Prediction of Kidney Function from Biopsy Images Using Convolutional Neural Networks

2017/02/06 by Ledbetter, David, Ho, Long, Lemley, Kevin V
#FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (stat.ML) #Quantitative Methods (q-bio.QM)

paper · doi:10.48550/arxiv.1702.01816

Abstract

A Convolutional Neural Network was used to predict kidney function in patients with chronic kidney disease from high-resolution digital pathology scans of their kidney biopsies. Kidney biopsies were taken from participants of the NEPTUNE study, a longitudinal cohort study whose goal is to set up infrastructure for observing the evolution of 3 forms of idiopathic nephrotic syndrome, including developing predictors for progression of kidney disease. The knowledge of future kidney function is desirable as it can identify high-risk patients and influence treatment decisions, reducing the likelihood of irreversible kidney decline.

Related

• A comment on the paper Prediction of Kidney Function from Biopsy Images using Convolutional Neural Networks
• Genomics of kidney volumes: one size does not fit all
• A Clinically Interpretable Deep CNN Framework for Early Chronic Kidney Disease Prediction Using Grad-CAM-Based Explainable AI
• Kidney segmentation in neck-to-knee body MRI of 40,000 UK Biobank participants
• Prediction of Chronic Kidney Disease Using Deep Neural Network