High-fidelity semantic segmentation of magnetic resonance volumes is critical for estimating tissue morphometry and relaxation parameters in both clinical and research applications. While manual segmentation is accepted as the gold-standard, recent advances in deep learning and convolutional neural networks (CNNs) have shown promise for efficient automatic segmentation of soft tissues. However, due to the stochastic nature of deep learning and the multitude of hyperparameters in training networks, predicting network behavior is challenging. In this paper, we quantify the impact of three factors associated with CNN segmentation performance: network architecture, training loss functions, and training data characteristics. We evaluate the impact of these variations on the segmentation of femoral cartilage and propose potential modifications to CNN architectures and training protocols to train these models with confidence.
University of Leicester（莱斯特大学）；NIHR Leicester Biomedical Research Centre（NIHR莱斯特生物医学研究中心）；Glenfield Hospital（格伦菲尔德医院）；Norwegian University of Science and Technology (NTNU)（挪威科技大学）；Saint-Petersburg State Electrotechnical University（圣彼得堡国立电工大学）
A "heart attack" or myocardial infarction (MI), occurs when an artery supplying blood to the heart is abruptly occluded. The "gold standard" method for imaging MI is Cardiovascular Magnetic Resonance Imaging (MRI), with intravenously administered gadolinium-based contrast (late gadolinium enhancement). However, no "gold standard" fully automated method for the quantification of MI exists. In this work, we propose an end-to-end fully automatic system (MyI-Net) for the detection and quantification of MI in MRI images. This has the potential to reduce the uncertainty due to the technical variabil…
Four-dimensional magnetic resonance imaging (4D-MRI) is an emerging technique for tumor motion management in image-guided radiation therapy (IGRT). However, current 4D-MRI suffers from low spatial resolution and strong motion artifacts owing to the long acquisition time and patients' respiratory variations; these limitations, if not managed properly, can adversely affect treatment planning and delivery in IGRT. Herein, we developed a novel deep learning framework called the coarse-super-resolution-fine network (CoSF-Net) to achieve simultaneous motion estimation and super-resolution in a unifi…
Correlated and Multi-frequency Diffusion Modeling for Highly Under-sampled MRI Reconstruction
School of Mathematics and Computer Sciences, Nanchang University（南昌大学数学与计算机科学学院）；School of Information Engineering, Nanchang University（南昌大学信息工程学院）；Research Center for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院医学人工智能研究中心）
University of Notre Dame（圣母大学）；Guangdong Cardiovascular Institute（广东省心血管病研究所）；Guangdong Provincial People’s Hospital（广东省人民医院）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Pittsburgh（匹兹堡大学）
Real-time cardiac magnetic resonance imaging (MRI) plays an increasingly important role in guiding various cardiac interventions. In order to provide better visual assistance, the cine MRI frames need to be segmented on-the-fly to avoid noticeable visual lag. In addition, considering reliability and patient data privacy, the computation is preferably done on local hardware. State-of-the-art MRI segmentation methods mostly focus on accuracy only, and can hardly be adopted for real-time application or on local hardware. In this work, we present the first hardware-aware multi-scale neural archite…
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is widely used to complement ultrasound examinations and x-ray mammography during the early detection and diagnosis of breast cancer. However, images generated by various MRI scanners (e.g. GE Healthcare vs Siemens) differ both in intensity and noise distribution, preventing algorithms trained on MRIs from one scanner to generalize to data from other scanners successfully. We propose a method for image normalization to solve this problem. MRI normalization is challenging because it requires both normalizing intensity values and map…
P-Count: Persistence-based Counting of White Matter Hyperintensities in Brain MRI
