Fast and Robust Deep Learning for Medical imaging: Segmentation and Registration methods invariant to contrast and resolution

快速、鲁棒的医学成像深度学习：对比度和分辨率不变的分割和配准方法

• 批准号: 10733935
• 负责人: Adrian Dalca
• 金额: $ 58.5万
• 依托单位: MASSACHUSETTS GENERAL HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-06 至 2027-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10733935
• 关键词: Address; Age; Anatomy; Basic Science; Bayesian Modeling; Biological; Clinical; Clinical Investigator; Clinical Research; Collection; Computer software; Data; Data Set; Development; Disease; Disease Pathway; Drug Targeting; Image; Image Analysis; Knowledge; Label; Learning; Lesion; Longitudinal Studies; Machine Learning; Magnetic Resonance Imaging; Manuals; Maps; Medical Imaging; Methods; Modality; Modeling; Morphologic artifacts; Motion; Multimodal Imaging; Noise; Output; Phenotype; Physics; Predisposition; Process; Protocols documentation; Qualifying; Race; Recording of previous events; Research; Research Personnel; Resolution; Resources; Scanning; Science; Scientist; Site; Source; Source Code; Speed; Stroke; Stroke prevention; System; Techniques; Testing; Therapeutic Intervention; Training; Treatment Efficacy; Variant; White Matter Hyperintensity; Work; brain magnetic resonance imaging; cerebrovascular; clinical care; clinical imaging; cohort; deep learning; deep neural network; design; experience; heterogenous data; human disease; image registration; imaging Segmentation; improved; insight; learning strategy; multimodality; neural network; novel; open source; open source tool; sex; skills; stroke outcome; success; tool; validation studies; white matter

Project Summary Title Fast and Robust Deep Learning for Medical imaging: Segmentation and Registration methods invariant to con- trast and resolution. Summary Segmentation and registration are critical tasks in a broad range of scientific studies, and have been widely implemented in imaging analysis frameworks. Unfortunately, most existing tools suffer from two important draw- backs: they are computationally demanding, and most often impose limiting restrictions on the type of image data that can be accurately analyzed. While the former drawback has been recently addressed through the use of deep neural networks that execute rapidly once trained, these systems amplify the latter, which remains a major restriction. This typically means that tools only yield accurate results on a very limited range of scan types, most commonly those that they were trained on and are susceptible to repeating bias present in those data. For segmentation this is particularly burdensome as training frequently requires manually labeled representations for different types of input data. The constraint of image type greatly restricts image analysis and its downstream impact in an array of important domains. For example, in research imaging, it limits multi-site and longitudinal studies that must hold acquisition protocols constant or attempt to harmonize protocols across different acquisition platforms, and even this process has limited success when the differences are too extreme (e.g. across field strength). Investigators often need to adjust, redesign, or retrain the tools for their intended tasks and available images and manual labels, leading to more barriers to analysis. There is also a wealth of knowledge to be gained from analyzing clinically-sourced MR images, which could lead to better understanding of the biological underpinnings of many disease processes and a more precise quantification of the efficacy of therapeutic interventions. However, scans acquired as part of routine clinical care are often of diverse contrast, significantly lower resolution, and lower quality due to noise or subject motion. There are few if any publicly available tools that can handle the wide range of acquisition variability in typical clinical imaging. We propose to design and distribute machine learning based tools to completely remove these barriers. We will develop imaging segmentation and registration deep learning methods that retain their accuracy given unpro- cessed scans of most contrasts or resolution without the need for training data or network fine-tuning to each data variation. We will build on our recent work in learning-based methods for segmentation, registration, syn- thesis, and augmentation to leverage the speed of neural networks, the richness of MR physics models, and the generalizability of probabilistic Bayesian models. We will validate these tools on a large comprehensive multi-site study incorporating new manual labeling of scans spanning different age, sex, and race . Finally, we will deploy them to analyze anatomy and white matter lesions in a retrospective stroke cohort. The novel techniques will be implemented both as standalone open source software as well as part of FreeSurfer analysis package, making them freely available to thousands of method developers as well as science and clinical researchers.

项目摘要 标题 医学成像的快速和鲁棒的深度学习：不受约束的分割和配准方法 信任与决心 总结 分割和配准是广泛的科学研究中的关键任务，并且已经被广泛应用。 在成像分析框架中实现。不幸的是，大多数现有的工具都有两个重要的缺点- 背面：它们对计算要求很高，并且通常对图像类型施加限制 可以准确分析的数据。虽然前一个缺点最近已经通过使用 深度神经网络一旦训练就能快速执行，这些系统放大了后者，后者仍然是一个 主要限制。这通常意味着工具只能在非常有限的扫描类型范围内产生准确的结果， 最常见的是那些他们接受过培训的数据，并且容易受到这些数据中存在的重复偏差的影响。为 这是特别繁重的，因为训练经常需要手动标记表示， 不同类型的输入数据。 图像类型的约束极大地限制了图像分析及其在一系列重要的 域.例如，在研究成像中，它限制了必须保持采集的多站点和纵向研究 协议恒定或尝试协调不同采集平台之间的协议，甚至此过程 当差异太极端时（例如，跨场强），成功有限。调查人员往往需要 调整、重新设计或重新培训工具，以实现其预期任务以及可用图像和手册标签， 更多的分析障碍。从临床来源的分析中也可以获得丰富的知识。 磁共振成像，这可能导致更好地了解许多疾病过程的生物学基础 以及更精确地量化治疗干预的功效。然而，作为一部分， 常规临床护理的对比度通常不同，分辨率明显较低，并且由于噪声而质量较低 或主体运动。几乎没有任何公开可用的工具可以处理广泛的收购 典型临床成像的可变性。 我们建议设计和分发基于机器学习的工具，以完全消除这些障碍。我们将 开发成像分割和配准深度学习方法，保持其准确性， 大多数对比度或分辨率的扫描，而不需要训练数据或网络微调到每个 数据变异我们将建立在我们最近的工作，在基于学习的方法分割，注册，同步， 论文，并增强利用神经网络的速度，丰富的MR物理模型， 概率贝叶斯模型的推广。我们将在大型综合多站点上验证这些工具 研究纳入了新的手动标记扫描跨越不同年龄，性别和种族。最后，我们将部署 在回顾性卒中队列中分析解剖学和白色病变。新技术将是 作为独立的开源软件以及FreeSurfer分析包的一部分实现， 它们免费提供给成千上万的方法开发人员以及科学和临床研究人员。