An Effective Radiomics Model for Noninvasive Discrimination of Fat-poor Angiomyolipoma from Clear Cell Renal Cell Carcinoma

Accurate preoperative differential diagnosis of fat-poor angiomyolipoma (fp-AML) and clear cell renal cell carcinoma (ccRCC) is essential for proper treatment planning. In this paper, we develop an effective radiomics model for reliable noninvasive discrimination of fp-AML from ccRCC, which incorporates a sophisticated feature selection procedure and a sparse radial basis function neural network (sRBFNN). Specifically, 774 three-dimensional radiomics features are first extracted from contrast-enhanced computed tomography (CECT) images. Pearson’s correlation matrices and Welch’s t-test are used to remove the insignificant features, then sequential forward floating selection method is utilized to select the discriminative features. Finally, the sRBFNN is employed for classification. The radiomics model is examined by leave-one-out cross validation and yields the best performance of 90.00%, 66.67%, 100.0%, and 0.9173 in terms of prediction accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curves, respectively. Furthermore, the reliability of the predictions is verified by evaluating the probabilistic outputs of the sRBFNN. The experimental results demonstrate that the developed radiomics model has great potential in the noninvasive discrimination of fp-AML from ccRCC.

[1]  D. Halpenny,et al.  The radiological diagnosis and treatment of renal angiomyolipoma-current status. , 2010, Clinical radiology.

[2]  K. Pearson.  VII. Note on regression and inheritance in the case of two parents , 1895, Proceedings of the Royal Society of London.

[3]  Tingwen Huang,et al.  Efficient construction of sparse radial basis function neural networks using L1-regularization , 2017, Neural Networks.

[4]  Mamta Juneja,et al.  Computer-aided diagnosis of renal lesions in CT images: A comprehensive survey and future prospects , 2019, Comput. Electr. Eng..

[5]  Nicola Schieda,et al.  Can Quantitative CT Texture Analysis be Used to Differentiate Fat-poor Renal Angiomyolipoma from Renal Cell Carcinoma on Unenhanced CT Images? , 2015, Radiology.

[6]  Lifen Yan,et al.  Angiomyolipoma with minimal fat: differentiation from clear cell renal cell carcinoma and papillary renal cell carcinoma by texture analysis on CT images. , 2015, Academic radiology.

[7]  Perry J Pickhardt,et al.  CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges. , 2017, Radiographics : a review publication of the Radiological Society of North America, Inc.

[8]  M. Karno,et al.  Renal cell carcinoma. , 1956, Bulletin. Tufts-New England Medical Center.

[9]  S. S. Kumar,et al.  An automatic computer-aided diagnosis system for liver tumours on computed tomography images , 2013, Comput. Electr. Eng..

[10]  Sachio Kuribayashi,et al.  Angiomyolipomas that do not contain fat attenuation at unenhanced CT. , 2005, Radiology.

[11]  David W. Aha,et al.  A Comparative Evaluation of Sequential Feature Selection Algorithms , 1995, AISTATS.

[12]  Stijn Bonte,et al.  Machine learning based brain tumour segmentation on limited data using local texture and abnormality , 2018, Comput. Biol. Medicine.

[13]  P. Lambin,et al.  Machine Learning methods for Quantitative Radiomic Biomarkers , 2015, Scientific Reports.

[14]  Ming Zhou,et al.  Angiomyolipoma with minimal fat on MDCT: can counts of negative-attenuation pixels aid diagnosis? , 2009, AJR. American journal of roentgenology.

[15]  U. Rajendra Acharya,et al.  Computer-aided diagnosis of Myocardial Infarction using ultrasound images with DWT, GLCM and HOS methods: A comparative study , 2015, Comput. Biol. Medicine.

[16]  Christine O Menias,et al.  Benign renal neoplasms in adults: cross-sectional imaging findings. , 2008, AJR. American journal of roentgenology.

[17]  Erick M Remer,et al.  Clinical correlates of renal angiomyolipoma subtypes in 209 patients: classic, fat poor, tuberous sclerosis associated and epithelioid. , 2008, The Journal of urology.

[18]  Namkug Kim,et al.  CT histogram analysis: differentiation of angiomyolipoma without visible fat from renal cell carcinoma at CT imaging. , 2008, Radiology.

[19]  He Huang,et al.  Probabilistic Classification Vector Machines for Multiclass Classification , 2019, 2019 Chinese Control And Decision Conference (CCDC).

[20]  Saeid Fallahpour,et al.  Using an ensemble classifier based on sequential floating forward selection for financial distress prediction problem , 2017 .

[21]  Claudio Landoni,et al.  Radiomics of the primary tumour as a tool to improve 18F-FDG-PET sensitivity in detecting nodal metastases in endometrial cancer , 2018, EJNMMI Research.

[22]  Jun Zhao,et al.  Novel 3D Radiomic Features for Computer-Aided Polyp Detection in CT Colonography , 2018, IEEE Access.

[23]  Liang-Bi Chen,et al.  Development and Experimental Evaluation of Machine-Learning Techniques for an Intelligent Hairy Scalp Detection System , 2018 .

[24]  Robert J. Gillies,et al.  Delta Radiomics Improves Pulmonary Nodule Malignancy Prediction in Lung Cancer Screening , 2018, IEEE Access.

[25]  Yi Li,et al.  Contrast-Enhanced Ultrasonography with Quantitative Analysis allows Differentiation of Renal Tumor Histotypes , 2016, Scientific Reports.

[26]  P. Lambin,et al.  Radiomics: the bridge between medical imaging and personalized medicine , 2017, Nature Reviews Clinical Oncology.

[27]  Shu-Huei Shen,et al.  Are there useful CT features to differentiate renal cell carcinoma from lipid-poor renal angiomyolipoma? , 2013, AJR. American journal of roentgenology.

[28]  Ronald M. Summers,et al.  A Bottom-Up Approach for Pancreas Segmentation Using Cascaded Superpixels and (Deep) Image Patch Labeling , 2015, IEEE Transactions on Image Processing.

[29]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[30]  Shuai Leng,et al.  Small (< 4 cm) Renal Masses: Differentiation of Angiomyolipoma Without Visible Fat From Renal Cell Carcinoma Using Unenhanced and Contrast-Enhanced CT. , 2015, AJR. American journal of roentgenology.

[31]  H. Aerts.  The Potential of Radiomic-Based Phenotyping in Precision Medicine: A Review. , 2016, JAMA oncology.

[32]  D. Toher,et al.  Why Welch’s test is Type I error robust , 2016 .

[33]  Junmo Kim,et al.  Differentiation of fat‐poor angiomyolipoma from clear cell renal cell carcinoma in contrast‐enhanced MDCT images using quantitative feature classification , 2017, Medical physics.

[34]  Bu-Sung Lee,et al.  Leveraging social media news to predict stock index movement using RNN-boost , 2018, Data Knowl. Eng..

[35]  Chiou-Jye Huang,et al.  Application of Support Vector Machine in Designing Theo Jansen Linkages , 2019, Applied Sciences.

[36]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[37]  R. Harikumar,et al.  Performance analysis of neural networks for classification of medical images with wavelets as a feature extractor , 2015, Int. J. Imaging Syst. Technol..