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
   
Diffusion: Artificial Intelligence & Machine Learning
Oral
Diffusion
Thursday, 09 May 2024
Nicoll 1
08:15 -  10:15
Moderators: Daniel Alexander & ZERAII ABDERRAZEK
Session Number: O-78
CME Credit

08:15 Introduction
Daniel Alexander
University College London, United Kingdom
08:271134.
Estimating microscopy-informed fibre orientations from in-vivo dMRI using a domain adaptation adversarial network
Silei Zhu1, Nicola K. Dinsdale2, Saad Jbabdi1, Karla L. Miller*1, and Amy F.D. Howard*1
1Wellcome Centre for Integrative Neuroimaging, FMRIB Centre, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom, 2Oxford Machine Learning in NeuroImaging Lab (OMNI), Department of Computer Science, University of Oxford, Oxford, United Kingdom

Keywords: Tractography, Tractography & Fibre Modelling, Multimodal, Microscopy, structural connectivity, diffusion, machine learning

Motivation: Joint modelling of diffusion MRI and microscopy can leverage their complementary strengths to improve the estimation of fibre orientations. Ideally, these benefits would extend beyond the few datasets where dMRI and microscopy are acquired in the same brain to improve orientation estimates in in-vivo data.

Goal(s): To translate the unique properties of joint dMRI-microscopy data modelling to benefit in-vivo dMRI datasets.

Approach: We construct a domain adaptation adversarial network that can estimate microscopy-informed FODs from single-shell in-vivo dMRI.

Results: Tractography performed using network-derived FODs show improved tracking in grey matter, bottleneck regions, superficial white matter fibres, and long-range structural connectivity.

Impact: Our microscopy-informed neural network improves fibre orientation estimation from in-vivo single-shell dMRI datasets. We demonstrate improvements in fibre tracking that may enable more precise and detailed detection of connectivity, with a broad range of applications in basic and clinical neuroscience.

08:391135.
Hierarchical-µGUIDE: fast and robust Bayesian hierarchical modelling using deep learning simulation-based inference
Louis Rouillard1, Demian Wassermann1, Marco Palombo2, and Maëliss Jallais2
1MIND team - Inria, Palaiseau, France, 2CUBRIC - Cardiff University, Cardiff, United Kingdom

Keywords: Microstructure, Microstructure

Motivation: In-vivo brain microstructure can be estimated using diffusion MRI. However, most approaches do not quantify estimates reliability, although crucial for interpreting the results, and consider every voxel independently, leading to high uncertainties.

Goal(s): Our goal is to develop a new framework to efficiently estimate tissue microstructure and improve data fitting quality.

Approach: We propose Hierarchical-µGUIDE, a Bayesian method that estimates posterior distributions, by combining simulation-based inference with a hierarchical structure.

Results: Hierarchical-µGUIDE bypasses the high computational and time cost of conventional Bayesian approaches. Sharper microstructure parameter maps that preserve tissue heterogeneity are obtained, along with a tissue parcellation that segments an epileptic lesion.

Impact: The proposed Bayesian framework improves single-subject inference for clinical diagnosis, by efficiently estimating posterior distributions, reducing estimates uncertainty, and learning a tissue parcellation. This works unlocks the possibility to apply hierarchical Bayesian methods taylored for microstructure estimation to large datasets.

08:511136.
gNET: gSlider Self-Supervised Neural Network for Accelerated Reconstruction of Super-resolution Diffusion MRI
Caique de Oliveira Kobayashi1,2,3, Yohan Jun1,4,5, Jaejin Cho1,4,5, Xiaoqing Wang4,5,6, Zihan Li7, Qiyuan Tian7, and Berkin Bilgic1,4,5
1Athinoula A. Martinos Center for Biomedical Imaging, Boston, MA, United States, 2Mechanical Engineering, Escola Politécnica da USP, São Paulo, Brazil, 3Technical University of Munich, Munich, Germany, 4Radiology, Harvard Medical School, Boston, MA, United States, 5Harvard/MIT Health Sciences and Technology, Cambridge, MA, United States, 6Boston Children’s Hospital, Boston, MA, United States, 7Department of Biomedical Engineering, Tsinghua University, Beijin, China

Keywords: Diffusion Reconstruction, Diffusion/other diffusion imaging techniques, gSlider, deep-learning, self-supervised, AI/ML Image Reconstruction

Motivation: gSlider utilizes radio-frequency encoding to acquire high and isotropic resolution brain diffusion-MRI with high SNR. However, this comes at the cost of prolonged acquisition time, which also increases the sensitivity to motion.

Goal(s): This work proposes gSlider Network (gNET) to accelerate gSlider from acquisitions with jointly subsampled RF- and q-space.

