在放射学实践中，常规获取多序列MRI以表征解剖结构和组织。然而，由于成像协议的异质性和对造影剂的禁忌症，某些MRI序列（例如对比增强T1加权图像（T1ce））可能无法获取。这给汇总异构数据集的大规模临床研究带来了困难。现代深度学习技术已展现出通过从广泛的多序列MRI数据集中学习来从现有序列合成缺失序列的能力。在本文中，我们提出了一种基于局部隐式神经表示的新型MR图像转换解决方案。我们将可用的MRI序列分割为局部图像块，并为每个图像块分配一个局部多层感知机（MLP），以表示T1ce中的图像块。这些局部MLP的参数由基于图像特征的超网络生成。在BraTS挑战赛数据集上的实验结果和消融研究表明，局部MLP对于恢复精细的图像和肿瘤细节至关重要，因为它们允许局部特化，这对于准确的图像转换非常重要。与经典的pix2pix模型相比，所提出的方法展示了视觉改善和显著提高的定量分数（MSE 0.86 x 10^-3 vs. 1.02 x 10^-3，SSIM 94.9 vs 94.3）。
英文摘要：
In radiological practice, multi-sequence MRI is routinely acquired to characterize anatomy and tissue. However, due to the heterogeneity of imaging protocols and contra-indications to contrast agents, some MRI sequences, e.g. contrast-enhanced T1-weighted image (T1ce), may not be acquired. This creates difficulties for large-scale clinical studies for which heterogeneous datasets are aggregated. Modern deep learning techniques have demonstrated the capability of synthesizing missing sequences from existing sequences, through learning from an extensive multi-sequence MRI dataset. In this paper, we propose a novel MR image translation solution based on local implicit neural representations. We split the available MRI sequences into local patches and assign to each patch a local multi-layer perceptron (MLP) that represents a patch in the T1ce. The parameters of these local MLPs are generated by a hypernetwork based on image features. Experimental results and ablation studies on the BraTS challenge dataset showed that the local MLPs are critical for recovering fine image and tumor details, as they allow for local specialization that is highly important for accurate image translation. Compared to a classical pix2pix model, the proposed method demonstrated visual improvement and significantly improved quantitative scores (MSE 0.86 x 10^-3 vs. 1.02 x 10^-3 and SSIM 94.9 vs 94.3)
Unsupervised domain adaptation is a type of domain adaptation and exploits labeled data from the source domain and unlabeled data from the target one. In the Cross-Modality Domain Adaptation for Medical Image Segmenta-tion challenge (crossMoDA2022), contrast enhanced T1 MRI volumes for brain are provided as the source domain data, and high-resolution T2 MRI volumes are provided as the target domain data. The crossMoDA2022 challenge contains two tasks, segmentation of vestibular schwannoma (VS) and cochlea, and clas-sification of VS with Koos grade. In this report, we presented our solution for…
Do High-Performance Image-to-Image Translation Networks Enable the Discovery of Radiomic Features? Application to MRI Synthesis from Ultrasound in Prostate Cancer
Parallel imaging is a widely-used technique to accelerate magnetic resonance imaging (MRI). However, current methods still perform poorly in reconstructing artifact-free MRI images from highly undersampled k-space data. Recently, implicit neural representation (INR) has emerged as a new deep learning paradigm for learning the internal continuity of an object. In this study, we adopted INR to parallel MRI reconstruction. The MRI image was modeled as a continuous function of spatial coordinates. This function was parameterized by a neural network and learned directly from the measured k-space it…
Center for Translational Research in Neuroimaging and Data Science (TReNDS)（神经影像与数据科学转化研究中心（TReNDS））
Deep learning has become a prominent computational modeling tool in the areas of computer vision and image processing in recent years. This research comprehensively analyzes the different deep-learning methods used for image-to-image translation and reconstruction in the natural and medical imaging domains. We examine the famous deep learning frameworks, such as convolutional neural networks and generative adversarial networks, and their variants, delving into the fundamental principles and difficulties of each. In the field of natural computer vision, we investigate the development and extens…
Tel Aviv University（特拉维夫大学）；GE Research（GE研究院）；GE Healthcare（GE医疗）
