanced MRI

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11791504 #AI #ML #MachineLearning
April 3, 2026 at 2:16 PM
FastMRI Breast is a large-scale dataset of radial k-space & DICOM data for breast dynamic contrast-enhanced #MRI https://doi.org/10.1148/ryai.240345 @ESolomonMRI @WeillCornell @FAU_Germany #breast #AI #MachineLearning
January 26, 2025 at 4:15 PM
FastMRI Breast: A Publicly Available Radial K-space Dataset of Breast Dynamic Contrast-enhanced MRI https://doi.org/10.1148/ryai.240345 @ESolomonMRI @WeillCornell @FAU_Germany #BreastCancer #OncoRad #MachineLearning
January 24, 2025 at 10:15 PM
FastMRI Breast: A Publicly Available Radial K-space Dataset of Breast Dynamic Contrast-enhanced MRI https://buff.ly/4fT1Son #OncoRad #BreastRad #ML
January 21, 2025 at 3:45 PM
FastMRI Breast: A Publicly Available Radial K-space Dataset of Breast Dynamic Contrast-enhanced MRI https://buff.ly/4fT1Son #breast #OncoRad #MachineLearning
January 13, 2025 at 3:45 PM
perturbations in a sparse domain, leading to more reliable and artifact-free reconstructions. The results obtained from the fastMRI knee and brain datasets show that the proposed training strategy effectively reduces aliasing artifacts and mitigates [4/5 of https://arxiv.org/abs/2505.24136v1]
June 2, 2025 at 6:01 AM
samples, and privacy concerns. The SD model, pre-trained on natural images, was fine-tuned using the 3T fastMRI dataset and the 0.3T M4Raw dataset, with the goal of generating brain T1, T2, and FLAIR images across different magnetic field strengths. [2/5 of https://arxiv.org/abs/2505.22682v1]
May 30, 2025 at 6:01 AM
one-step reconstruction by first training a conditional DM and then iteratively distilling this model. Comprehensive experiments were conducted on both publicly available fastMRI images and an in-house multi-echo GRE (QSM) subject. Overall, the [4/6 of https://arxiv.org/abs/2505.08142v1]
May 14, 2025 at 6:01 AM
varying noise conditions and MRI contrasts on the M4Raw and fastMRI dataset. [8/8 of https://arxiv.org/abs/2505.05631v1]
May 12, 2025 at 6:01 AM
tasks: skull-stripping directly in k-Space and MRI reconstruction using the publicly available FastMRI dataset. Our results show that training with synthetic phase data significantly improves generalization for skull-stripping on real-world data, with [4/7 of https://arxiv.org/abs/2504.07560v1]
April 11, 2025 at 6:02 AM
sequentially trained in a supervised manner on the fastMRI dataset and validated for 2D multi-coil MRI in simulation and on real data, targeting highly under-sampled radial k-space sampling. Results suggest that a series with only few DNNs achieves [6/8 of https://arxiv.org/abs/2503.09559v1]
March 13, 2025 at 6:02 AM
maintain high reconstruction quality with approximately 50% fewer parameters compared to existing models. Experimental evaluation on the FastMRI dataset demonstrates competitive PSNR, SSIM, and LPIPS metrics, even at high acceleration factors (8x and [4/6 of https://arxiv.org/abs/2503.05063v1]
March 10, 2025 at 6:12 AM
fastMRI datasets show that Delta-WKV outperforms existing methods, improving PSNR by 0.06 dB and SSIM by 0.001, while reducing training and inference times by over 15\%. These results demonstrate its efficiency and potential [6/7 of https://arxiv.org/abs/2502.20852v1]
March 3, 2025 at 6:02 AM
in the dual space of image-space signal and k-space measurement. We compared our method with state-of-the-art learning-based baselines on the fastMRI database of both single-coil knee and multi-coil brain MRIs. The results [5/7 of https://arxiv.org/abs/2502.17174v1]
February 25, 2025 at 6:06 AM
we provide implementations of all methods in the DeepInverse library (https://deepinv.github.io) and easy-to-use demo code at https://andrewwango.github.io/deepinv-selfsup-fastmri. [6/6 of https://arxiv.org/abs/2502.14009v1]
February 21, 2025 at 6:03 AM
AI innovation in #MRI requires raw k-space data, but open access to such data is scarce. Our fastMRI dataset—launched in 2018 & expanded since—is the largest open collection of professionally prepared & deidentified raw MRI data for #AI research.

🎁 fastmri.med.nyu.edu

#OpenScience
3/3
fastMRI Dataset
fastmri.med.nyu.edu
February 18, 2025 at 8:42 PM