Martinos Center for Biomedical Imaging, MGH and Harvard Medical School（马蒂诺斯生物医学成像中心，麻省总医院与哈佛医学院）；Center for Medical Image Computing, University College London（伦敦大学学院医学影像计算中心）；Amsterdam University Medical Center（阿姆斯特丹大学医学中心）；Danish Research Centre for Magnetic Resonance, Copenhagen University Hospital（哥本哈根大学医院丹麦磁共振研究中心）；Computer Science and Artificial Intelligence Laboratory, MIT（麻省理工学院计算机科学与人工智能实验室）
MRI Super-Resolution with Deep Learning: A Comprehensive Survey
A. I. Virtanen Institute for Molecular Sciences, Faculty of Health Sciences, University of Eastern Finland（A.I.维塔内恩分子科学研究所，健康科学学院，东芬兰大学）；Harvard Medical School and Boston Children’s Hospital（哈佛医学院和波士顿儿童医院）；Department of Radiology, Technical University of Munich（医学影像学系，慕尼黑技术大学）；Department of Radiology, Massachusetts General Hospital（医学影像学系，麻省总医院）
University of Sydney（悉尼大学）；University of New South Wales（新南威尔士大学）；Sydney Neuroimaging Analysis Centre（悉尼神经影像分析中心）
Multiple sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system, characterized by the appearance of focal lesions in the white and gray matter that topographically correlate with an individual patient's neurological symptoms and signs. Magnetic resonance imaging (MRI) provides detailed in-vivo structural information, permitting the quantification and categorization of MS lesions that critically inform disease management. Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-obser…
RSFR: A Coarse-to-Fine Reconstruction Framework for Diffusion Tensor Cardiac MRI with Semantic-Aware Refinement
Imperial College London（帝国理工学院伦敦分校）；National Heart and Lung Institute（国家心肺研究所）；Cardiovascular Research Centre（心血管研究中心）；Royal Brompton Hospital（皇家布里蒙特医院）；School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区生物医学工程学院）；Robotics and Autonomous Systems Thrust & Data Science and Analytics Thrust, HKUST (GZ)（香港科技大学（广州）机器人与自主系统 thrust 及数据科学与分析 thrust）；Yau Mathematical Sciences Centre, Tsinghua University（清华大学姚数学科学中心）；Department of Applied Mathematics and Theoretical Physics, University of Cambridge（剑桥大学应用数学与理论物理系）；School of Biomedical Engineering and Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与影像科学学院）
Arizona State University（亚利桑那州立大学）；Barrow Neurological Institute（巴罗神经学研究所）；Mayo Clinic Arizona（亚利桑那州梅奥诊所）
Typical Magnetic Resonance Imaging (MRI) scan may take 20 to 60 minutes. Reducing MRI scan time is beneficial for both patient experience and cost considerations. Accelerated MRI scan may be achieved by acquiring less amount of k-space data (down-sampling in the k-space). However, this leads to lower resolution and aliasing artifacts for the reconstructed images. There are many existing approaches for attempting to reconstruct high-quality images from down-sampled k-space data, with varying complexity and performance. In recent years, deep-learning approaches have been proposed for this task, …
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）
Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）；Graz University of Technology（格拉茨工业大学）；GE Healthcare（GE医疗）
Purpose: To investigate feasibility of accelerating prostate diffusion-weighted imaging (DWI) by reducing the number of acquired averages and denoising the resulting image using a proposed guided denoising convolutional neural network (DnCNN). Materials and Methods: Raw data from the prostate DWI scans were retrospectively gathered (between July 2018 and July 2019) from six single-vendor MRI scanners. 118 data sets were used for training and validation (age: 64.3 +- 8 years) and 37 - for testing (age: 65.1 +- 7.3 years). High b-value diffusion-weighted (hb-DW) data were reconstructed into nois…
South China University of Technology（华南理工大学）；Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences（广东省人民医院，广东省医学科学院）
Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain tumor diagnosis, cancer management and research purposes. With the great success of the ten-year BraTS challenges as well as the advances of CNN and Transformer algorithms, a lot of outstanding BTS models have been proposed to tackle the difficulties of BTS in different technical aspects. However, existing studies hardly consider how to fuse the multi-modality images in a reasonable manner. In this paper, we leverage the clinical knowledge of how radiologists diagnose brain tumors from multiple MRI modalities…