Approach: The self-supervised model was trained and tested on a 1mm3 resolution BUDA-gSlider dataset (Tacq = 32 min). FSL and the DIMOND self-supervised were used to estimate the diffusion parameters.

Results: gNET achieved an acceleration factor of R=2 and, when combined with DIMOND, reached a total R=4-fold (Tacq = 8 min).

Impact: gNET facilitates super-resolution dMRI by reducing the acquisition time by 4-fold with high fidelity. Its application may propel new discoveries in the neuroscientific field and the clinical translation of the gSlider framework.

09:031137.
Spatio-Angular Noise2Noise for Self-Supervised Denoising of Diffusion MRI Data
Haotian Jiang1, Shu Zhang2, Xuyun Wen3, Hui Cui4, Jun Lu1, Islem Rekik5, Jiquan Ma*1, and Geng Chen*2
1Heilongjiang University, Harbin, China, 2Northwestern Polytechnical University, Xian, China, 3Nanjing University of Aeronautics and Astronautics, NanJing, China, 4La Trobe University, Victoria, Australia, 5lmperial College London, London, United Kingdom

Keywords: DWI/DTI/DKI, Diffusion/other diffusion imaging techniques, Denoising, Self-Supervised Learning, Spatio-Angular Domain

Motivation: Diffusion MRI (DMRI) suffers from heavy noise. The noise issue reduces the accuracy and reliability of the derived diffusion metrics.

Goal(s): Existing Deep Learning (DL) methods for DMRI denoising usually rely on training with paired noisy-clean data, which are unavailable in a clinical setting. Therefore, we propose a self-supervised DL denoising method, called Spatio-Angular Noise2Noise, for DMRI denoising.

Approach: We stem from the fact that a network trained with paired noisy data can capture the essential information of underlying clean data for noise reduction.

Results: Extensive experiments on simulated and real datasets demonstrate the superiority of SAN2N over existing DMRI denoising methods.

Impact: SAN2N can reduce the noise effectively and improve the quality of fiber ODFs and tractography.

09:151138.
Unsupervised deep learning for denoising diffusion-weighted images with noise-correction loss functions
Yunwei Chen1, Zhicheng Zhang2, Yanqiu Feng1, and Xinyuan Zhang1
1Southern Medical University, Guangzhou, China, 2JancsiLab, JancsiTech, HongKong, China

Keywords: DWI/DTI/DKI, Brain, denoise

Motivation: Since the noisy magnitude MR data generally follows Rician distribution, using the noisy images and network’s output to construct unsupervised learning’s loss function for denoising will lead to a biased estimation, especially for DW images which suffers from the lower SNR. 

Goal(s): To address the noise bias issue.

Approach: We proposed two noise-correction loss functions for unsupervised denoising of DW images, based on DIP and the characteristics of Rician distribution.

Results: The experimental results on simulated and in-vivo data demonstrated that the proposed loss functions effectively corrected the signal-dependent noise bias and improved the accuracy of unsupervised learning-based DW images denoising method. 

Impact: Firstly, we proposed two noise-correction loss functions and validate their effectiveness in denoising DW images. Secondly, the proposed loss functions are not limited to DW images and can be directly applied to other modality MR images.

09:271139.
Neighborhood-attention models for incorporating spatial information in deep learning parameter estimation applied to IVIM
Misha Pieter Thijs Kaandorp1,2,3, Frank Zijlstra1,2, Davood Karimi3, Ali Gholipour3, and Peter Thomas While1,2
1Department of Radiology and Nuclear Medicine, St. Olav’s University Hospital, Trondheim, Norway, 2Department of Circulation and Medical Imaging, NTNU – Norwegian University of Science and Technology, Trondheim, Norway, 3Department of Radiology, Boston Children’s Hospital, Harvard Medical School, Boston, MA, United States

Keywords: Analysis/Processing, Signal Representations, AI, transformers, synthetic data, parameter estimation, IVIM

Motivation: Conventional model-fitting approaches neglect spatial information. Recent work showed promise in using convolutional neural networks (CNNs) trained on spatially-correlated synthetic data. However, the convergence rate remained suboptimal, and the spatial extent was limited.

Goal(s): To improve estimator performance by utilizing transformer networks and training on larger receptive-fields.  

Approach: Transformers with self-attention and neighborhood-attention with increased receptive-field were trained on spatially-correlated synthetic data (IVIM), and evaluated quantitatively using novel fractal-noise maps and in-vivo scans.

Results: Transformers excelled in integrating spatial information over CNNs. The application of larger receptive-fields with neighborhood-attention effectively leveraged correlated signal information from nearby voxels, leading to improved estimator performance.

