The paper presents a systematic comparison of recurrent neural networks and Transformer models for iterative diffusion MRI tractography, focusing on training strategies, input representations, and hyperparameter tuning. It introduces a generation‑validation phase that provides streamline‑level supervision, enabling the models to achieve the best performance reported on the ISMRM2015 challenge dataset. The study also evaluates the effects of missing bundles, noisy training data, and invalid fibers, and demonstrates applicability to in‑vivo data from the Tractoinferno database.
By Emmanuelle Renauld, Philippe Poulin, Hugo Larochelle, Antoine Th\'eberge, Maxime Descoteaux
The paper introduces τ+C+Mag, a physics‑driven deep learning method that incorporates auxiliary k‑space magnitude information into accelerated steady‑state dynamic MRI reconstruction. By observing strong consistency of k‑space magnitudes across time‑frames, the authors develop an ADMM‑based unrolling framework with a magnitude‑aware data‑fidelity term, using quadratically smoothed optimization and momentum updates to handle non‑differentiability and non‑convexity. Experiments on retrospectively and prospectively undersampled cine and phase‑contrast flow MRI datasets show improved artifact suppression, sharper anatomical detail, and better phase preservation compared to conventional PD‑DL approaches, as confirmed by blinded expert readers.
By Mahdi Saberi, Ya\c{s}ar Utku Al\c{c}alar, Merve G\"{u}lle, Chetan Shenoy, Mehmet Ak\c{c}akaya
arXiv:2606. 00100v1 Announce Type: cross Abstract: Self-supervised deep learning-based methods have shown great promise for accelerated magnetic resonance imaging (MRI) reconstruction, achieving high image quality without requiring fully sampled data for training.
By Tongxi Song, Ziyu Li, Zihan Li, Wen Zhong, Congyu Liao, Yang Yang, Hua Guo, Wenchuan Wu, Qiyuan Tian
X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete. While learned reconstruction methods such as the Learned Primal-Dual algorithm achieve strong performance, they typically rely on supervised training with access to ground-truth data, which is often unavailable in practice.
The paper tackles the inverse problem of recovering the initial pressure distribution in photoacoustic tomography (PAT) when nonlinear acoustic propagation and viscous attenuation are present. It models these effects with a nonlinear damped viscoelastic wave equation and proves well‑posedness of the forward problem. For the inverse problem, the authors establish existence, uniqueness, and local uniqueness results, and then propose a hybrid reconstruction framework that uses a convolutional neural network to generate an initial guess followed by a gradient‑free sequential quadratic Hamiltonian optimization to enforce the PDE dynamics. Numerical experiments show that this hybrid approach yields better reconstruction quality, contrast, and robustness than either time‑reversal or CNN‑only methods.
By Madhu Gupta, Anwesa Dey, Prapti Tala, Souvik Roy
Machine learning (ML) has emerged as a promising approach for improving diffusion MRI (dMRI) tractography, a task that remains limited by the intrinsic tension between local diffusion information and...