Sustainable Technology and Wellness R&D Group, Korea Institute of Industrial Technology, Cheonan, Republic of Korea.
Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania.
J Am Soc Nephrol. 2022 Aug;33(8):1581-1589. doi: 10.1681/ASN.2021111400. Epub 2022 Jun 29.
Total kidney volume (TKV) is an important imaging biomarker in autosomal dominant polycystic kidney disease (ADPKD). Manual computation of TKV, particularly with the exclusion of exophytic cysts, is laborious and time consuming.
We developed a fully automated segmentation method for TKV using a deep learning network to selectively segment kidney regions while excluding exophytic cysts. We used abdominal -weighted magnetic resonance images from 210 individuals with ADPKD who were divided into two groups: one group of 157 to train the network and a second group of 53 to test it. With a 3D U-Net architecture using dataset fingerprints, the network was trained by -fold cross-validation, in that 80% of 157 cases were for training and the remaining 20% were for validation. We used Dice similarity coefficient, intraclass correlation coefficient, and Bland-Altman analysis to assess the performance of the automated segmentation method compared with the manual method.
The automated and manual reference methods exhibited excellent geometric concordance (Dice similarity coefficient: mean±SD, 0.962±0.018) on the test datasets, with kidney volumes ranging from 178.9 to 2776.0 ml (mean±SD, 1058.5±706.8 ml) and exophytic cysts ranging from 113.4 to 2497.6 ml (mean±SD, 549.0±559.1 ml). The intraclass correlation coefficient was 0.9994 (95% confidence interval, 0.9991 to 0.9996; <0.001) with a minimum bias of -2.424 ml (95% limits of agreement, -49.80 to 44.95).
We developed a fully automated segmentation method to measure TKV that excludes exophytic cysts and has an accuracy similar to that of a human expert. This technique may be useful in clinical studies that require automated computation of TKV to evaluate progression of ADPKD and response to treatment.
全肾体积（TKV）是常染色体显性多囊肾病（ADPKD）的重要影像学生物标志物。手动计算 TKV，特别是排除外生囊肿，既费力又耗时。
我们开发了一种使用深度学习网络选择性地分割肾脏区域同时排除外生囊肿的 TKV 全自动分割方法。我们使用来自 210 名 ADPKD 患者的腹部加权磁共振图像，将这些患者分为两组：一组 157 名用于训练网络，另一组 53 名用于测试。使用带有数据集指纹的 3D U-Net 架构，通过 -折交叉验证对网络进行训练，即 157 例中有 80%用于训练，其余 20%用于验证。我们使用 Dice 相似系数、组内相关系数和 Bland-Altman 分析来评估与手动方法相比，自动分割方法的性能。
在测试数据集上，自动和手动参考方法的几何一致性非常好（Dice 相似系数：平均值±标准差，0.962±0.018），肾脏体积范围为 178.9 至 2776.0 ml（平均值±标准差，1058.5±706.8 ml），外生囊肿体积范围为 113.4 至 2497.6 ml（平均值±标准差，549.0±559.1 ml）。组内相关系数为 0.9994（95%置信区间，0.9991 至 0.9996；<0.001），最小偏差为-2.424 ml（95%一致性界限，-49.80 至 44.95）。
我们开发了一种全自动分割方法来测量 TKV，该方法排除了外生囊肿，并且具有与人类专家相似的准确性。该技术可能在需要自动计算 TKV 以评估 ADPKD 进展和治疗反应的临床研究中有用。