Impact: The improved parameter estimation from neighborhood-attention models trained on synthetic data brings challenging ill-posed signal analysis problems, like IVIM, closer to clinical implementation. Additionally, the novel fractal-noise maps provide spatially-correlated ground truths, permitting new approaches to quantitative medical image analysis. 

09:391140.
Diffusion MRI-based Estimation of Cortical Architecture via Machine Learning (DECAM) enhanced by cortical label vectors
Tianjia Zhu1,2, Minhui Ouyang1,3, Xuan Liu4, Risheng Liu4, and Hao Huang1,3
1Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, PA, United States, 2Department of Bioengineering, University of Pennsylvania, Philadelphia, PA, United States, 3Department of Radiology, University of Pennsylvania, Philadelphia, PA, United States, 4School of Information Science and Engineering, Dalian University of Technology, Dalian, China

Keywords: Microstructure, Diffusion/other diffusion imaging techniques, Diffusion analysis and visualization, biomarkers, cortical architecture, non-invasive virtual histology

Motivation: Advanced diffusion MRI (dMRI) has enabled noninvasive assessment of cortical measures conventionally only available from neuropathology. Analytical dMRI models are limited by restrictive model assumptions. 

Goal(s): In this study, we develop Diffusion-MRI based Estimation of Cortical Architecture using Machine-learning (DECAM), a translational framework of “noninvasive neuropathology” that can quantify cortical architecture based on dMRI. 

Approach: DECAM incorporates cortical label vectors to address the challenge of achieving perfect MRI-histology registration in primate brains due to their complex morphology. 

Results: By providing high-fidelity, reproducible whole-brain soma density maps validated with histology, DECAM paves the way for data-driven noninvasive histology for potential applications such as Alzheimer’s.

Impact: DECAM is the first translational framework and robust pipeline that addresses the challenge of estimating high-fidelity whole-brain soma density in primate brains with complex morphology. DECAM paves the way for data-driven noninvasive histology for potential applications such as Alzheimer’s.

09:511141.
AID-DTI: fast and high-fidelity diffusion tensor imaging with detail-preserving model-based deep learning
Wenxin Fan1,2, Cheng Li1, Jing Yang3,4, Juan Zou5,6, Hairong Zheng1, and Shanshan Wang1,7,8
1Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, 2University of Chinese Academy of Science, Beijing, China, 3Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, 4University of Chinese Academy of Science, Beijing, China,, Beijing, China, 5School of Physics and Optoelectronics, Xiangtan University, Xiangtan, China, 6Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, 7Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China, 8Peng Cheng Laboratory, Shenzhen, China

Keywords: DWI/DTI/DKI, Diffusion Tensor Imaging, Deep Learning

Motivation: Existing methods tend to suffer from Rician noise, leading to detail loss during the reconstruction of DTI-derived parametric maps. This issue becomes particularly pronounced when sparsely sampled q-space data are used.

Goal(s): Our goal was to facilitate fast and high-fidelity estimation of DTI metrics.

Approach: We propose a novel SVD-based regularizer, which can effectively preserve fine details while suppressing noise during network training.

Results: Experimental results consistently demonstrate that the proposed method estimates DTI parameter maps with finer details, outperforming current state-of-the-art methods.

Impact: The proposed method may facilitate fast and high-fidelity DTI with a newly designed SVD-based regularizer, and it has a potential to become a practical tool in clinical and neuroscientific applications.

10:031142.
A Contrastive Learning for Accelerating Diffusion Tensor Imaging with High Adaptability to Diffusion Gradient Schemes
Siyun Jung1, Jae-Yoon Kim1, and Dong-Hyun Kim1
1Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea, Republic of

Keywords: Diffusion Reconstruction, Diffusion Tensor Imaging

Motivation: High-quality DTI requires numerous DWIs, extending scan times; however, despite deep learning's advances in reconstructing DTI with fewer DWIs, its adaptability across various gradient protocols remains limited, challenging its clinical application.

Goal(s): Our aim is to enable consistent, high-quality DTI reconstructions from fewer DWIs across different gradient schemes, enhancing adaptability in various clinical environments.

Approach: We employ self-supervised contrastive learning to extract and preserve key features between datasets derived from the same data with different gradient sampling methods.

Results: Our method reliably enhanced diffusion tensor maps from reduced DWIs across various gradient sampling schemes, outperforming both conventional methods and state-of-the-art deep learning model.

Impact: Our method creates high-quality DTI from fewer DWIs, reducing scan times and easing patient burden, while showing consistent performance across various gradient sampling schemes, ensuring high adaptability and ease of use in diverse clinical settings.