Department of Radiology, School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA; School of Computer and Control Engineering, Yantai University, Yantai, 264005, China.
Department of Pediatrics, Division of Pediatric Nephrology, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA.
J Pediatr Urol. 2019 Feb;15(1):75.e1-75.e7. doi: 10.1016/j.jpurol.2018.10.020. Epub 2018 Oct 31.
Anatomic characteristics of kidneys derived from ultrasound images are potential biomarkers of children with congenital abnormalities of the kidney and urinary tract (CAKUT), but current methods are limited by the lack of automated processes that accurately classify diseased and normal kidneys.
The objective of the study was to evaluate the diagnostic performance of deep transfer learning techniques to classify kidneys of normal children and those with CAKUT.
A transfer learning method was developed to extract features of kidneys from ultrasound images obtained during routine clinical care of 50 children with CAKUT and 50 controls. To classify diseased and normal kidneys, support vector machine classifiers were built on the extracted features using (1) transfer learning imaging features from a pretrained deep learning model, (2) conventional imaging features, and (3) their combination. These classifiers were compared, and their diagnosis performance was measured using area under the receiver operating characteristic curve (AUC), accuracy, specificity, and sensitivity.
The AUC for classifiers built on the combination features were 0.92, 0.88, and 0.92 for discriminating the left, right, and bilateral abnormal kidney scans from controls with classification rates of 84%, 81%, and 87%; specificity of 84%, 74%, and 88%; and sensitivity of 85%, 88%, and 86%, respectively. These classifiers performed better than classifiers built on either the transfer learning features or the conventional features alone (p < 0.001).
The present study validated transfer learning techniques for imaging feature extraction of ultrasound images to build classifiers for distinguishing children with CAKUT from controls. The experiments have demonstrated that the classifiers built on the transfer learning features and conventional image features could distinguish abnormal kidney images from controls with AUCs greater than 0.88, indicating that classification of ultrasound kidney scans has a great potential to aid kidney disease diagnosis. A limitation of the present study is the moderate number of patients that contributed data to the transfer learning approach.
The combination of transfer learning and conventional imaging features yielded the best classification performance for distinguishing children with CAKUT from controls based on ultrasound images of kidneys.
从超声图像中提取的肾脏解剖特征可能是儿童先天性肾和尿路异常（CAKUT）的潜在生物标志物，但目前的方法受到缺乏准确分类患病和正常肾脏的自动化过程的限制。
本研究旨在评估深度转移学习技术在分类正常儿童和 CAKUT 儿童肾脏方面的诊断性能。
开发了一种转移学习方法，从 50 名 CAKUT 儿童和 50 名对照儿童常规临床护理中获得的超声图像中提取肾脏特征。为了对患病和正常肾脏进行分类，使用（1）从预先训练的深度学习模型转移学习成像特征，（2）常规成像特征，以及（3）它们的组合，在提取特征上构建支持向量机分类器。比较这些分类器，并使用接收者操作特征曲线下的面积（AUC）、准确性、特异性和敏感性来衡量它们的诊断性能。
用于从对照组中区分左、右和双侧异常肾脏扫描的分类器的 AUC 分别为 0.92、0.88 和 0.92，分类率分别为 84%、81%和 87%；特异性为 84%、74%和 88%；敏感性为 85%、88%和 86%。这些分类器的性能优于仅基于转移学习特征或常规特征构建的分类器（p<0.001）。
本研究验证了用于超声图像成像特征提取的转移学习技术，以构建用于区分 CAKUT 儿童与对照的分类器。实验表明，基于转移学习特征和常规图像特征构建的分类器可以将异常肾脏图像与对照组区分开来，AUC 大于 0.88，这表明超声肾脏扫描的分类具有很大的潜力来辅助肾脏疾病的诊断。本研究的一个局限性是为转移学习方法提供数据的患者数量适中。
基于肾脏超声图像，转移学习和常规成像特征的组合可实现区分 CAKUT 儿童与对照的最佳分类性能。
