Computational Imaging of Renal Structures for Diagnosing Diabetic Nephropathy

用于诊断糖尿病肾病的肾脏结构计算成像

• 批准号: 10208865
• 负责人: Pinaki Sarder
• 金额: $ 29.69万
• 依托单位: STATE UNIVERSITY OF NEW YORK AT BUFFALO
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-15 至 2022-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10208865
• 关键词: Accounting; Adult; Albumins; Albuminuria; Architecture; Biological Markers; Biometry; Biopsy; Characteristics; Classification; Classification Scheme; Clinical; Clinical Data; Communities; Computer Models; Computing Methodologies; Consumption; Cost Savings; Creatinine; Data; Detection; Development; Diabetes Mellitus; Diabetic Nephropathy; Diagnosis; Diagnostic Procedure; Disease; Disease Progression; Early Intervention; Elements; End stage renal failure; Eye; Feedback; Functional disorder; Future; Glomerular Filtration Rate; Glucose; Goals; Hand; Histologic; Histopathology; Human; Image; Image Analysis; Intervention; Kidney; Kidney Diseases; Kidney Failure; Lead; Manuals; Measurable; Measurement; Measures; Medicare; Methods; Microalbuminuria; Microscopic; Modeling; Morphology; Mus; Neural Network Simulation; Outcome; Pathologic; Pathologist; Patients; Performance; Physiological; Precision therapeutics; Proteins; Refractory; Renal Tissue; Research; Resources; Risk; Risk Estimate; Secondary to; Serum; Severities; Staging; Stains; Standardization; Streptozocin; Structural Models; Structure; Therapeutic Intervention; Thinness; Time; Tissue imaging; Tissues; Training; Urine; Variant; Visual; Work; autoencoder; base; clinical biomarkers; clinically relevant; computer studies; computerized tools; convolutional neural network; cost; detection method; diabetic; digital; follow-up; histological image; human data; human imaging; improved; information model; innovation; kidney biopsy; mouse model; network models; novel; personalized diagnostics; predictive marker; prognostic; protein biomarkers; response; statistics; tool; urinary

Project Summary At the current rate, one in three U.S. adults will be diabetic by 2050. A disease secondary to diabetes is diabetic nephropathy (DN), which causes end-stage renal disease (ESRD) for >225K U.S. patients (50% of all ESRD cases), accounting for >$19K in yearly Medicare costs for each patient. Measurement of minute urinary albumin (microalbuminuria) is the most common non-invasive clinical biomarker of DN. In order to conclusively define DN severity, pathologists conduct qualitative manual estimation of glomerular structural damage in renal biopsies. However, renal glomerular structure in DN biopsies does not often correlate with less invasive clinical biometrics (e.g., estimated glomerular filtration rate, urine protein, serum creatinine and glucose levels). This traditional diagnostic method is approximate, subjected to user bias, time-consuming, and has low diagnostic precision in early disease stages; further, manual hand identified features may not always accurately predict disease progression. Computational image analysis offers the opportunity to project clinical biometrics onto glomerular histological structures. This method provides finer precision in identifying structural changes that lead to physiological changes, which in turn reduces the required clinical resources and time for diagnosis, and provides clinicians with greater feedback to improve early intervention. We have developed computational tools to quantify renal structures in human DN biopsies. Our tools quantify glomerular features in histological renal tissue images more efficiently than manual methods. We have also derived a quantitative progression risk score (PRS) describing DN progression risk estimated off only a single biopsy point. Here, we will rigorously analyze the performance of these methods to predict disease progression using histological images of human DN renal biopsies. We will computationally quantify morphologically diverse DN-indicative intra-glomerular features. We will analytically integrate computationally derived glomerular features with clinical biometrics in order to develop patient-specific PRS to identify patients at risk of renal failure. Since human renal DN data is sparse, we will also use murine data, which can be generated in large amounts in a controlled fashion, to initially train the computational models. We will then refine the model for clinical use by fine-tuning the parameters using human data. The innovation is in the novel integration of traditional clinical detection methods with traditional diagnostic methods, under a computational schema for enhanced precision. This integration will lead to computational disease predicting biomarkers of the earliest measurable renal DN dysfunction. We will study the predictive power of these markers to foretell future clinical endpoints from earlier time points. These methods support the development of quantifiable prognostic and predictive information, which is dynamic over the disease course, easily discriminated, and is highly informative for modeling disease progression or response to therapy. This study will 1) enable earlier clinical predictions, thus extending windows for interventions of evolving DN; and 2) work as a pilot platform for future studies to computationally derive renal biomarkers predictive of other diseases.

项目概要 按照目前的速度，到 2050 年，三分之一的美国成年人将患有糖尿病。继发于糖尿病的一种疾病是糖尿病 肾病 (DN)，导致超过 225,000 名美国患者终末期肾病 (ESRD)（占所有 ESRD 的 50%） 例），每位患者每年的医疗保险费用超过 19,000 美元。微量尿白蛋白测定 （微量白蛋白尿）是 DN 最常见的非侵入性临床生物标志物。为了最终定义 DN 严重程度，病理学家对肾小球结构损伤进行定性手动评估 活检。然而，DN 活检中的肾小球结构通常与微创临床并不相关。 生物测定（例如估计肾小球滤过率、尿蛋白、血清肌酐和血糖水平）。这 传统的诊断方法是近似的，容易受到用户偏差的影响，耗时长，诊断率低 疾病早期阶段的精确性；此外，手动识别的特征可能并不总是准确预测 疾病进展。计算图像分析提供了将临床生物特征投射到 肾小球组织学结构。该方法可以更精确地识别结构变化，从而导致 生理变化，从而减少诊断所需的临床资源和时间，以及 为临床医生提供更多反馈以改善早期干预。我们开发了计算工具 量化人类 DN 活检中的肾脏结构。我们的工具量化肾脏组织学中的肾小球特征 组织图像比手动方法更有效。我们还得出了定量进展风险评分 (PRS) 描述仅根据单个活检点估计的 DN 进展风险。下面我们就来认真分析一下 这些方法使用人类 DN 肾组织学图像预测疾病进展的性能 活检。我们将通过计算量化形态多样的 DN 指示性肾小球内特征。我们 将分析性地将计算得出的肾小球特征与临床生物识别相结合，以开发 患者特异性 PRS 来识别有肾衰竭风险的患者。由于人类肾脏 DN 数据稀疏，我们还将 使用可以以受控方式大量生成的小鼠数据来初步训练 计算模型。然后，我们将通过使用人类微调参数来完善临床使用的模型 数据。创新在于传统临床检测方法与传统诊断的新颖整合 方法，在计算模式下提高精度。这种整合将导致计算 最早可测量的肾 DN 功能障碍的疾病预测生物标志物。我们将研究预测 这些标记物从早期时间点预测未来临床终点的能力。这些方法支持 开发可量化的预后和预测信息，这些信息在疾病过程中是动态的， 很容易区分，并且对于疾病进展或治疗反应建模具有丰富的信息。这 研究将 1) 实现早期临床预测，从而延长对不断发展的 DN 进行干预的窗口；和 2) 作为未来研究的试点平台，通过计算得出预测其他疾病的肾脏生物标志物。