Department of Diagnostic Imaging, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China.
School of Information and Electronics, Beijing Institute of Technology, Beijing, 100081, China.
Abdom Radiol (NY). 2021 Jul;46(7):3260-3268. doi: 10.1007/s00261-021-02981-5. Epub 2021 Mar 3.
With advancements in medical imaging, more renal tumors are detected early, but it remains a challenge for radiologists to accurately distinguish subtypes of renal parenchymal tumors. We aimed to establish a novel deep convolutional neural network (CNN) model and investigate its effect on identifying subtypes of renal parenchymal tumors in T2-weighted fat saturation sequence magnetic resonance (MR) images.
This retrospective study included 199 patients with pathologically confirmed renal parenchymal tumors, including 77, 46, 34, and 42 patients with clear cell renal cell carcinoma (ccRCC), chromophobe renal cell carcinoma (chRCC), angiomyolipoma (AML), and papillary renal cell carcinoma (pRCC), respectively. All enrolled patients underwent kidney MR scans with the field strength of 1.5 Tesla (T) or 3.0 T before surgery. We selected T2-weighted fat saturation sequence images of all patients and built a deep learning model to determine the type of renal tumors. Receiver operating characteristic (ROC) curve was depicted to estimate the performance of the CNN model; the accuracy, precision, sensitivity, specificity, F-score, and area under the curve (AUC) were calculated. One-way analysis of variance and χ tests of independent samples were used to analyze the variables.
The experimental results demonstrated that the model had a 60.4% overall accuracy, a 61.7% average accuracy, and a macro-average AUC of 0.82. The AUCs for ccRCC, chRCC, AML, and pRCC were 0.94, 0.78, 0.80, and 0.76, respectively.
Deep CNN model based on T2-weighted fat saturation sequence MR images was useful to classify the subtypes of renal parenchymal tumors with a relatively high diagnostic accuracy.
随着医学成像技术的进步，更多的肾肿瘤被早期发现，但对于放射科医生来说，准确区分肾实质肿瘤的亚型仍然是一个挑战。本研究旨在建立一种新的深度卷积神经网络（CNN）模型，并探讨其在 T2 加权脂肪饱和序列磁共振（MR）图像中识别肾实质肿瘤亚型的效果。
这是一项回顾性研究，纳入了 199 例经病理证实的肾实质肿瘤患者，包括 77 例、46 例、34 例和 42 例透明细胞肾细胞癌（ccRCC）、嫌色细胞肾细胞癌（chRCC）、血管平滑肌脂肪瘤（AML）和乳头状肾细胞癌（pRCC）患者。所有入组患者均在术前进行了场强为 1.5T 或 3.0T 的肾脏 MR 扫描。我们选择了所有患者的 T2 加权脂肪饱和序列图像，并建立了一个深度学习模型来确定肾肿瘤的类型。描绘了受试者工作特征（ROC）曲线以评估 CNN 模型的性能；计算了准确率、精确率、敏感度、特异度、F 分数和曲线下面积（AUC）。采用单因素方差分析和 χ 检验对变量进行分析。
实验结果表明，该模型的总体准确率为 60.4%，平均准确率为 61.7%，宏观平均 AUC 为 0.82。ccRCC、chRCC、AML 和 pRCC 的 AUC 分别为 0.94、0.78、0.80 和 0.76。
基于 T2 加权脂肪饱和序列 MR 图像的深度 CNN 模型有助于对肾实质肿瘤的亚型进行分类，具有较高的诊断准确率。
