- author = "Ianto Lin Xi and Yijun Zhao and Robin Wang and Marcello Chang and Subhanik Purkayastha and Ken Chang and Raymond Y. Huang and Alvin C. Silva and Martin Vallieres and Peiman Habibollahi and Yong Fan and Beiji Zou and Terence P. Gade and Paul J. Zhang and Michael C. Soulen and Zishu Zhang and Harrison X. Bai and S. William Stavropoulos",
- title = "Deep Learning to Distinguish Benign from Malignant Renal Lesions Based on Routine {MR} Imaging",
- journal = "Clinical Cancer Research",
- year = "2020",
- volume = "26",
- number = "8",
- pages = "1944--1952",
- month = apr # " 15",
- keywords = "genetic algorithms, genetic programming, TPOT, GPU, Python sklearn",
- publisher = "American Association for Cancer Research",
- ISSN = "1078-0432",
-
URL = "
https://clincancerres.aacrjournals.org/content/early/2020/02/23/1078-0432.CCR-19-0374.full.pdf",
-
URL = "
https://clincancerres.aacrjournals.org/content/early/2020/02/23/1078-0432.CCR-19-0374",
-
DOI = "
doi:10.1158/1078-0432.CCR-19-0374",
-
code_url = "https://github.com/intrepidlemon/renal-mri",
- size = "9 pages",
-
abstract = "Purpose: With increasing incidence of renal mass, it
is important to make a pretreatment differentiation
between benign renal mass and malignant tumour. 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 learning model had a statistically significant higher test accuracy (0.70 vs. 0.56, P = 0.004). Compared with all experts averaged, the ensemble deep learning model 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.",
-
notes = "two NVidia V100 GPUs
'This hand-optimised pipe line out performed the TPOT pipeline'
overfitting (training ROC 0.73--0.99 => test 0.43--0.73)?
Supplementary data for this article are available at Clinical Cancer Research Online (http://clincancerres.aacrjournals.org/).",
