ISSN# 1545-4428 | Published date: 19 April, 2024
You must be logged in to view entire program, abstracts, and syllabi
At-A-Glance Session Detail
   
AI/ML-Driven Reconstruction Techniques for Dynamic MRI
Oral
AI & Machine Learning
Monday, 06 May 2024
Hall 606
08:15 -  10:15
Moderators: Thomas Küstner & Chen Qin
Session Number: O-57
CME Credit

08:15 Introduction
Thomas Küstner
University Hospital Tuebingen, Germany
08:270009.
Cardiac Cine MRI with Dimension-Reduced Deep Separable Spatiotemporal Learning
Zi Wang1, Yirong Zhou1, Chengyan Wang2, Di Guo3, and Xiaobo Qu4
1Xiamen University, Xiamen, China, 2Fudan University, Shanghai, China, 3Xiamen University of Technology, Xiamen, China, 4Department of Electronic Science, Xiamen University, Xiamen, China

Keywords: AI/ML Image Reconstruction, Machine Learning/Artificial Intelligence, Cardiovascular MRI

Motivation: Cardiac cine MRI reconstruction is a natural high-dimensional problem that poses great challenges to deep learning.

Goal(s): To develop a new deep learning method that can work efficiently in cardiac cine MRI, even with limited training data.

Approach: In this work, the proposed method DeepSSL significantly alleviates training and generalization challenges of deep learning in cardiac cine MRI through efficient dimension-reduced separable learning and spatiotemporal modeling.

Results: Extensive results show that DeepSSL can work efficiently even with highly limited training data (5~10 cases), and provides state-of-the-art reconstructions while reduces data demand by up to 75%. It further shows robustness in prospective real-time MRI.

Impact: The proposed deep separable spatiotemporal learning (DeepSSL) significantly alleviates the training and generalization challenges of deep learning in high-dimensional cardiac cine MRI through efficient dimension-reduced separable learning and spatiotemporal modeling.

08:390010.
Rapid Motion Estimation and Motion-Corrected End-to-End Deep Learning Reconstruction for 1 Heartbeat CINE
Thomas James Fletcher1, Lina Felsner1, Andrew Phair1, Gastão Cruz2, Haikun Qi3, René Botnar1,4,5,6,7, and Claudia Prieto1,5,6
1School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, 2Department of Radiology, University of Michigan, Ann Arbor, MI, United States, 3School of Biomedical Engineering, ShanghaiTech University, Shanghai, China, 4Instituto de Ingeniería Biológica y Médica, Pontificia Universidad Católica de Chile, Santiago, Chile, 5Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile, 6Millenium Institute for Intelligent Healthcare Engineering iHEALTH, Santiago, Chile, 7Institute of Advanced Study, Technical University of Munich, Munich, Germany

Keywords: AI/ML Image Reconstruction, Cardiovascular

Motivation: Cardiac CINE provides dynamic images of the heart for morphology and function assessment. Single-heartbeat CINE enables faster acquisition times and the study of heart rate variations, but conventional reconstruction methods incur significant computational cost.

Goal(s): This study aims to speed up single-heartbeat CINE reconstruction by using deep learning reconstruction.

Approach: We propose a novel, rapid, end-to-end deep learning pipeline for motion estimation and motion-corrected single-heartbeat CINE reconstruction with golden-angle radial acquisition.

Results: The network reconstructs each CINE slice in ~40 seconds (400 times faster than state-of-the-art), with comparable image quality, achieving SSIM values ranging from 0.75 to 0.84 across cardiac phases and slices.

Impact: The proposed approach enables reconstruction of single-heartbeat golden-angle radial CINE acquisition in ~40 seconds, making it clinically feasible. Single-heartbeat CINE could reduce scan times, achieve acquisitions of multiple slices in a single breath-hold and be robust to heart rate variations.

08:510011.
A Temporal-compensated Structure-preserving Enhancement Network (Tco-SEN) for Abdominal Four-dimensional Magnetic Resonance Imaging
Yinghui Wang1, Haonan Xiao2, Wen Li1, Tian Li1, and Jing Cai1
1Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, 2Department of Radiation Oncology and Physics, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, China

Keywords: AI/ML Image Reconstruction, Cancer, 4D-MRI\Enhancement\Temporal-compensation

Motivation: Four-dimensional Magnetic Resonance Imaging (4D-MRI) shows promise for motion management in abdominal radiotherapy. However, the prevalent undersampling often hampers its image quality. 

Goal(s): To enhance the image quality of 4D-MRI, we propose Tco-SEN, a deep-learning model to exploit its properties. 

Approach: Tco-SEN employs a two-stage architecture and a customized loss penalty, enabling effective restoration of detailed features and preservation of anatomical structures.

