Radiomics of small renal masses on multiphasic CT: accuracy of machine learning–based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat
To investigate the discriminative capabilities of different machine learning–based classification models on the differentiation of small (< 4 cm) renal angiomyolipoma without visible fat (AMLwvf) and renal cell carcinoma (RCC).
This study retrospectively collected 163 patients with pathologically proven small renal mass, including 118 RCC and 45 AMLwvf patients. Target region of interest (ROI) delineation, followed by texture feature extraction, was performed on a representative slice with the largest lesion area on each phase of the four-phase CT images. Fifteen concatenations of the four-phasic features were fed into 224 classification models (built with 8 classifiers and 28 feature selection methods), classification performances of the 3360 resultant discriminative models were compared, and the top-ranked features were analyzed.
Image features extracted from the unenhanced phase (UP) CT image demonstrated dominant classification performances over features from other three phases. The two discriminative models “SVM + t_score” and “SVM + relief” achieved the highest classification AUC of 0.90. The 10 top-ranked features from UP included 1 shape feature, 5 first-order statistics features, and 4 texture features, where the shape feature and the first-order statistics features showed superior discriminative capabilities in differentiating RCC vs. AMLwvf through the t-SNE visualization.
Image features extracted from UP are sufficient to generate accurate differentiation between AMLwvf and RCC using machine learning–based classification model.
• Radiomics extracted from unenhanced CT are sufficient to accurately differentiate angiomyolipoma without visible fat and renal cell carcinoma using machine learning–based classification model.
• The highest discriminative models achieved an AUC of 0.90 and were based on the analysis of unenhanced CT, alone or in association with images obtained at the nephrographic phase.
• Features related to shape and to histogram analysis (first-order statistics) showed superior discrimination compared with gray-level distribution of the image (second-order statistics, commonly called texture features).
KeywordsAngiomyolipoma Renal cell carcinoma Machine learning Classification
Angiomyolipoma without visible fat
Area under the ROC curve
Gray-level co-occurrence matrix
Gray-level dependence matrix
Gray-level run length matrix
Gray-level size zone matrix
Interobserver correlation coefficient
Neighboring gray tone difference matrix
Picture archiving and communication system
Renal cell carcinoma
Receiver operating characteristic
Region of interest
Synthetic minority oversampling technique
T-distributed stochastic neighbor embedding method
We gratefully acknowledge all the members of Department of Radiology, Guangzhou First People’s Hospital, for continuous assistance. In particular, we would like to thank Dr. Zaiyi Liu for his advice during the project.
This study has received funding from the National Natural Science Foundation of China (81874216 and 81728016), the National Key Research and Development Program of China (2017YFC0112900), the Natural Science Foundation of Guangdong Province, P.R. China (2018A030313282), the Fundamental Research Funds for the Central Universities, SCUT (2018MS23), and the Guangzhou Science and Technology Project, P.R. China (201607010038).
Compliance with ethical standards
The scientific guarantor of this publication is Dr. Xin Zhen.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Written informed consent was waived by the Institutional Review Board.
Institutional Review Board approval was obtained.
• multicenter study
- 1.Simpfendorfer C, Herts BR, Motta-Ramirez GA et al (2009) Angiomyolipoma with minimal fat on MDCT: can counts of negative-attenuation pixels aid diagnosis? AJR Am J Roentgenol 192:438Google Scholar
- 12.van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104Google Scholar
- 13.Pyradiomics Documentation. Available via https://pyradiomics.readthedocs.io/en/latest/. Accessed 6 July 2019
- 15.He H, Yang B, Garcia EA, Li S (2008) ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: IEEE International Joint Conference on Neural NetworksGoogle Scholar