Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
Else Kröner Forschungskolleg Clonal Evolution in Cancer, University Hospital Cologne, Cologne, Germany.
Eur Radiol. 2020 Mar;30(3):1397-1404. doi: 10.1007/s00330-019-06455-7. Epub 2019 Nov 26.
To predict the main component of pure and mixed kidney stones using dual-energy computed tomography and machine learning.
200 kidney stones with a known composition as determined by infrared spectroscopy were examined using a non-anthropomorphic phantom on a spectral detector computed tomography scanner. Stones were of either pure (monocrystalline, n = 116) or compound (dicrystalline, n = 84) composition. Image acquisition was repeated twice using both, normal and low-dose protocols, respectively (ND/LD). Conventional images and low and high keV virtual monoenergetic images were reconstructed. Stones were semi-automatically segmented. A shallow neural network was trained using data from ND1 acquisition split into training (70%), testing (15%) and validation-datasets (15%). Performance for ND2 and both LD acquisitions was tested. Accuracy on a per-voxel and a per-stone basis was calculated.
Main components were: Whewellite (n = 80), weddellite (n = 21), Ca-phosphate (n = 39), cysteine (n = 20), struvite (n = 13), uric acid (n = 18) and xanthine stones (n = 9). Stone size ranged from 3 to 18 mm. Overall accuracy for predicting the main component on a per-voxel basis attained by ND testing dataset was 91.1%. On independently tested acquisitions, accuracy was 87.1-90.4%.
Even in compound stones, the main component can be reliably determined using dual energy CT and machine learning, irrespective of dose protocol.
• Spectral Detector Dual Energy CT and Machine Learning allow for an accurate prediction of stone composition. • Ex-vivo study demonstrates the dose independent assessment of pure and compound stones. • Lowest accuracy is reported for compound stones with struvite as main component.
利用双能 CT 和机器学习预测纯和混合肾结石的主要成分。
在光谱探测器 CT 扫描仪上使用非拟人化体模对 200 颗已知红外光谱成分的肾结石进行检查。结石为纯（单晶，n=116）或复合（双晶，n=84）成分。分别使用常规和低剂量方案（ND/LD）重复两次采集图像。重建常规图像和低、高 keV 虚拟单能图像。对结石进行半自动分割。使用从 ND1 采集中分割的训练（70%）、测试（15%）和验证数据集（15%）训练浅层神经网络。测试 ND2 和两种 LD 采集的性能。计算基于体素和结石的准确率。
主要成分包括：Whewellite（n=80）、weddellite（n=21）、Ca-磷酸盐（n=39）、半胱氨酸（n=20）、struvite（n=13）、尿酸（n=18）和黄嘌呤结石（n=9）。结石大小从 3 到 18 毫米不等。在基于体素的 ND 测试数据集上，预测主要成分的总体准确率为 91.1%。在独立测试的采集上，准确率为 87.1-90.4%。
即使是复合结石，也可以使用双能 CT 和机器学习可靠地确定主要成分，而与剂量方案无关。
• 光谱探测器双能 CT 和机器学习允许对结石成分进行准确预测。• 离体研究证明了对纯和复合结石进行独立于剂量的评估。• 结构最复杂的结石（以 struvite 为主要成分）的准确率最低。
