TY - JOUR
T1 - Deep learning to distinguish benign from malignant renal lesions based on routine MR imaging
AU - Xi, Ianto Lin
AU - Zhao, Yijun
AU - Wang, Robin
AU - Chang, Marcello
AU - Purkayastha, Subhanik
AU - Chang, Ken
AU - Huang, Raymond Y.
AU - Silva, Alvin C.
AU - Valliéres, Martin
AU - Habibollahi, Peiman
AU - Fan, Yong
AU - Zou, Beiji
AU - Gade, Terence P.
AU - Zhang, Paul J.
AU - Soulen, Michael C.
AU - Zhang, Zishu
AU - Bai, Harrison X.
AU - Stavropoulos, S. William
N1 - Funding Information:
This study was supported by RSNA fellow research grant (RF1802), National Natural Science Foundation of China grant (8181101287), SIR Foundation Radiology Resident Research Grant, and National Cancer Institute of the National Institutes of Health under Award Number R03CA249554 to H.X. Bai. This project was supported by a training grant from the National Institute of Biomedical Imaging and Bioengineering (NIBIB) of the National Institutes of Health under award number 5T32EB1680 and by the National Cancer Institute (NCI) of the National Institutes of Health under Award Number F30CA239407 to K. Chang. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The study was supported by funding from the Nicole Foundation for Kidney Cancer Research to S.W. Stavropoulos. The authors acknowledge the help of Hui Liu (H.L.), Ting Huang (T.H.), Dehong Peng (D.P.), and Quanliang Shang (Q.S.) in evaluating all renal lesions in the test set; Lin Zhu (L.Z.) and Yeyu Cai (Y.C.) in segmenting all renal lesions in the test set; and Sukhdeep Khurana, Aidan McGirr, An Xie, and JianbinLiu in data collection.
Funding Information:
T.P. Gade is an employee/paid consultant for Trisalus Life Sciences. S.W. Stavropoulos is an employee/paid consultant for Becton Dickinson, and reports receiving commercial research grants from Sillajen and Cook Medical. No potential conflicts of interest were disclosed by the other authors.
Publisher Copyright:
© 2020 American Association for Cancer Research.
PY - 2020/4/15
Y1 - 2020/4/15
N2 - 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: PreoperativeMRimages (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 multiinstitutional dataset with good accuracy, sensitivity, and specificity comparable with experts and radiomics.
AB - 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: PreoperativeMRimages (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 multiinstitutional dataset with good accuracy, sensitivity, and specificity comparable with experts and radiomics.
UR - http://www.scopus.com/inward/record.url?scp=85082407753&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082407753&partnerID=8YFLogxK
U2 - 10.1158/1078-0432.CCR-19-0374
DO - 10.1158/1078-0432.CCR-19-0374
M3 - Article
C2 - 31937619
AN - SCOPUS:85082407753
SN - 1078-0432
VL - 26
SP - 1944
EP - 1952
JO - Clinical Cancer Research
JF - Clinical Cancer Research
IS - 8
ER -