Recent accelerated MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes struggle to reconstruct sharp images that preserve fine detail while maintaining a natural appearance. In this work, we enhance the image quality by using a Conditional Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing (AGB) technique that automates the process of combining the adversarial and pixel-wise terms and st…
Multi-modal MRI Translation via Evidential Regression and Distribution Calibration
Fudan University（复旦大学）；University of Cambridge（剑桥大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Fuzhou University（福州市大学）；Shanghai Jiao Tong University（上海交通大学）
Comparative Analysis of GAN and Diffusion for MRI-to-CT translation
Department of Computer Science, University of Copenhagen, Copenhagen, Denmark（哥本哈根大学计算机科学系）；Department of Oncology, Rigshospitalet, Copenhagen, Denmark（哥本哈根医院肿瘤科）
Single-Subject Multi-View MRI Super-Resolution via Implicit Neural Representations
Department of Radiology, Weill Cornell Medicine, New York, USA（韦尔·科恩医学系放射科，纽约，美国）；School of Electrical and Computer Engineering, Cornell University（康奈尔大学电气与计算机工程学院）；Cornell Tech, New York, USA（康奈尔科技，纽约，美国）；Weill Cornell Graduate School of Medical Sciences, New York, USA（韦尔·科恩医学科学研究生院，纽约，美国）
Stanford University（斯坦福大学）；GE Healthcare（通用电气医疗集团）；University of California Riverside（加州大学河滨分校）；National Taiwan University（台湾大学）
Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of cerebrovascular diseases such as Moyamoya, carotid stenosis, aneurysms, and stroke. Positron emission tomography (PET) is currently regarded as the gold standard for the measurement of CBF in the human brain. PET imaging, however, is not widely available because of its prohibitive costs, use of ionizing radiation, and logistical challenges, which require a co-localized cyclotron to deliver the 2 min half-life Oxygen-15 radioisotope. Magnetic resonance imaging (MRI), in contrast, is more readil…
Politecnico di Milano（米兰理工大学）；University of Twente（特温特大学）；University of Bath（巴斯大学）；University of Cambridge（剑桥大学）
4D flow MRI is a non-invasive imaging method that can measure blood flow velocities over time. However, the velocity fields detected by this technique have limitations due to low resolution and measurement noise. Coordinate-based neural networks have been researched to improve accuracy, with SIRENs being suitable for super-resolution tasks. Our study investigates SIRENs for time-varying 3-directional velocity fields measured in the aorta by 4D flow MRI, achieving denoising and super-resolution. We trained our method on voxel coordinates and benchmarked our approach using synthetic measurements…
Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstruction
School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China（上海交通大学生物医学工程学院）；School of Information Science and Technology, ShanghaiTech University, Shanghai, China（上海科技大学信息科学与技术学院）；iHuman Institute, Shanghaitech University, Shanghai, China（上海科技大学iHuman研究所）
Self-Supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representation
Helmholtz Center Munich（慕尼黑亥姆霍兹中心）；Technical University of Munich（慕尼黑工业大学）；Imperial College London（伦敦帝国学院）；Millenium Institute for Intelligent Healthcare Engineering（千禧智能医疗工程研究所）；Pontificia Universidad Católica de Chile（智利天主教大学）；King’s College London（伦敦国王学院）
Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resolution. Super-resolution technique can enhance the through-plane resolution of MR images to facilitate downstream visualization and computer-aided diagnosis. However, most existing works train the super-resolution network at a fixed scaling factor, which is not friendly to clinical scenes of varying inter-slice spacing in MR scanning. Inspired by the recent progress in implicit neural representation, we propose a Spatial…
Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static $q$-space sampling during training and reconstruction. Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography. We propose a generative adversarial translation framework for high-quality DWI synthesis with arbitrary $q$-space…
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
Department of Bioengineering and Imperial-X, Imperial College London（生物工程系和Imperial-X，帝国理工学院伦敦分校）；Department of Bioengineering, Imperial College London（生物工程系，帝国理工学院伦敦分校）
MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstruction
Department of Bioengineering and I-X, Imperial College London（生物工程系和I-X，帝国理工学院伦敦分校）；Cardiovascular Research Centre, Royal Brompton Hospital（心脏血管研究中心，皇家布隆特医院）；National Heart and Lung Institute, Imperial College London（国家心脏和肺研究所，帝国理工学院伦敦分校）；School of Biomedical Engineering & Imaging Sciences, King’s College London（生物医学工程与成像科学学院，伦敦国王学院）；Shanghai Pudong Hospital and Human Phenome Institute, Fudan University（上海浦东医院和人类表型研究所，复旦大学）；International Human Phenome Institute (Shanghai), Shanghai, China（国际人类表型研究所（上海），上海，中国）
VinAI Research（VinAI研究院）；FPT University（FPT大学）；University of Arkansas（阿肯色大学）
Image synthesis from corrupted contrasts increases the diversity of diagnostic information available for many neurological diseases. Recently the image-to-image translation has experienced significant levels of interest within medical research, beginning with the successful use of the Generative Adversarial Network (GAN) to the introduction of cyclic constraint extended to multiple domains. However, in current approaches, there is no guarantee that the mapping between the two image domains would be unique or one-to-one. In this paper, we introduce a novel approach to unpaired image-to-image tr…
Influence of High-Performance Image-to-Image Translation Networks on Clinical Visual Assessment and Outcome Prediction: Utilizing Ultrasound to MRI Translation in Prostate Cancer
Memorial Sloan Kettering Cancer Center（纪念斯隆-凯特琳癌症中心）
Our contribution is a unified cross-modality feature disentagling approach for multi-domain image translation and multiple organ segmentation. Using CT as the labeled source domain, our approach learns to segment multi-modal (T1-weighted and T2-weighted) MRI having no labeled data. Our approach uses a variational auto-encoder (VAE) to disentangle the image content from style. The VAE constrains the style feature encoding to match a universal prior (Gaussian) that is assumed to span the styles of all the source and target modalities. The extracted image style is converted into a latent style sc…
Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation
Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程系，沈阳，中国）；Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China（教育部医学图像智能计算重点实验室，东北大学，沈阳，中国）；National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Shenyang, China（工业智能与系统优化国家级前沿科学中心，沈阳，中国）；Amii, University of Alberta, Edmonton, Alberta, Canada（阿尔伯塔大学阿米人工智能研究所，埃德蒙顿，阿尔伯塔，加拿大）；AiShiWeiLai AI Research, Beijing, China（人工智能研究（北京）有限公司，北京，中国）
Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；The Hong Kong Polytechnic University（香港理工大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Meta-learning Slice-to-Volume Reconstruction in Fetal Brain MRI using Implicit Neural Representations
School of Computation, Information and Technology, and School of Medicine and Health, Technical University Munich（计算、信息与技术学院，以及医学与健康学院，技术大学慕尼黑）；CIBM Center for Biomedical Imaging and Radiology Department of Lausanne University Hospital and University of Lausanne（日内瓦大学医院与日内瓦大学生物医学影像与放射学中心部门）；Centre for the Developing Brain, School of Biomedical Engineering and Imaging Sciences, King’s College London（发展脑中心，生物医学工程与影像科学学院，伦敦国王学院）；Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid（生物医学影像技术，电信工程学院，马德里理工大学）；Department of Computing, Imperial College London（计算学院，伦敦帝国学院）
Massachusetts General Hospital（马萨诸塞总医院）；Harvard Medical School（哈佛医学院）
Multimodal MRI provides complementary and clinically relevant information to probe tissue condition and to characterize various diseases. However, it is often difficult to acquire sufficiently many modalities from the same subject due to limitations in study plans, while quantitative analysis is still demanded. In this work, we propose a unified conditional disentanglement framework to synthesize any arbitrary modality from an input modality. Our framework hinges on a cycle-constrained conditional adversarial training approach, where it can extract a modality-invariant anatomical feature with …
FS-RWKV: Leveraging Frequency Spatial-Aware RWKV for 3T-to-7T MRI Translation
