Quantifying the individual contributions of comorbid tau neuropathologies using deep learning

使用深度学习量化共病 tau 神经病理学的个体贡献

• 批准号: 10058010
• 负责人: Satwik Rajaram
• 金额: $ 45.03万
• 依托单位: UT SOUTHWESTERN MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-15 至 2023-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10058010
• 关键词: Adoption; Affect; Age; Aging; Alzheimer' s Disease; Antibodies; Astrocytes; Atlases; Autopsy; Biological; Brain; Cells; Cerebral cortex; Characteristics; Classification; Clinical; Complex; Data; Dementia; Deposition; Development; Diagnosis; Diagnostic; Disease; Elements; Exhibits; Future; Genetic; Gold; Heterogeneity; Histopathology; Human; Image; Individual; Investigation; Knowledge; Lesion; Libraries; Light; Machine Learning; Malignant Neoplasms; Methods; Microscopic; Monoclonal Antibodies; Morphology; Nerve Degeneration; Neurodegenerative Disorders; Neurons; Pathologic; Pathologist; Pathology; Pattern; Phenotype; Progressive Supranuclear Palsy; Protein Isoforms; Research; Resources; Sampling; Senile Plaques; Spatial Distribution; Stains; Tauopathies; Technology; Testing; Tissue Stains; Tissues; Visual; Visualization; base; case-based; cell type; clinical biomarkers; comorbidity; deep learning; digital imaging; gray matter; hands-on learning; improved; learning classifier; learning strategy; method development; neocortical; neuropathology; protein aggregation; specific biomarkers; tau Proteins; tau-1; tool; tumor; virtual; virtual imaging; white matter; whole slide imaging

PROJECT SUMMARY/ABSTRACT Co-occurrence of different neurodegenerative diseases is increasingly common with age and acts as a confounding factor in the development of disease-specific biomarkers. Yet, even by the gold standard of evaluating immunostaining for aggregated proteins in autopsy brains, pathologic complexity makes it impossible to reliably quantify the mixture of diseases by visual inspection, especially when coexistent disorders both feature the same aggregated protein, albeit in different disease-specific patterns. Here, we hypothesize that recent advances in deep learning can identify the distinctive patterns of Alzheimer disease (AD) and progressive supranuclear palsy (PSP) neuropathology, thereby allowing us to de-convolve their individual contributions from phospho-tau immunostaining of mixed pathologies. We will tackle this problem in three steps. First, in order to incorporate biological knowledge and enable interpretability of our disease predictions, we will develop a set of deep learning classifiers to identify disease relevant “features” in virtual whole slide images. These features will include different types of cells (e.g. neurons, astrocytes), aggregates (e.g. tufted astrocytes and senile plaques that are enriched in PSP and AD, respectively) and tissue regions (gray vs. white matter, which differ in pattern of involvement in these diseases). Second, based on the assumption that comorbid pathologies exhibit a mixture of pure disease features, we will build disease classifiers from pure AD and pure PSP cases. Given a local patch of tau-stained tissue, these classifiers will return their confidence that tissue exhibited either of these diseases. We will evaluate two approaches, one building on the “features” identified above and the other a more traditional black- box deep learning approach working purely off of image patches. Finally, we will evaluate our pure disease classifiers on cases with mixed pathologies based on pathologist review and concordance with antibodies to tau isoforms whose individual histomorphologies help to distinguish between AD and PSP. As they will identify established neuropathology features demonstrated by the widely-used AT8 phospho-tau and 3R and 4R tau isoform immunostaining, our classifiers will be a valuable resource for future digital imaging based studies in neuropathology. Our framework for de-convolving comorbidities from autopsy samples can be extended to other diseases, thus enabling better integration with clinical and biomarker data, and ultimately, improved antemortem diagnosis and therapy.

项目概要/摘要 随着年龄的增长，不同神经退行性疾病同时发生的情况越来越普遍，这可以作为一种 然而，即使按照黄金标准，疾病特异性生物标志物的发展也是混杂因素。 评估尸检大脑中聚集蛋白的免疫染色，病理复杂性使其 不可能通过目视检查可靠地量化疾病的混合物，特别是当同时存在时 尽管疾病特异性模式不同，但这两种疾病都具有相同的聚集蛋白。 推进深度学习的最新进展可以识别阿尔茨海默病的独特模式 （AD）和进行性核上性麻痹（PSP）神经病理学，从而使我们能够去卷积他们的 混合病理的磷酸-tau 免疫染色的个体贡献。 我们将分三步解决这个问题，首先，整合生物学知识并使其成为可能。 为了提高疾病预测的可解释性，我们将开发一套深度学习分类器来识别疾病 虚拟整个幻灯片图像中的相关“特征”这些特征将包括不同类型的细胞（例如 神经元、星形胶质细胞）、聚集体（例如富含 PSP 和 AD 的簇状星形胶质细胞和老年斑， 分别）和组织区域（灰质与白质，它们参与这些的模式不同） 其次，基于共病病理表现出纯疾病的混合的假设。 特征，我们将从纯 AD 和纯 PSP 病例构建疾病分类器，给定局部 tau 染色斑块。 组织，这些分类器将返回他们的信心，即组织表现出这些疾病中的任何一种。 评估两种方法，一种基于上面确定的“特征”，另一种则采用更传统的黑- 框学习深度方法纯粹基于图像补丁工作最后，我们将评估我们的纯疾病。 基于病理学家审查和抗体一致性的混合病理病例分类器 tau 亚型，其各自的组织形态有助于区分 AD 和 PSP。 因为他们将识别广泛使用的 AT8 磷酸化 tau 所证明的既定神经病理学特征 以及 3R 和 4R tau 亚型免疫染色，我们的分类器将成为未来数字成像的宝贵资源 我们从尸检样本中去卷积合并症的框架可以是 扩展到其他疾病，从而能够更好地与临床和生物标志物数据整合，最终， 改进生前诊断和治疗。