Cell and Network Disruptions and Associated Pathogenenesis in Tauopathy and Down Syndrome

Tau 蛋白病和唐氏综合症的细胞和网络破坏及相关发病机制

• 批准号: 10599756
• 负责人: STEVEN M FINKBEINER
• 金额: $ 37.8万
• 依托单位: J. DAVID GLADSTONE INSTITUTES
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-15 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10599756
• 关键词: 3-Dimensional; Acute; Affect; Alzheimer' s Disease; Alzheimer' s disease model; Animal Model; Animals; Artificial Intelligence; Biological Markers; Biology; Biosensor; Brain; Cell Death; Cells; Cellular Morphology; Cessation of life; Communities; Computer Vision Systems; Data; Data Analyses; Data Set; Development; Down Syndrome; Ethical Analysis; Ethics; Frontotemporal Dementia; Funding; Grant; Human; Image; Image Analysis; Imaging technology; Individual; Induced pluripotent stem cell derived neurons; Label; Learning; Link; Machine Learning; Mathematics; Microscopy; Modeling; Monitor; Morphology; Nerve Degeneration; Neurodegenerative Disorders; Neurons; Nuclear; Organoids; Outcome; Outcome Study; Parents; Pathogenesis; Patients; Population Heterogeneity; Process; Property; Proteins; Reporting; Research; Research Personnel; Resistance; Signal Transduction; Standardization; Structure; Supervision; Tauopathies; Technology; Time; Training; United States National Institutes of Health; Visual; Zebrafish; algorithm training; base; cell type; convolutional neural network; deep learning algorithm; deep neural network; experimental study; human imaging; human model; imaging modality; imaging study; improved; in vivo; innovation; microscopic imaging; neural network; neural network algorithm; neuron loss; novel; novel strategies; robotic microscopy; serial imaging; tau Proteins; tool; unethical

PROJECT SUMMARY Our studies will develop and implement novel artificial intelligence (AI)/ machine learning (ML) technologies to reduce experimental unethical bias in analysis of imaging data of our studies in our parent, NIH-funded grant (AG064579-02) that focuses on identifying mechanisms of neurodegeneration in Alzheimer’s disease and Frontotemporal dementia. We study neurodegeneration in human iPSC-derived neurons (i-neurons) of controls and patients with tauopathies in 3-dimensional (3D) human brain organoids and use robotic microscopy (RM) to monitor changes in morphology and structure of individual i-neurons in large populations of heterogeneous cells over time as an indicator of neurodegeneration. Since the initiation of this grant, we have developed novel approaches to study mechanisms of neurodegeneration with a unique biosensor (Genetically encoded cell death indicator – GEDI) that acutely identifies living neurons at a stage at which they are irreversibly committed to die. Initially, imaging data from these studies involved human curation, which carries some degree of experimental bias that can cause ethical problems in interpretation of data. To reduce experimental bias of our data analysis, we have developed ML and deep neural networks (DNN) and use a subclass of DNN, convolutional neural networks (CNNs) which have mathematical properties particularly adept at Computer Vision. We have developed deep learning (DL) algorithms for detecting neuronal death by constructing a novel quantitative RM pipeline that automatically generates GEDI-curated data to train a CNN without human input. The resulting GEDI-CNN detects neuronal death from images of morphology alone, alleviating the need for any additional use of GEDI in subsequent experiments. Through systematic analysis of a trained GEDI-CNN, we find that it learns to detect death in neurons by locating morphology linked to death, despite receiving no explicit supervision toward these features. Uniquely, it detects cell death as a change in nuclear readouts as well as other cellular features, which human curation can’t easily identify. We also show that this model generalizes to images captured with different parameters or displays of neurons and cell types from different species without additional training. The advances we made in unbiased AI image analysis are not restricted to our benefit but will be applicable to a large range of ML based imaging studies of other investigators because it focuses on improving how the CNN algorithms are trained to analyze data without the need of humans but with super-human accuracy. In this supplemental application, we will further develop this novel ethical AI technology for studies on neurodegeneration of human i-neurons in 3D brain organoids using GEDI-CNN. We will refine the CNN algorithms to optimize and standardize its widespread use in ethical analysis of live imaging analysis and provide the technology to the scientific community for AI-based imaging research.

项目概要 我们的研究将开发和实施新型人工智能（AI）/机器学习（ML）技术 减少我们在 NIH 资助的母公司研究的成像数据分析中的实验不道德偏差 （AG064579-02）专注于识别阿尔茨海默病和神经退行性疾病的机制 额颞叶痴呆。我们研究对照的人类 iPSC 衍生神经元（i-神经元）的神经退行性变 以及 3 维 (3D) 人脑类器官中患有 tau蛋白病的患者，并使用机器人显微镜 (RM) 来 监测大量异质细胞中单个 i 神经元的形态和结构变化 随着时间的推移，作为神经退行性变的指标。自这项资助启动以来，我们开发了新颖的 使用独特的生物传感器（基因编码的细胞死亡）研究神经退行性变机制的方法 指示器（GEDI），可以敏锐地识别处于不可逆转的死亡阶段的活神经元。 最初，这些研究的成像数据涉及人类管理，这带有一定程度的实验性 可能导致数据解释道德问题的偏见。为了减少我们数据分析的实验偏差， 我们开发了 ML 和深度神经网络 (DNN)，并使用 DNN 的子类——卷积神经网络 网络（CNN）具有特别擅长计算机视觉的数学特性。我们开发了 深度学习 (DL) 算法通过构建新颖的定量 RM 管道来检测神经元死亡 自动生成 GEDI 整理的数据来训练 CNN，无需人工输入。由此产生的 GEDI-CNN 仅从形态学图像中即可检测神经元死亡，从而减少了在检测中额外使用 GEDI 的需要 后续实验。通过对经过训练的 GEDI-CNN 进行系统分析，我们发现它学会了检测 通过定位与死亡相关的形态来识别神经元的死亡，尽管没有接受对这些死亡的明确监督 特征。独特的是，它通过核读数以及其他细胞特征的变化来检测细胞死亡，这 人类的管理无法轻易识别。我们还表明，该模型可推广到使用不同方式捕获的图像 无需额外训练即可显示来自不同物种的神经元和细胞类型的参数或显示。进展情况 我们在公正的人工智能图像分析中所做的并不局限于我们的利益，而是适用于大范围的 其他研究人员基于 ML 的成像研究，因为它专注于改进 CNN 算法 经过训练，可以在不需要人类的情况下分析数据，但具有超人类的准确性。在这个补充 应用程序，我们将进一步开发这种新颖的伦理人工智能技术，用于人类神经退行性疾病的研究 使用 GEDI-CNN 观察 3D 大脑类器官中的 i 神经元。我们将对CNN算法进行细化优化和标准化 它广泛应用于实时成像分析的伦理分析，并为科学界提供技术 基于人工智能的成像研究社区。