CT texture analysis of renal masses: pilot study using random forest classification for prediction of pathology.

RATIONALE AND OBJECTIVES Computed tomography texture analysis (CTTA) allows quantification of heterogeneity within a region of interest. This study investigates the possibility of distinguishing between several common renal masses using CTTA-derived parameters by developing and validating a predictive model. MATERIALS AND METHODS CTTA software was used to analyze 20 clear cell renal cell carcinomas (RCCs), 20 papillary RCCs, 20 oncocytomas, and 20 renal cysts. Regions of interest were drawn around each mass on multiple slices in the arterial, venous, and delayed phases on renal mass protocol CT scans. Unfiltered images and spatial band-pass filtered images were analyzed to quantify heterogeneity. Random forest method was used to construct a predictive model to classify lesions using quantitative parameters. The model was externally validated on a separate set of 19 unknown cases. RESULTS The random forest model correctly categorized oncocytomas in 89% of cases (sensitivity = 89%, specificity = 99%), clear cell RCCs in 91% of cases (sensitivity = 91%, specificity = 97%), cysts in 100% of cases (sensitivity = 100%, specificity = 100%), and papillary RCCs in 100% of cases (sensitivity = 100%, specificity = 98%). CONCLUSIONS CTTA, in conjunction with random forest modeling, demonstrates promise as a tool to characterize lesions. Various renal masses were accurately classified using quantitative information derived from routine scans.

[1]  Roberto Maroldi,et al.  Texture analysis of advanced non-small cell lung cancer (NSCLC) on contrast-enhanced computed tomography: prediction of the response to the first-line chemotherapy , 2013, European Radiology.

[2]  Omar S. Al-Kadi,et al.  Texture Analysis of Aggressive and Nonaggressive Lung Tumor CE CT Images , 2008, IEEE Transactions on Biomedical Engineering.

[3]  N. Obuchowski,et al.  Enhancement characteristics of papillary renal neoplasms revealed on triphasic helical CT of the kidneys. , 2002, AJR. American journal of roentgenology.

[4]  S. Jeon,et al.  Characterization of Small Renal Masses Less than 4 cm with Quadriphasic Multidetector Helical Computed Tomography: Differentiation of Benign and Malignant Lesions , 2012, Korean journal of urology.

[5]  J. Cho,et al.  Subtype differentiation of small renal cell carcinomas on three-phase MDCT: usefulness of the measurement of degree and heterogeneity of enhancement , 2012, Acta radiologica.

[6]  Yali Amit,et al.  Shape Quantization and Recognition with Randomized Trees , 1997, Neural Computation.

[7]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Daniel Margolis,et al.  Clear cell renal cell carcinoma: discrimination from other renal cell carcinoma subtypes and oncocytoma at multiphasic multidetector CT. , 2013, Radiology.

[9]  K. Miles,et al.  Tumour heterogeneity in oesophageal cancer assessed by CT texture analysis: preliminary evidence of an association with tumour metabolism, stage, and survival. , 2012, Clinical radiology.

[10]  J. Ellis,et al.  Quantitative Enhancement Washout Analysis of Solid Cortical Renal Masses Using Multidetector Computed Tomography , 2011, Journal of computer assisted tomography.

[11]  Xuesong Li,et al.  The correlation between size of renal cell carcinoma and its histopathological characteristics: a single center study of 1867 renal cell carcinoma cases , 2012, BJU international.

[12]  C. Good,et al.  Measurements of heterogeneity in gliomas on computed tomography relationship to tumour grade , 2012, Journal of Neuro-Oncology.

[13]  E. Fishman,et al.  Chromophobe renal cell carcinoma: multiphase MDCT enhancement patterns and morphologic features. , 2013, AJR. American journal of roentgenology.

[14]  V. Goh,et al.  Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival. , 2013, Radiology.

[15]  C Chatwin,et al.  Gray matter textural heterogeneity as a potential in-vivo biomarker of fine structural abnormalities in Asperger syndrome , 2012, The Pharmacogenomics Journal.