Results:  Compared to state-of-the-art algorithms, Tco-SEN significantly enhances image quality by improving spatial resolution, reducing motion artifacts and noise, and preserving delicate structures. Furthermore, our method enhances the accuracy of subsequent motion modeling in 4D-MRI, highlighting its potential for clinical applications.

Impact: Tco-SEN effectively improves the image quality of 4D-MRI, benefiting more accurate tumor delineation and motion estimation. This advancement promotes the application of 4D-MRI in cancer radiotherapy, ultimately enhancing the accuracy of abdominal cancer radiation treatment.

09:030012.
A self-supervised feature learning strategy for training reconstruction networks on undersampled data in cardiac Cine MRI
Siying Xu1, Kerstin Hammernik2, Daniel Rueckert2,3,4, Sergios Gatidis1,5, and Thomas Kuestner1
1Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University of Tuebingen, Tuebingen, Germany, 2School of computation, Information and Technology, Technical University of Munich, Munich, Germany, 3Department of Computing, Imperial College London, London, United Kingdom, 4Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany, 5Department of Radiology, Stanford University, Stanford, CA, United States

Keywords: AI/ML Image Reconstruction, Cardiovascular, Self-Supervised learning, Feature learning

Motivation: Most existing deep learning-based MR image reconstruction methods are supervised learning, relying on fully-sampled images, which is challenging to acquire in practice.

Goal(s): We aim to leverage undersampled data in a self-supervised reconstruction framework to enhance expressibility and model performance.

Approach: We use information maximization methods to learn sampling-invariant features from undersampled images and incorporate them in a self-supervised reconstruction network.

Results: The proposed method can learn sampling-invariant features from undersampled data, which enhance the reconstruction performance, enabling self-supervised MR image reconstruction for up to 16× undersampling.

Impact: The proposed self-supervised feature learning strategy can extract sampling-invariant features from undersampled images, effectively assisting the reconstruction of undersampled cardiac cine MR imaging without requiring fully-sampled images. This feature learning strategy may also be advantageous for other downstream tasks.

09:150013.
Joint Optimization of Data Sampling and Reconstruction for Dynamic MRI
Cagan Alkan1, Julio Oscanoa1, Andy Dimnaku2, Ali Syed1, Shreyas Vasanawala1, and John Pauly1
1Stanford University, Stanford, CA, United States, 2California Institute of Technology, Pasadena, CA, United States

Keywords: AI/ML Image Reconstruction, New Trajectories & Spatial Encoding Methods

Motivation: Sampling patterns in deep learning (DL) or compressed sensing (CS) based accelerated dynamic MRI reconstructions are typically chosen heuristically. k-t sampling patterns can be optimized to capture the spatio-temporal characteristics of dynamic MRI data more efficiently.

Goal(s): Our objective is to develop a method for optimizing k-t sampling patterns for dynamic MRI.

Approach: We extend the recently developed AutoSamp framework to dynamic MRI setting to jointly optimize k-t sampling and reconstruction. We test our method on a cardiac cine dataset.

Results: DL reconstruction with optimized k-t patterns using the proposed method produces higher quality results with reduced spatial and temporal artifacts.

Impact: Dynamic MRI reconstructions with learned sampling patterns improves reconstruction quality. The learned patterns can also provide insights about designing general k-t MRI sampling patterns.

09:270014.
DE-NIK: Leveraging Dual-Echo Data for Respiratory-Resolved Abdominal MR Reconstructions Using Neural Implicit k-Space Representations
Veronika Spieker1,2,3, Jonathan Stelter4, Wenqi Huang2, Hannah Eichhorn1,2, Kilian Weiss5, Rickmer Braren4, Veronika A Zimmer2, Kerstin Hammernik2, Claudia Prieto3,6,7, Dimitrios C Karampinos4, and Julia A Schnabel1,2,6
1Institute of Machine Learning in Biomedical Imaging, Helmholtz Center Munich, Munich, Germany, 2School of Computation, Information and Technology, Technical University of Munich, Munich, Germany, 3Millenium Institute for Intelligent Healthcare Engineering, Santiago, Chile, 4School of Medicine and Health, Technical University of Munich, Munich, Germany, 5Philips GmbH, Hamburg, Germany, 6School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, 7School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile

Keywords: AI/ML Image Reconstruction, Machine Learning/Artificial Intelligence

Motivation:
Neural implicit k-space representations (NIK) enable binning-free respiratory-resolved MR reconstructions in a data-driven manner. The multi-dimensionality of MR, i.e., provided in dual-echo acquisitions, is expected to improve reconstruction performance and allows for further echo-processing.

Goal(s): A Dual-Echo-NIK that takes advantage of the redundant data present in two echoes and enables subsequent water-fat-separation.

