Convolution Neural Network for Renal Function Assessment Based on Glomerular Filtration Rate

Absract ✓ Objective : To develop a Convolution Neural Network (CNN) and discuss its performance in the estimation of Glomerular Fifiltration Rate (GFR) for patients with chronic kidney disease (CKD). Methods A total 112 were enrolled this study. The GFR is measured by 99mTc-DTPA renal dynamic used as standard after normalization body surface area imaging. We established CNN model verified comparing predicted GFR. It turned out that could better evaluate which superior to CG formula, MDRD CKD-EPI formula GRNN model. Conclusions significantly evaluated CKD, it showed than traditional methods closer results 99mTc-DTPA. experimental demonstrated be estimate