[16]  Chris R Chatwin,et al.  Texture analysis in non-contrast enhanced CT: impact of malignancy on texture in apparently disease-free areas of the liver. , 2009, European journal of radiology.

[17]  K. Miles,et al.  Tumour heterogeneity in non-small cell lung carcinoma assessed by CT texture analysis: a potential marker of survival , 2012, European Radiology.

[18]  Hersh Chandarana,et al.  Contemporary imaging of the renal mass. , 2012, The Urologic clinics of North America.

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  Wu-Chung Shen,et al.  Diagnosis of hepatic tumors with texture analysis in nonenhanced computed tomography images. , 2006, Academic radiology.

[21]  Ahmed Mosbah,et al.  Differentiation of renal cell carcinoma subtypes by multislice computerized tomography. , 2005, The Journal of urology.

[22]  Shoji Kido,et al.  Fractal Analysis of Small Peripheral Pulmonary Nodules in Thin-section CT: Evaluation of the Lung-nodule Interfaces , 2002, Journal of computer assisted tomography.

[23]  V. Goh,et al.  Assessment of response to tyrosine kinase inhibitors in metastatic renal cell cancer: CT texture as a predictive biomarker. , 2011, Radiology.

[24]  Chris R Chatwin,et al.  Hepatic enhancement in colorectal cancer: texture analysis correlates with hepatic hemodynamics and patient survival. , 2007, Academic Radiology.

[25]  C. Chatwin,et al.  Dynamic Contrast-Enhanced Texture Analysis of the Liver: Initial Assessment in Colorectal Cancer , 2011, Investigative radiology.

[26]  Balaji Ganeshan,et al.  Colorectal cancer: texture analysis of portal phase hepatic CT images as a potential marker of survival. , 2009, Radiology.

[27]  M. Jinzaki,et al.  Double-Phase Helical CT of Small Renal Parenchymal Neoplasms: Correlation with Pathologic Findings and Tumor Angiogenesis , 2000, Journal of computer assisted tomography.

[28]  Chris R Chatwin,et al.  In search of biologic correlates for liver texture on portal-phase CT. , 2007, Academic Radiology.

[29]  Elliot K Fishman,et al.  Preliminary Data Using Computed Tomography Texture Analysis for the Classification of Hypervascular Liver Lesions: Generation of a Predictive Model on the Basis of Quantitative Spatial Frequency Measurements—A Work in Progress , 2015, Journal of computer assisted tomography.

[30]  J. Kim,et al.  Predicting the histology of small renal masses using preoperative dynamic contrast-enhanced magnetic resonance imaging. , 2012, Urology.

[31]  Dina Muin,et al.  Texture-based classification of different gastric tumors at contrast-enhanced CT. , 2013, European journal of radiology.

[32]  Bal Sanghera,et al.  Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? , 2012, Insights into Imaging.

[33]  E. Kleinberg.  An overtraining-resistant stochastic modeling method for pattern recognition , 1996 .

[34]  R. Leveillee,et al.  Differentiation of oncocytoma and renal cell carcinoma in small renal masses (<4 cm): the role of 4-phase computerized tomography , 2011, World Journal of Urology.

[35]  Balaji Ganeshan,et al.  Texture analysis of non-small cell lung cancer on unenhanced computed tomography: initial evidence for a relationship with tumour glucose metabolism and stage , 2010, Cancer imaging : the official publication of the International Cancer Imaging Society.

[36]  Chaya S Moskowitz,et al.  Solid renal cortical tumors: differentiation with CT. , 2007, Radiology.

[37]  Chris Chatwin,et al.  Heterogeneity of Focal Breast Lesions and Surrounding Tissue Assessed by Mammographic Texture Analysis: Preliminary Evidence of an Association with Tumor Invasion and Estrogen Receptor Status , 2011, Front. Oncol..

[38]  Kyoung-Sik Cho,et al.  Differentiation of subtypes of renal cell carcinoma on helical CT scans. , 2002, AJR. American journal of roentgenology.

[39]  Hugo D. Critchley,et al.  Three-dimensional textural analysis of brain images reveals distributed grey-matter abnormalities in schizophrenia , 2010, European Radiology.