Approach: We propose three Dual-Echo-NIK variants trained (1) individually, (2) jointly and (3) in an echo-modulated way. Motion-resolved echo and water-fat reconstructions are evaluated on a free-breathing phantom simulation and in-vivo.

Results: Quantitative simulations demonstrate improved performance for the modulated Dual-Echo-NIK. In-vivo reconstructions reveal sharper reconstructions when both echoes are utilized.

Impact: The Dual-Echo Neural Implicit k-space Representations indicate how echo information can lead to improved motion-resolved reconstructions, including subsequent water-fat separations. Echo-modulation can further enhance reconstruction performance and offers the potential to reduce acquisition times for training data.

09:390015.
Graph Image Prior for Unsupervised Dynamic MRI Reconstruction
Zhongsen Li1, Wenxuan Chen1, Chuyu Liu1, Puguang Xie2, Haozhong Sun1, Haining Wei1, Jiachen Ji1, Jing Zou1, and Rui Li1
1Tsinghua University, Beijing, China, 2School of Medicine, Chongqing University, Chongqing, China

Keywords: AI/ML Image Reconstruction, Machine Learning/Artificial Intelligence, Unsupervised Learning, Image Reconstruction, Dynamic MRI

Motivation: Current unsupervised dynamic-MRI reconstruction algorithms based on DIP uses very low-dimensional latent variables and a single generator for direct non-linear mapping, which may limit the performance.

Goal(s): To propose a new model and algorithm for unsupervised dynamic MRI reconstruction.

Approach: We propose a novel Graph-Image-Prior(GIP) model, which uses branched CNN generators to recover the image structure, and use a Graph-Neural-Network(GNN) to discover the best spatio-temporal manifold. Besides, we devise an ADMM algorithm to alternately optimize the dynamic image and network.

Results: The proposed method achieves the state-of-art performance even compared with supervised deep-learning methods, without the need for any fully-sampled data.

Impact: The proposed Graph-Image-Prior(GIP) scheme is a new unsupervised image reconstruction model, which has a significant value for further research. Besides, GIP is promising to be used in other multi-frame MRI reconstruction applications where fully-sampled data is scarce or unavailable.

09:510016.
HD-Movienet: High-definition 4D MRI using 3D radial kooshball acquisition and deep learning reconstruction
Victor Murray1, Can Wu1, and Ricardo Otazo1,2
1Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York City, NY, United States, 2Department of Radiology, Memorial Sloan Kettering Cancer Center, New York City, NY, United States

Keywords: AI/ML Image Reconstruction, Image Reconstruction

Motivation: State-of-the-art motion-resolved 4D MRI techniques lack sufficient spatial resolution and efficient acquisition and reconstruction for application in clinical practice.

Goal(s): To develop HD-Movienet, a deep learning-based method to efficiently acquire and reconstruct 4D MRI with approximately 1mm isotropic resolution using 3D radial acquisitions.

Approach: HD-Movienet uses accelerated half-spoke (UTE) and full-spoke (T1-weighted) 3D radial kooshball acquisition and image-time-coil deep learning 4D reconstruction without k-space data consistency.

Results: HD-Movienet can enable 4D MRI with isotropic 1.1mm resolution, 4 minutes of scan time, and reconstruction of less than 7 seconds to image patients with lung tumors.

Impact: Deep learning-based HD-Movienet reconstruction enables motion-resolved 4D MRI technique with isotropic 1.1mm resolution, 4 minutes of scan time, and reconstruction of less than 7 seconds for robust radiation-free imaging of patients with mobile tumors.

10:030017.
Low-Latency Reconstruction of Real-Time Cine MRI Using an Unrolled Network
Marc Vornehm1,2, Jens Wetzl2, Florian Fürnrohr1, Daniel Giese2,3, Rizwan Ahmad4, and Florian Knoll1
1Computational Imaging Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany, 2Magnetic Resonance, Siemens Healthcare GmbH, Erlangen, Germany, 3Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany, 4Biomedical Engineering, The Ohio State University, Columbus, OH, United States

Keywords: Machine Learning/Artificial Intelligence, Image Reconstruction

Motivation: Interactive real-time MRI requires low reconstruction latencies. Deep learning-based methods are promising, but unrolled networks like the Variational Network have longer inference times than purely image-based methods.

Goal(s): Design and train a Variational Network with high reconstruction quality and inference times suitable for interactive real-time applications.

Approach: Modify the Variational Network architecture such that few unrolling steps are sufficient for high reconstruction quality with short inference times.

Results: The proposed architectural modifications allowed to halve the number of unrolling steps without compromising image quality, therefore enabling considerably shortened reconstruction times.

Impact: Two modifications to an unrolled Variational Network architecture for MRI reconstruction are proposed. These enable reconstructing interactive real-time cardiac cine MRI with high reconstruction quality while maintaining minimal reconstruction latency.