Faculty of Science and Technology, University of Macau（澳门大学科学与技术学院）；School of Electronic and Communication Engineering, Shenzhen Polytechnic University（深圳职业技术学院电子与通信工程学院）；Department of Cardiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China（广东省人民医院心内科（广东省医学科学院））；Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China（广东省心血管病研究院，广东省人民医院，广东省医学科学院，广州，中国）
Mass General Brigham, Harvard Medical School, MA, United States（马萨诸塞州总医院、哈佛医学院）；Department of Statistics, University of South Carolina, SC, United States（统计学系，南卡罗来纳大学）；Department of Anatomy and Neurobiology, Boston University Chobanian & Avedisian School of Medicine, MA, United States（解剖学与神经生物学系，波士顿大学钱德林与阿维迪亚安医学学院）；Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, MA, United States（阿提诺拉A·马丁诺斯生物医学成像中心，马萨诸塞总医院）；Department of Radiology, Harvard Medical School, MA, United States（放射学系，哈佛医学院）；Harvard/MIT Health Sciences and Technology, MA, United States（哈佛/麻省理工健康科学与技术）
PISCO: Self-Supervised k-Space Regularization for Improved Neural Implicit k-Space Representations of Dynamic MRI
Helmholtz Munich（亥姆霍兹慕尼黑中心）；Technical University of Munich（慕尼黑工业大学）；Klinikum rechts der Isar（右岸医院（慕尼黑工业大学附属））；Imperial College London（帝国理工学院）；Pontificia Universidad Católica de Chile（智利天主教大学）；King’s College London（伦敦国王学院）
Accelerated Patient-specific Non-Cartesian MRI Reconstruction using Implicit Neural Representations
University of California, San Francisco（加利福尼亚大学旧金山分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Keck School of Medicine, University of Southern California（南加州大学凯克医学院）；University of San Francisco（旧金山大学）
School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）；School of Information Science and Technology, ShanghaiTech University（上海交通大学信息科学与技术学院）；School of Biomedical Engineering and the National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy (NERCAMRT), Shanghai Jiao Tong University（上海交通大学生物医学工程学院和先进磁共振诊断与治疗国家工程研究中心）
Efficient MRI Parallel Imaging Reconstruction by K-Space Rendering via Generalized Implicit Neural Representation
Department of Neuroradiology, University Hospital Heidelberg（神经放射科，海德堡大学医院）；School of Electrical Engineering and Automation, Wuhan University（电气工程与自动化学院，武汉大学）；Momoni AI；Department of Stomatology, Shenzhen People’s Hospital（口腔科，深圳人民医院）；College of Science and Engineering, James Cook University（科学与工程学院，詹姆斯库克大学）；Department of Game Design, Faculty of Arts, Uppsala University（游戏设计系，艺术学院，乌普萨拉大学）；School of Computer Science, University of Sydney（计算机科学学院，悉尼大学）；School of Biomedical Engineering, The University of Sydney（生物医学工程学院，悉尼大学）
提出一种基于广义 INR 的 MRI 并行成像重建框架，利用尺度嵌入编码器和体素先验渲染全采样 k 空间，在 4–6 倍加速下提升质量并降低计算开销。
Continuous K-space Recovery Network with Image Guidance for Fast MRI Reconstruction
The Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention（上海医学影像计算与计算机辅助介入重点实验室）；Academy of Engineering and Technology, Fudan University（复旦大学工程与技术学院）
Bilkent University（比尔肯特大学）；University of Southern California（南加州大学）
Multi-institutional collaborations are key for learning generalizable MRI synthesis models that translate source- onto target-contrast images. To facilitate collaboration, federated learning (FL) adopts decentralized training and mitigates privacy concerns by avoiding sharing of imaging data. However, FL-trained synthesis models can be impaired by the inherent heterogeneity in the data distribution, with domain shifts evident when common or variable translation tasks are prescribed across sites. Here we introduce the first personalized FL method for MRI Synthesis (pFLSynth) to improve reliabil…
Imperial College London（帝国理工学院）；University of Edinburgh（爱丁堡大学）
Image registration is an ill-posed inverse problem which often requires regularisation on the solution space. In contrast to most of the current approaches which impose explicit regularisation terms such as smoothness, in this paper we propose a novel method that can implicitly learn biomechanics-informed regularisation. Such an approach can incorporate application-specific prior knowledge into deep learning based registration. Particularly, the proposed biomechanics-informed regularisation leverages a variational autoencoder (VAE) to learn a manifold for biomechanically plausible deformations…
