Deep Learning for Detecting the Early Anatomical Effects of Alzheimer's Disease

深度学习检测阿尔茨海默病的早期解剖学影响

• 批准号: 10658045
• 负责人: Bruce Fischl
• 金额: $ 19.87万
• 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: 2023-06-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10658045
• 关键词: Accounting; Alzheimer' s Disease; Alzheimer' s disease related dementia; Alzheimer' s disease risk; Anatomic Models; Anatomy; Atrophic; Behavior; Cell Death; Clinical; Clinical Research; Clinical Trials; Computer software; Darkness; Data; Data Set; Detection; Development; Diagnosis; Dimensions; Disease; Early Diagnosis; Ensure; Generations; Hippocampus; Image; Impaired cognition; Label; Learning; Left; Lesion; Location; Magnetic Resonance Imaging; Manuals; Maps; Modality; Modernization; Neuroanatomy; Neurologic; Noise; Picture Archiving and Communication System; Positron-Emission Tomography; Predisposition; Procedures; Process; Progressive Disease; Property; Protocols documentation; Research; Scanning; Schedule; Sensitivity and Specificity; Series; Shapes; Site; Structure; Surrogate Endpoint; Techniques; Technology; Testing; Thalamic structure; Therapeutic Intervention; Time; Training; Treatment Efficacy; Validation; Variant; Ventricular; clinical application; clinical imaging; deep learning; deep neural network; design; disease classification; follow-up; imaging modality; improved; learning network; longitudinal analysis; neuropathology; simulation; therapeutically effective; tool; usability

Project Summary Longitudinal, within-subject approaches, have the potential to increase sensitivity and specificity, improving the efficiency of clinical trials by requiring fewer subjects and providing potential surrogate endpoints to assess therapeutic efficacy. There is also great potential that these tools will enable more sophisticated anatomical modeling to better understand the temporal dynamics of progression. In Alzheimer’s Disease in particular, early detection, prior to widespread and likely irreversible cell death, is crucial for the development of effective therapeutic interventions. However, longitudinal tools have not yet been optimized for use in clinical studies. Challenges include the reduction of noise across serial scans while providing each time point equal relative weighting to avoid bias; adequately and appropriately accounting for atrophy; and handling varying MRI contrast and distortion across time. In this proposal, we seek to improve longitudinal analysis in a number of ways, leveraging the power of modern deep learning to increase accuracy, make it applicable to any type of MRI contrast, radically reduce execution time, as well as make it usable in direct clinical applications. To achieve these aims we will employ newly developed image synthesis techniques to train networks to detect small, “true” anatomical change hidden within a set of large-scale “MRI” distortions, that will capture longitudinal differences in image acquisition such as gradient nonlinearities, field strength and B0 distortions, and sequence parameter variations. The change-detection network will be cascaded with a deep registration network that will learn to decompose the temporal warp into uninteresting MRI distortions and interesting anatomical effects, then both warp fields and the aligned images will be provided to a segmentation network to ensure no information is lost by the registration. The networks will learn to ignore MRI effects based on their stereotypical behavior (e.g. the one-dimensionality of B0 distortions, the spatial smoothness of gradient nonlinearities) and to detect the subtle anatomical changes such as increasing ventricular size or decreasing hippocampal volume. The result will be a set of robust contrast-and-distortion-agnostic tools that highlight potential disease effects for clinicians.

项目摘要 纵向内部的方法有可能提高灵敏度和特异性，改善 临床试验的效率通过减少受试者并为潜在的替代终点提供的效率 评估治疗效率。这些工具也将使更复杂的工具具有很大的潜力 解剖模型可以更好地理解进展的临时动力学。在阿尔茨海默氏病 特别的，早期检测，在宽度和可能不可逆的细胞死亡之前，对发展至关重要 有效的治疗干预措施。但是，尚未优化纵向工具用于 临床研究。挑战包括在每个时间点提供串行扫描的噪声降低 相对的相对权重以避免偏见；充分，适当地考虑萎缩；和处理 随时间变化的MRI对比度和失真。在此提案中，我们试图改善 多种方式，利用现代深度学习的力量提高准确性，使其适用于 任何类型的MRI对比度，从根本上减少执行时间，并使其可在直接临床中使用 申请。 为了实现这些目标，我们将采用新开发的图像合成技术来训练网络以检测 在一组大规模的“ MRI”扭曲中隐藏了小的“真实”解剖变化，它将捕获 图像采集的纵向差异，例如梯度非线性，野外强度和B0扭曲， 和序列参数变化。变更检测网络将通过深入注册级联 将学会将临时翘曲分解为无趣的MRI扭曲和有趣的网络 解剖效应，然后将两个经线字段和对齐图像提供给分割网络 确保注册不会丢失任何信息。网络将学会根据 它们的定型行为（例如，B0扭曲的一维性，梯度的空间平滑度 非线性）并检测微妙的解剖变化，例如增加心室尺寸或减小 海马体积。结果将是一组强大的对比度和分数不合骨的工具，这些工具突出显示 对临床医生的潜在疾病影响。