paper-with-me

Papers

J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction

2019-11-06 · Hemant Kumar Aggarwal, Mathews Jacob

Modern MRI schemes, which rely on compressed sensing or deep learning algorithms to recover MRI data from undersampled multichannel Fourier measurements, are widely used to reduce scan time. The image quality of these approaches is heavily dependent on the sampling pattern. We introduce a continuous strategy to jointly optimize the sampling pattern and network parameters. We use a multichannel forward model, consisting of a non-uniform Fourier transform with continuously defined sampling locations, to realize the data consistency block within a model-based deep learning image reconstruction scheme. This approach facilitates the joint and continuous optimization of the sampling pattern and the CNN parameters to improve image quality. We observe that the joint optimization of the sampling patterns and the reconstruction module significantly improves the performance of most deep learning reconstruction algorithms. The source code of the proposed joint learning framework is available at https://github.com/hkaggarwal/J-MoDL.

📄 PDF Abstract BibTeX arXiv:1911.02945

Code (1)

hkaggarwal/J-MoDL 공식 구현 tf

Tasks

compressed sensingDeep LearningImage Reconstruction

Similar Papers 제목 키워드 기반

Wave-Encoded Model-based Deep Learning for Highly Accelerated Imaging with Joint Reconstruction

2022-02-06 · Jaejin Cho, Borjan Gagoski, Taehyung Kim, Qiyuan Tian 외

Purpose: To propose a wave-encoded model-based deep learning (wave-MoDL) strategy for highly accelerated 3D imaging and joint multi-contrast image reconstruction, and further extend this to enable rapid quantitative imag…

Image Reconstruction

MF-JMoDL-Net: A Deep Network for Azimuth Undersampling Pattern Design and Ambiguity Suppression for Sparse SAR Imaging

2023-03-20 · Yuwei Wu, Zhe Zhang, Xiaolan Qiu, Yao Zhao 외

repetition frequency (PRF). Given the system complexity and resource constraints, it is often difficult to achieve high imaging performance and low ambiguity without compromising the swath. In this paper, we propose a jo…

FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI Reconstruction

2026-08-26 · Tristan Gottwald, Michelle Bruch, Mubashir-Ul Hassan, Fatma Alickovic 외 arxiv

We present FlowMoDL, an unrolled neural network for highly accelerated 4D flow MRI reconstruction that directly optimizes for both anatomical magnitude and phase-derived velocity accuracy. Building on the MoDL framework,…

MRI Reconstruction

DARCS: Memory-Efficient Deep Compressed Sensing Reconstruction for Acceleration of 3D Whole-Heart Coronary MR Angiography

2024-02-01 · Zhihao Xue, Fan Yang, Juan Gao, Zhuo Chen 외

Three-dimensional coronary magnetic resonance angiography (CMRA) demands reconstruction algorithms that can significantly suppress the artifacts from a heavily undersampled acquisition. While unrolling-based deep reconst…

3D Reconstructioncompressed sensingDe-aliasingGenerative Adversarial Network+1

Off-the-grid model based deep learning (O-MODL)

2018-12-27 · Aniket Pramanik, Hemant Kumar Aggarwal, Mathews Jacob

We introduce a model based off-the-grid image reconstruction algorithm using deep learned priors. The main difference of the proposed scheme with current deep learning strategies is the learning of non-linear annihilatio…

Deep LearningImage Reconstruction