Machine Intelligence Laboratory, College of Computer Science, Sichuan University, No. 24 South Section 1, Yihuan Road, Chengdu, 610065, China.
Laboratory of Clinical Nuclear Medicine, Department of Nuclear Medicine, West China Hospital of Sichuan University, No.37 Guo Xue Alley, Chengdu, 610041, China.
Eur Radiol. 2023 Jan;33(1):34-42. doi: 10.1007/s00330-022-08970-6. Epub 2022 Jul 7.
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.
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.
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.
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.
• 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.
开发和评估一种人工智能（AI）系统，该系统可以从动态肾脏成像中自动计算肾小球滤过率（GFR），而无需手动描绘肾脏的感兴趣区域（ROI）及其相应的背景。
本研究是对 14634 例接受 Tc-DTPA 动态肾脏成像的患者数据进行的单中心回顾性分析。开发并评估了两个基于卷积神经网络（CNN）的系统：sGFR 预测 ROI 的放射性计数，并使用 Gates 方程计算 GFR；sGFR 直接从动态肾脏成像预测 GFR，而不使用其他信息。使用均方根误差（RMSE）、平均绝对误差（MAE）、平均绝对百分比误差（MAPE）和 R 来评估我们方法的性能。
sGFR 对总 GFR 的 RMSE 为 5.05、MAE 为 4.03、MAPE 为 6.07%和 R 为 0.93，而 sGFR 对总 GFR 的 RMSE 为 7.61、MAE 为 5.92、MAPE 为 8.92%和 R 为 0.85。sGFR 和 sGFR 确定慢性肾脏病分期的准确性分别为 87.41%和 82.44%。
sGFR 的结果表明，基于 CNN 的自动 GFR 计算和使用动态肾脏成像既可行又高效，此外，还可以辅助临床诊断。此外，sGFR 的有前景的结果表明，CNN 可以在没有其他与 Gates 方程相关的参数的情况下，从动态肾脏成像预测 GFR。
• 我们基于 CNN 的 AI 系统可以从动态肾脏成像中自动计算 GFR，而无需手动描绘肾脏的 ROI 和相应的背景。• sGFR 准确预测了 ROI 的放射性计数，并使用 Gates 方法计算 GFR。• sGFR 无需任何与 Gates 方程相关的参数即可直接预测 GFR。
