Lupus Nephritis Neural Network, LuNN

狼疮性肾炎神经网络，LuNN

• 批准号: 10246669
• 负责人: CHANDRA MOHAN
• 金额: $ 10.08万
• 依托单位: UNIVERSITY OF HOUSTON
• 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 2021-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10246669
• 关键词: Adult; Algorithms; Automobile Driving; Cellular Structures; Child; Chronic; Classification; Computer Vision Systems; Diagnosis; Diagnostic; End stage renal failure; Feedback; Gold; Histologic; Human; Image; Kidney; Lupus; Lupus Nephritis; Machine Learning; Mus; Nephritis; Outcome; Outcome Study; Pathologist; Pathology; Patients; Performance; Phenotype; Prediction of Response to Therapy; Reading; Reporting; Reproducibility; Retrieval; Supervision; Systemic Lupus Erythematosus; Testing; Tissues; Training; Uncertainty; accurate diagnosis; base; convolutional neural network; deep learning; diagnosis standard; falls; improved; indexing; innovation; kidney biopsy; neural network; novel; predict clinical outcome; time interval; tool; treatment response; user-friendly; web portal

Up to 60% of adults and 80% of children with systemic lupus erythematosus (SLE) develop nephritis (LN), with 10–30% progressing to end-stage renal disease (ESRD). The gold standard for diagnosis of LN is a renal biopsy. Histological parameters remain the best predictors of ESRD. Despite being the gold standard, histological diagnosis of LN has several shortcomings. In multiple inter-observer renal pathology assessment studies reported thus far, the inter- pathologist correlation coefficients, or concordance, in assessing most histological parameters have been sub-optimal. This has provided the impetus for the current proposal. We propose to leverage the power of computer vision and deep learning to build a classifier that rivals the best-trained renal pathologists in making a histological diagnosis of LN using current diagnostic criteria. We propose to train a deep convolutional neural network to distinguish the different LN classes, and to identify a full spectrum of histological attributes useful for diagnosis. We will compare the performance of the newly generated neural network in scoring glomerular/tubulo-interstitial features and LN classes, against a panel of human renal pathologists. Finally, we propose to build a neural network that can predict clinical outcome based on baseline renal pathology. Reliable and reproducible classification of LN could dramatically improve patient management and long-term renal and patient survival.

高达 60% 的成人和 80% 的儿童患有系统性红斑狼疮 (SLE) 肾炎 (LN)，其中 10-30% 进展为终末期肾病 (ESRD)。 肾活检是诊断 LN 的最佳预测指标。 尽管 ESRD 是金标准，但 LN 的组织学诊断仍存在一些缺点。 在迄今为止报道的多项观察者间肾脏病理学评估研究中， 病理学家在评估大多数组织学参数时的相关系数或一致性 这为当前提案提供了动力。 我们建议利用计算机视觉和深度学习的力量来构建一个分类器 在使用电流对 LN 进行组织学诊断方面，可与训练有素的肾脏病理学家相媲美 我们建议训练一个深度卷积神经网络来区分 不同的 LN 类别，并识别对诊断有用的全谱组织学属性。 我们将比较新生成的神经网络在评分方面的表现 肾小球/肾小管间质特征和 LN 类别，针对一组人肾 最后，我们建议建立一个可以预测临床结果的神经网络。 基于基线肾脏病理学可以对 LN 进行可靠且可重复的分类。 显着改善患者管理以及肾脏和患者的长期生存。