Abstract
To quantitatively evaluate chronic kidney disease (CKD), a deep convolutional neural network-based segmentation model was applied to renal enhanced computed tomography (CT) images. A retrospective analysis was conducted on a cohort of 100 individuals diagnosed with CKD and 90 individuals with healthy kidneys, who underwent contrast-enhanced CT scans of the kidneys or abdomen. Demographic and clinical data were collected from all participants. The study consisted of two distinct stages: firstly, the development and validation of a three-dimensional (3D) nnU-Net model for segmenting the arterial phase of renal enhanced CT scans; secondly, the utilization of the 3D nnU-Net model for quantitative evaluation of CKD. The 3D nnU-Net model achieved a mean Dice Similarity Coefficient (DSC) of 93.53% for renal parenchyma and 81.48% for renal cortex. Statistically significant differences were observed among different stages of renal function for renal parenchyma volume (V(RP)), renal cortex volume (V(RC)), renal medulla volume (V(RM)), the CT values of renal parenchyma (Hu(RP)), the CT values of renal cortex (Hu(RC)), and the CT values of renal medulla (Hu(RM)) (F = 93.476, 144.918, 9.637, 170.533, 216.616, and 94.283; p < 0.001). Pearson correlation analysis revealed significant positive associations between glomerular filtration rate (eGFR) and V(RP), V(RC), V(RM), Hu(RP), Hu(RC), and Hu(RM) (r = 0.749, 0.818, 0.321, 0.819, 0.820, and 0.747, respectively, all p < 0.001). Similarly, a negative correlation was observed between serum creatinine (Scr) levels and V(RP), V(RC), V(RM), Hu(RP), Hu(RC), and Hu(RM) (r = - 0.759, - 0.777, - 0.420, - 0.762, - 0.771, and - 0.726, respectively, all p < 0.001). For predicting CKD in males, V(RP) had an area under the curve (AUC) of 0.726, p < 0.001; V(RC), AUC 0.765, p < 0.001; V(RM), AUC 0.578, p = 0.018; Hu(RP), AUC 0.912, p < 0.001; Hu(RC), AUC 0.952, p < 0.001; and Hu(RM), AUC 0.772, p < 0.001 in males. In females, V(RP) had an AUC of 0.813, p < 0.001; V(RC), AUC 0.851, p < 0.001; V(RM), AUC 0.623, p = 0.060; Hu(RP), AUC 0.904, p < 0.001; Hu(RC), AUC 0.934, p < 0.001; and Hu(RM), AUC 0.840, p < 0.001. The optimal cutoff values for predicting CKD in Hu(RP) are 99.9 Hu for males and 98.4 Hu for females, while in Hu(RC) are 120.1 Hu for males and 111.8 Hu for females. The kidney was effectively segmented by our AI-based 3D nnU-Net model for enhanced renal CT images. In terms of mild kidney injury, the CT values exhibited higher sensitivity compared to kidney volume. The correlation analysis revealed a stronger association between V(RC), Hu(RP), and Hu(RC) with renal function, while the association between V(RP) and Hu(RM) was weaker, and the association between V(RM) was the weakest. Particularly, Hu(RP) and Hu(RC) demonstrated significant potential in predicting renal function. For diagnosing CKD, it is recommended to set the threshold values as follows: Hu(RP) < 99.9 Hu and Hu(RC) < 120.1 Hu in males, and Hu(RP) < 98.4 Hu and Hu(RC) < 111.8 Hu in females.