Next generation axonal quantification and classification using AI

使用人工智能的下一代轴突量化和分类

• 批准号: 10324805
• 负责人: Paul Angstman
• 金额: $ 44.98万
• 依托单位: MICROBRIGHTFIELD, LLC
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-19 至 2022-08-18
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10324805
• 关键词: 3-Dimensional; Acute; Address; Animal Model; Area; Artificial Intelligence; Autopsy; Axon; Biotechnology; Brain Diseases; Classification; Collaborations; Communities; Complex; Computer Assisted; Computer software; Detection; Development; Feasibility Studies; Fiber; Goals; Gold; High Performance Computing; Human; Image; Individual; Knowledge; Laboratories; Learning; Logic; Machine Learning; Methods; Morphology; National Institute of Mental Health; Nature; Neuraxis; Neurodegenerative Disorders; Neurodevelopmental Disorder; Neurosciences Research; Pattern; Pharmacology; Phase; Physiological; Publishing; Research; Research Personnel; Societies; Synapses; System; Technology; Time; Tissues; Transgenic Animals; Validation; Work; automated segmentation; axon injury; base; convolutional neural network; density; fighting; image processing; improved; innovation; insight; microscopic imaging; nervous system disorder; neural network; neuropsychiatric disorder; new technology; next generation; novel; operation; prevent; prototype; reconstruction; research and development; terabyte; treatment strategy; usability

Abstract This Lab to Marketplace project describes the development of HyperAxon™, highly innovative software for performing automated segmentation, tracing, reconstruction and quantitative analysis of all axonal fibers visible in three-dimensional (3D) microscopic images of central nervous system (CNS) areas, even those with extremely high axonal fiber density. Accurate and rigorous analysis of all axonal fibers visible in 3D microscopic images of CNS tissue of non-transgenic and transgenic animal models as well as in human post mortem CNS tissue holds the promise of novel insights into physiological neural network connectivity patterns as well as into the neuropathological underpinnings of alterations in connectivity associated with human neuropsychiatric and neurological disorders. However, this cannot be achieved with contemporary, computer-assisted tracing and reconstruction methods, which currently are the gold standard for investigating axonal fibers, because these methods primarily address tracing and reconstruction of only a limited number of individual axonal fibers. HyperAxon will be based on the highly innovative artificial intelligence technology Learning-based Tracing of Dense Axonal Fibers (LTDAF) that was recently developed at MIT Lincoln Laboratory (MIT LL) (Lexington, MA). This project will build upon the original, lab-built LTDAF technology to create commercial software for wide- spread dissemination of this important new technology. Dissemination of this technology via a Lab to Marketplace commercial product is consistent with NIMH goals and will result in the technology having a significant impact on neuroscience research. The game-changing innovation in HyperAxon is the ability to automatically (i) segment, trace and reconstruct all axonal fibers visible in 3D microscopic images of CNS areas with high axonal fiber density, (ii) identify axonal branch points, (iii) resolve axonal fibers of passage from axonal fibers that make presumptive synapses in target regions, (iv) identify axonal fibers showing acute axonal injury and (v) precisely quantify alterations in number and density of axonal fibers in CNS tissue. Based on published pilot work performed at MIT LL, we are convinced that HyperAxon will be impactful in the field of neuroscience research and will enable substantial advancements in research on alterations in CNS circuitry associated with neurodevelopmental, neuropsychiatric, neurodegenerative and neurological disorders. Ultimately, this will result in an improved basis for developing novel treatment strategies for a wide spectrum of complex brain diseases. In Phase I we will demonstrate feasibility of this novel technology by developing prototype software; work in Phase II will focus on creating the full functionality of HyperAxon for commercial release. We will perform extensive feasibility studies, product validation and usability studies of HyperAxon in close collaboration with MIT LL and our academic collaboration partners. A competing technology is not available.

抽象的 该实验室到市场项目描述了 HyperAxon™ 的开发，这是一种高度创新的软件，用于 对所有可见轴突纤维进行自动分割、追踪、重建和定量分析 中枢神经系统 (CNS) 区域的三维 (3D) 显微图像，即使是那些极其严重的区域 高轴突纤维密度。对 3D 显微图像中可见的所有轴突纤维进行准确而严格的分析。 非转基因和转基因动物模型以及人类死后 CNS 组织中的 CNS 组织 有望对生理神经网络连接模式以及对 与人类神经精神相关的连通性改变的神经病理学基础 然而，现代计算机辅助追踪和治疗无法实现这一目标。 重建方法，目前是研究轴突纤维的黄金标准，因为这些 方法主要解决仅有限数量的单个轴突纤维的追踪和重建。 HyperAxon将基于高度创新的人工智能技术Learning-based Tracing 致密轴突纤维 (LTDAF) 最近在麻省理工学院林肯实验室 (MIT LL)（马萨诸塞州列克星敦）开发。 该项目将建立在原始的、实验室构建的 LTDAF 技术的基础上，为广泛的应用创建商业软件。 通过实验室传播这项重要的新技术。 市场商业产品与 NIMH 的目标一致，并将导致该技术具有 HyperAxon 的颠覆性创新在于能够对神经科学研究产生重大影响。 自动 (i) 分割、追踪和重建中枢神经系统区域 3D 显微图像中可见的所有轴突纤维 具有高轴突纤维密度，（ii）识别轴突分支点，（iii）解析来自轴突的通道的轴突纤维 在目标区域中形成推定突触的纤维，(iv) 识别显示急性轴突损伤的轴突纤维 (v) 根据已发表的文献精确量化中枢神经系统组织中轴突纤维数量和密度的变化。 在 MIT LL 进行的试点工作中，我们相信 HyperAxon 将在神经科学领域产生影响 研究并将使中枢神经系统电路改变的研究取得实质性进展 最终，这将导致神经发育、神经精神、神经退行性和神经系统疾病。 为开发针对广泛的复杂脑部疾病的新治疗策略奠定了更好的基础。 在第一阶段，我们将通过开发原型软件来证明这项新技术的可行性； 第二阶段将专注于创建 HyperAxon 的完整功能以进行商业发布。 与麻省理工学院密切合作对 HyperAxon 进行广泛的可行性研究、产品验证和可用性研究 LL 和我们的学术合作伙伴没有可用的竞争技术。