paper-with-me

홈 › Papers

Stabilizing 3D EPI time series by servo navigation and phase equalization exploiting repeated shots (PEERS)

2025-05-06 · Malte Riedel, Thomas Ulrich, Samuel Bianchi, Klaas P. Pruessmann

Purpose: To enable run-time head motion control and robust frequency corrections for 3D EPI fMRI. Methods: A short 3D orbital navigator (3 ms) is inserted into a 3D EPI sequence. A linear perturbation model is calibrated to estimate rigid motion and frequency parameters per shot. Rigid motion is corrected by scan geometry updates in run-time, while several techniques are investigated to stabilize navigator-based frequency corrections in the reconstruction. An additional method termed PEERS is proposed that exploits the repetitive structure of fMRI scans to fine-tune shot-wise phase and frequency estimates using the motion-corrected EPI data itself. Results: Servo navigation effectively reduces motion in the raw data of in-vivo fMRI scans in six subjects. PEERS provides high-precision frequency parameters for robust phase-corrected reconstructions in the phantom and in-vivo accounting for scanner drifts and slice encoding-related effects on EPI. In combination, servo navigation and PEERS achieve successful intra-volume corrections and consistent tSNR improvements of 8% on average throughout the brain. The two methods prove to be highly synergetic. Conclusion: Servo navigation achieves high-precision motion correction for 3D-EPI fMRI in run-time and, in synergy with PEERS, provides stable frequency corrections with short navigators even for long echo times. With its automatic self-calibration and no hardware requirements, servo navigation and PEERS enable effective plug-and-play motion correction for 3D fMRI.

📄 PDF Abstract BibTeX arXiv:2505.03637

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series

Similar Papers 제목 키워드 기반

Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing

2021-08-06 · André Röhm, Daniel J. Gauthier, Ingo Fischer

Reservoir computers are powerful tools for chaotic time series prediction. They can be trained to approximate phase space flows and can thus both predict future values to a high accuracy, as well as reconstruct the gener…

Time SeriesTime Series AnalysisTime Series Prediction

Controlling Chaotic Maps using Next-Generation Reservoir Computing

2023-07-07 · Robert M. Kent, Wendson A. S. Barbosa, Daniel J. Gauthier

In this work, we combine nonlinear system control techniques with next-generation reservoir computing, a best-in-class machine learning approach for predicting the behavior of dynamical systems. We demonstrate the perfor…

Versatile Reservoir Computing for Heterogeneous Complex Networks

2025-05-21 · Yao Du, Huawei Fan, Xingang Wang

A new machine learning scheme, termed versatile reservoir computing, is proposed for sustaining the dynamics of heterogeneous complex networks. We show that a single, small-scale reservoir computer trained on time series…

A Novel Reservoir Computing Framework for Chaotic Time Series Prediction Using Time Delay Embedding and Random Fourier Features

2025-11-04 · S. K. Laha arxiv

Forecasting chaotic time series requires models that can capture the intrinsic geometry of the underlying attractor while remaining computationally efficient. We introduce a novel reservoir computing (RC) framework that …

Time Series Prediction

Oscillations enhance time-series prediction in reservoir computing with feedback

2024-06-05 · Yuji Kawai, Takashi Morita, Jihoon Park, Minoru Asada

Reservoir computing, a machine learning framework used for modeling the brain, can predict temporal data with little observations and minimal computational resources. However, it is difficult to accurately reproduce the …

Time SeriesTime Series Prediction