Deep Learning to Distinguish Benign from Malignant Renal Lesions Based on Routine MR Imaging
Deep Learning to Distinguish Benign from Malignant Renal Lesions Based on Routine MR Imaging
复制标题
DOI：
10.1158/1078-0432.ccr-19-0374
复制
发表时间：
2020-04-01
影响因子：
11.5
通讯作者：
Stavropoulos, S. William
中科院分区：
文献类型：
--
作者：
Xi, Ianto Lin;Zhao, Yijun;Stavropoulos, S. William
目的：随着肾肿块发病率的增加，对肾良性肿块与恶性肿瘤进行鉴别具有重要意义。我们旨在开发一个深度学习模型，通过在常规MR成像上应用残差卷积神经网络（ResNet）来区分良性肾肿瘤和肾细胞癌（RCC）。实验设计：在一个多中心队列中，对1162例经病理或影像学确诊的肾脏病变进行术前MR图像（t2加权和t1对比序列），分为训练组、验证组和测试组（70:20:10分割）。结合临床变量和T1C、T2WI MR图像，采用bagging分类器建立基于ResNet的集合模型预测肾肿瘤病理。将最终的模型性能与专家解释和最优化的放射组学模型进行比较。结果：1162例肾脏病变中，恶性655例，良性507例。与基线零规则算法相比，集成深度学习模型的测试准确率有统计学意义上的提高（0.70 vs. 0.56, P = 0.004）。与所有专家平均值相比，集成深度学习模型具有更高的测试精度（0.70 vs. 0.60, P = 0.053），灵敏度（0.92 vs. 0.80, P = 0.017）和特异性（0.41 vs. 0.35, P = 0.450）。与放射组学模型相比，集成深度学习模型具有更高的检测准确率（0.70 vs. 0.62, P = 0.081）、灵敏度（0.92 vs. 0.79, P = 0.012）和特异性（0.41 vs. 0.39, P = 0.770）。结论：深度学习可以在多机构数据集中使用常规MR成像无创地区分良性肾肿瘤和RCC，具有与专家和放射组学相当的准确性、灵敏度和特异性。
Purpose: With increasing incidence of renal mass, it is important to make a pretreatment differentiation between benign renal mass and malignant tumor. We aimed to develop a deep learning model that distinguishes benign renal tumors from renal cell carcinoma (RCC) by applying a residual convolutional neural network (ResNet) on routine MR imaging.Experimental Design: Preoperative MR images (T2-weighted and T1-postcontrast sequences) of 1,162 renal lesions definitely diagnosed on pathology or imaging in a multicenter cohort were divided into training, validation, and test sets (70:20:10 split). An ensemble model based on ResNet was built combining clinical variables and T1C and T2WI MR images using a bagging classifier to predict renal tumor pathology. Final model performance was compared with expert interpretation and the most optimized radiomics model.Results: Among the 1,162 renal lesions, 655 were malignant and 507 were benign. Compared with a baseline zero rule algorithm, the ensemble deep learningmodel had a statistically significant higher test accuracy (0.70 vs. 0.56, P = 0.004). Compared with all experts averaged, the ensemble deep learningmodel had higher test accuracy (0.70 vs. 0.60, P = 0.053), sensitivity (0.92 vs. 0.80, P = 0.017), and specificity (0.41 vs. 0.35, P = 0.450). Compared with the radiomics model, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.62, P = 0.081), sensitivity (0.92 vs. 0.79, P = 0.012), and specificity (0.41 vs. 0.39, P = 0.770).Conclusions: Deep learning can noninvasively distinguish benign renal tumors from RCC using conventional MR imaging in a multi-institutional dataset with good accuracy, sensitivity, and specificity comparable with experts and radiomics.