The paper introduces AWR-Net, a two‑stage framework that decouples anatomy and appearance to synthesize realistic 3D fetal brain ultrasound volumes from anatomical label maps. The first stage uses wavelet diffusion to generate volumes from atlas pairs in the wavelet domain, while the second stage applies residual refinement in the image domain to adapt to real ultrasound appearance. Experiments on real fetal brain ultrasound data show that AWR‑Net outperforms existing synthesis methods, improving metrics such as normalized cross‑correlation and Fréchet Inception Distance, and also enhances downstream segmentation, especially for severe abnormal cases.
By Yuhuan Lu, Sergio Valencia, Yuanji Zhang, Yuhao Huang, Camilo Jaimes, P. Ellen Grant, Davood Karimi
RFlash is a physics‑informed post‑processing technique that removes acoustic shadows in ultrasound by decomposing beamformed images into attenuation and scatter‑intensity maps using a differentiable radiance‑field model. It re‑renders images to eliminate depth‑dependent signal loss, effectively simulating a virtual transducer advance. Across thousands of fetal brain, abdominal, and liver scans, RFlash outperforms traditional attenuation correction, reduces prediction error by 40% in fetal brain imaging, and provides shadow‑confidence maps that enhance bone‑shadow segmentation.
By Valentin Bacher (Oxford Machine Learning in NeuroImaging Lab, University of Oxford, United Kingdom), Pak Hei Yeung (Oxford Machine Learning in NeuroImaging Lab, University of Oxford, United Kingdom, Quantitative Healthcare Analysis), Bernhard Kainz (Friedrich-Alexander-Universit\"at Erlangen-N\"urnberg, Germany, Imperial College London, United Kingdom), Madeleine K. Wyburd (Oxford Machine Learning in NeuroImaging Lab, University of Oxford, United Kingdom, Department of Computer Science, University of Copenhagen, Denmark), Nicola K. Dinsdale (Oxford Machine Learning in NeuroImaging Lab, University of Oxford, United Kingdom), Michael Gray (Institute of Biomedical Engineering, University of Oxford, United Kingdom), Ana I. L. Namburete (Oxford Machine Learning in NeuroImaging Lab, University of Oxford, United Kingdom)
This study introduces a self‑supervised, physics‑guided deep‑learning framework that converts standard clinical T1‑, T2‑, and FLAIR MRIs into quantitative T1, T2, and proton‑density maps. Trained on 4,121 scan sessions from four different 3 T scanners over six years, the method produces maps whose white‑ and gray‑matter values fall within literature ranges and shows minimal variation across scanner hardware and acquisition protocols (coefficients of variation ≤ 1.1 %). Voxel‑wise reproducibility is high, with Pearson and concordance correlation coefficients above 0.82 for T1 and T2 and mean relative differences below 6 % for T2.
By Jelmer van Lune, Stefano Mandija, Oscar van der Heide, Matteo Maspero, Martin B. Schilder, Jan Willem Dankbaar, Cornelis A. T. van den Berg, Alessandro Sbrizzi
arXiv:2606. 19651v1 Announce Type: new Abstract: Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented cohorts, simulate disease trajectories, and support privacy-preserving data sharing.
By Max Van Puyvelde, Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert
arXiv:2609.14312v1 Announce Type: new
Abstract: Multi-shell diffusion MRI (dMRI) unlocks more expressive microstructural modeling than single-shell scans, yet its longer acquisition time hinders depl...
By Binghua Li, Christina Andica, Tong Liang, Ziqing Chang, Chao Li, Wataru Uchida, Kaito Takabayashi, Qibin Zhao, Toshihisa Tanaka, Zhe Sun, Shigeki Aoki
Three-dimensional multi-echo MRI provides rich anatomical and quantitative information, but repeated volumetric encoding prolongs acquisition and motivates k-space undersampling. Reconstructing unders...
The paper introduces a transfer‑learning framework that pre‑trains an implicit neural representation (INR) on a high‑resolution diffusion MRI template and then adapts it to individual subjects through registration and fine‑tuning. This approach enables native single‑subject super‑resolution, achieving a 4× through‑plane up‑sampling from 5 mm to 1.25 mm on Human Connectome Project data. Compared to a recent baseline, the method reduces NRMSE by 36–49 % and increases FSIM by 24–43 %, while training 6× faster and outperforming other INR‑based techniques on both image quality and domain‑specific metrics.
By Abdulkader Ghandoura, Marsil Zakour, William Consagra, Yogesh Rathi
MIGA is a scan‑specific framework for accelerated 3D multi‑echo MRI that uses shared anisotropic Gaussian geometry, a coordinate‑conditioned multi‑output amplitude network, and explicit echo‑specific phase variables. The method jointly optimizes all components from undersampled multi‑coil k‑space data without requiring fully sampled training data. Experiments demonstrate that MIGA outperforms existing methods across various imaging tasks and acceleration factors, especially under stronger undersampling, and offers a favorable quality‑cost balance among full‑volume multi‑echo reconstruction techniques.
By Jingran Xu, Yuanyuan Liu, Yanjie Zhu
arXiv:2608. 14763v1 Announce Type: cross Abstract: Assessment of ventriculomegaly (VM) on fetal brain ultrasound relies primarily on measuring lateral ventricular atrial width on standard planes, which is operator-dependent and may not fully reflect the overall ventricular enlargement.
By Yuhao Huang, Yuanji Zhang, Yuhuan Lu, Dong Ni, P. Ellen Grant, Davood Karimi
arXiv:2605.24625v2 Announce Type: replace
Abstract: Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution...
By Toufiq Musah, Salvatore Calcagno, Federica Proietto Salanitri, Xiaomeng Li, Maruf Adewole, Marawan Elbatel
The paper introduces SIMS-MRI, a self‑supervised framework that performs single‑subject multi‑view MRI super‑resolution using implicit neural representations. It processes anisotropic multi‑view scans without pre‑ or post‑processing, employing a multi‑resolution hash‑encoded representation and learned inter‑view alignment to produce isotropic reconstructions. The method is validated on simulated brain and clinical prostate MRI datasets, and the code will be publicly released.
By Heejong Kim, Abhishek Thanki, Roel van Herten, Daniel Margolis, Mert R Sabuncu
arXiv:2608.08693v2 Announce Type: replace
Abstract: Quantitative T2* maps have strong potential for biomarker discovery but are limited by long scan times, rendering them impractical in clinical sett...
By Gideon N. L. Rouwendaal, Natascha Niessen, Hannah Eichhorn, Dirk H. J. Poot, Christine Preibisch, Julia A. Schnabel