Deep regression using Tc-DTPA dynamic renal imaging for automatic calculation of the glomerular filtration rate.

Objectives: To develop and evaluate an artificial intelligence (AI) system that can automatically calculate the glomerular filtration rate (GFR) from dynamic renal imaging without manually delineating the regions of interest (ROIs) of kidneys and the corresponding background.

Methods: This study was a single-center retrospective analysis of the data of 14,634 patients who underwent Tc-DTPA dynamic renal imaging. Two systems based on convolutional neural networks (CNN) were developed and evaluated: sGFR predicts the radioactive counts of ROIs and calculates GFR using the Gates equation and sGFR directly predicts GFR from dynamic renal imaging without using other information. The root-mean-square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and R were used to evaluate the performance of our approach.

Results: sGFR achieved an RMSE of 5.05, MAE of 4.03, MAPE of 6.07%, and R of 0.93 for total GFR while sGFR achieved an RMSE of 7.61, MAE of 5.92, MAPE of 8.92%, and R of 0.85 for total GFR. The accuracy of sGFR and sGFR in determining the stage of chronic kidney disease was 87.41% and 82.44%, respectively.

Conclusions: The findings of sGFR show that automatic GFR calculation based on CNN and using dynamic renal imaging is feasible and efficient and, additionally, can aid clinical diagnosis. Furthermore, the promising results of sGFR demonstrate that CNN can predict GFR from dynamic renal imaging without additional information.

Key Points: • Our CNN-based AI systems can automatically calculate GFR from dynamic renal imaging without manually delineating the ROIs of kidneys and the corresponding background. • sGFR accurately predicted the radioactive counts of ROIs and calculated GFR using the Gates method. • sGFR-predicted GFR directly without any parameters related to the Gates equation.