Deep learning and topological approaches to identify kidney tissue features associated with adverse outcomes after nephrectomy

深度学习和拓扑方法识别与肾切除术后不良后果相关的肾组织特征

• 批准号: 10229784
• 负责人: Markus Bitzer
• 金额: $ 23.4万
• 依托单位: UNIVERSITY OF MICHIGAN AT ANN ARBOR
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2023-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10229784
• 关键词: Acute; Albuminuria; Algorithms; Arteries; Atrophic; Blood Vessels; Categories; Chronic Kidney Failure; Classification; Clinical; Clinical Data; Collection; Computer Assisted; Consent; Consumption; Contralateral; Creatinine; Data; Data Analyses; Detection; Diabetes Mellitus; Diabetic Nephropathy; Disease; Distant; Elderly; Etiology; Evaluation; Excision; Fibrosis; Functional disorder; Future; Glomerulonephritis; Heterogeneity; Human; Hypertension; Image; Image Analysis; Individual; Kidney; Kidney Diseases; Kidney Failure; Malignant Neoplasms; Manuals; Masks; Measures; Methods; Modernization; Needle biopsy procedure; Needles; Nephrectomy; Nephrotic Syndrome; Neural Network Simulation; Obesity; Operative Surgical Procedures; Organ; Outcome; Pathologic; Pathology; Patients; Phenotype; Population; Renal function; Reproducibility; Research; Risk; Risk Factors; Sampling; Scanning; Serum; Spatial Distribution; Structure; Techniques; Testing; Time; Tissue imaging; Tissues; Training; Tubular formation; Visual; adverse outcome; base; clinically relevant; cohort; convolutional neural network; cost effective; deep learning; experience; glomerulosclerosis; histological stains; improved; insight; interstitial; kidney biopsy; kidney imaging; morphometry; novel; outcome prediction; prevent; prospective; renal damage; serial imaging; spatial relationship; tumor; user-friendly

ABSTRACT Pathologic assessment of kidney biopsy tissue remains the best predictor of adverse outcomes in patients with kidney diseases. These features are largely independent of disease etiology and are not well reflected in non- invasive tests (e.g. serum creatinine and albuminuria). Quantitative assessment of these parameters is time consuming and maybe flawed by heterogeneity of pathologic features within kidney tissue. We propose to evaluate and optimize computational image analysis approaches to support pathologic analysis of large pieces of cancer-free kidney tissue from patients who underwent nephrectomy which we have collected (n > 220). Computer-assisted analysis of glomerular phenotypes in these samples show that morphometric features in glomeruli without obvious pathology precede established pathologic changes. We hypothesize that evaluation of cancer-free kidney tissue will inform about subclinical damage in the remaining kidney which is associated with relevant pathologic and clinical parameters. We propose to assess glomeruli, arteries and tubuli, and determine the spatial inter-relationship of the assessed features within the kidney tissue. The examination of significantly larger pieces of kidney tissue than those obtained by needle biopsy allows to include 20 times more glomeruli (nephrectomy samples: avrg. 256 glomeruli/sample; needle biopsy: avrg. 13/sample) with the vast majority considered “normal appearing” as per standard pathologic criteria. In addition, these samples include a significant larger number of blood vessels (nephrectomy samples: avrg. 18 arteries/sample; needle biopsy: avrg. 1/sample) allowing a more robust evaluation of the vasculature. We propose to apply and optimize our detection and segmentation approach to detect glomeruli, arteries and tubular segments to train convolutional neural networks and use topological image analysis to automate the identification of visual and sub-visual features. In addition, we will assess the spatial relationship between individual features (glomeruli, arteries and tubular segments and features of the same category, i.e. globally sclerosed glomeruli, arteries with hyalinosis, atrophied tubuli) within the section. To determine reproducibility of our approach, we will assess a second tissue section from a separate part of the same samples. Specifically, we propose an algorithmic detection and characterization of kidney features using deep learning, a topological image analysis for discovery of novel sub-visual features in kidney tissue images and to determine spatial relatedness of these features. If successful, we will validate our analytical approach in future independent studies. For this purpose, we are already prospectively collecting kidney tissue and longitudinal clinical data from consented patients undergoing nephrectomies, allowing association of specific features with clinical relevant outcomes.

抽象的 肾脏活检组织的病理评估仍然是患者患者不良预后的最佳预测指标 肾脏疾病。这些特征在很大程度上与疾病的病因无关，并且在非 - 侵入性测试（例如血清肌酐和蛋白尿）。这些参数的定量评估是时间 肾脏组织中病理特征的异质性消耗，也许有缺陷。我们建议 评估和优化计算图像分析方法以支持大块的病理分析 来自我们已收集的肾切除术的患者的无癌肾组织（n> 220）。 这些样品中肾小球表型的计算机辅助分析表明，形态特征 没有明显病理的肾小球先于已建立的病理变化。我们假设该评估 无癌的肾脏组织将告知其余肾脏的亚临床损伤，这与 具有相关的病理和临床参数。我们建议评估肾小球，动脉和小节，以及 确定肾脏组织中评估特征的空间相互关系。 比针活检获得的肾脏组织的显着更大的肾脏组织允许 包括20倍的肾小球（肾切除术样品：AVRG。256glomerulli/样品；针头活检：AVRG。 根据标准病理标准，绝大多数被视为“正常外观”的13/样品）。在 成瘾，这些样本包括大量的血管（肾切除术样本：AVRG。18 动脉/样品；针头活检：AVRG。 1/样品）允许对脉管系统进行更强大的评估。我们 提议应用和优化我们的检测和分割方法检测肾小球，动脉和 结节段训练卷积神经网络并使用拓扑图像分析来自动化 识别视觉和次视感特征。此外，我们将评估 单个特征（肾小球，动脉和管状段以及同一类别的特征，即全球 在该部分内有巩膜的肾小球，透明膜病的动脉，萎缩性的tubuli）。确定可重复性 我们的方法，我们将从同一样品的单独部分评估第二个组织部分。具体来说， 我们提出了使用深度学习（拓扑结构）对肾脏特征的算法检测和表征 图像分析，用于发现肾脏组织图像中新型亚视觉特征的发现并确定空间 这些功能的相关性。 如果成功，我们将在未来的独立研究中验证我们的分析方法。为此，我们是 已经前瞻性地收集了接受同意患者的肾脏组织和纵向临床数据 肾切除术，允许将特定特征与临床相关结果相关联。