Abstract：
To investigate the feasibility of using deep learning (DL) to differentiate normal from abnormal (or scarred) kidneys using technetium-99m dimercaptosuccinic acid (99mTc-DMSA) single-photon-emission computed tomography (SPECT) in paediatric patients.
Three hundred and one 99mTc-DMSA renal SPECT examinations were reviewed retrospectively. The 301 patients were split randomly into 261, 20, and 20 for training, validation, and testing data, respectively. The DL model was trained using three-dimensional (3D) SPECT images, two-dimensional (2D) maximum intensity projections (MIPs), and 2.5-dimensional (2.5D) MIPs (i.e., transverse, sagittal, and coronal views). Each DL model was trained to determine renal SPECT images into either normal or abnormal. Consensus reading results by two nuclear medicine physicians served as the reference standard.
The DL model trained by 2.5D MIPs outperformed that trained by either 3D SPECT images or 2D MIPs. The accuracy, sensitivity, and specificity of the 2.5D model for the differentiation between normal and abnormal kidneys were 92.5%, 90% and 95%, respectively.
The experimental results suggest that DL has the potential to differentiate normal from abnormal kidneys in children using 99mTc-DMSA SPECT imaging.
Three hundred and one 99mTc-DMSA renal SPECT examinations were reviewed retrospectively. The 301 patients were split randomly into 261, 20, and 20 for training, validation, and testing data, respectively. The DL model was trained using three-dimensional (3D) SPECT images, two-dimensional (2D) maximum intensity projections (MIPs), and 2.5-dimensional (2.5D) MIPs (i.e., transverse, sagittal, and coronal views). Each DL model was trained to determine renal SPECT images into either normal or abnormal. Consensus reading results by two nuclear medicine physicians served as the reference standard.
The DL model trained by 2.5D MIPs outperformed that trained by either 3D SPECT images or 2D MIPs. The accuracy, sensitivity, and specificity of the 2.5D model for the differentiation between normal and abnormal kidneys were 92.5%, 90% and 95%, respectively.
The experimental results suggest that DL has the potential to differentiate normal from abnormal kidneys in children using 99mTc-DMSA SPECT imaging.
摘要：
目的：研究使用99m二巯基琥珀酸（99mTc-DMSA）单光子发射计算机断层扫描（SPECT）在儿科患者中使用深度学习（DL）区分正常肾脏和异常（或疤痕）肾脏的可行性。
方法：对3001例99mTc-DMSA肾SPECT检查进行回顾性分析。301名患者被随机分为261名、20名和20名进行训练，验证,和测试数据，分别。使用三维(3D)SPECT图像训练DL模型，二维（2D）最大强度投影（MIP），和2.5维(2.5D)MIP(即，横向,矢状,和冠状视图)。训练每个DL模型以确定肾SPECT图像为正常或异常。两位核医学医生的共识阅读结果作为参考标准。
结果：由2.5DMIP训练的DL模型优于由3DSPECT图像或2DMIP训练的DL模型。准确性,灵敏度,2.5D模型对正常肾脏和异常肾脏的区分特异性为92.5%，90%和95%，分别。
结论：实验结果表明，使用99mTc-DMSASPECT显像，DL具有区分儿童正常肾脏和异常肾脏的潜力。
方法：对3001例99mTc-DMSA肾SPECT检查进行回顾性分析。301名患者被随机分为261名、20名和20名进行训练，验证,和测试数据，分别。使用三维(3D)SPECT图像训练DL模型，二维（2D）最大强度投影（MIP），和2.5维(2.5D)MIP(即，横向,矢状,和冠状视图)。训练每个DL模型以确定肾SPECT图像为正常或异常。两位核医学医生的共识阅读结果作为参考标准。
结果：由2.5DMIP训练的DL模型优于由3DSPECT图像或2DMIP训练的DL模型。准确性,灵敏度,2.5D模型对正常肾脏和异常肾脏的区分特异性为92.5%，90%和95%，分别。
结论：实验结果表明，使用99mTc-DMSASPECT显像，DL具有区分儿童正常肾脏和异常肾脏的潜力。
