HeiShun Yu1,2, Jonathan Scalera3, Maria Khalid3, Anne-Sophie Touret3, Nicolas Bloch3, Baojun Li3, Muhammad M Qureshi3, Jorge A Soto3, Stephan W Anderson3. 1. Department of Radiology, Boston Medical Center, 820 Harrison Avenue, FGH Building, 3rd Floor, Boston, MA, 02118, USA. heishun.yu@mgh.harvard.edu. 2. Department of Radiology, Massachusetts General Hospital, 55 Fruit Street, Boston, MA, 02114, USA. heishun.yu@mgh.harvard.edu. 3. Department of Radiology, Boston Medical Center, 820 Harrison Avenue, FGH Building, 3rd Floor, Boston, MA, 02118, USA.
Abstract
PURPOSE: To evaluate the utility of texture analysis for the differentiation of renal tumors, including the various renal cell carcinoma subtypes and oncocytoma. MATERIALS AND METHODS: Following IRB approval, a retrospective analysis was performed, including all patients with pathology-proven renal tumors and an abdominal computed tomography (CT) examination. CT images of the tumors were manually segmented, and texture analysis of the segmented tumors was performed. A support vector machine (SVM) method was also applied to classify tumor types. Texture analysis results were compared to the various tumors and areas under the curve (AUC) were calculated. Similar calculations were performed with the SVM data. RESULTS: One hundred nineteen patients were included. Excellent discriminators of tumors were identified among the histogram-based features noting features skewness and kurtosis, which demonstrated AUCs of 0.91 and 0.93 (p < 0.0001), respectively, for differentiating clear cell subtype from oncocytoma. Histogram feature median demonstrated an AUC of 0.99 (p < 0.0001) for differentiating papillary subtype from oncocytoma and an AUC of 0.92 for differentiating oncocytoma from other tumors. Machine learning further improved the results achieving very good to excellent discrimination of tumor subtypes. The ability of machine learning to distinguish clear cell subtype from other tumors and papillary subtype from other tumors was excellent with AUCs of 0.91 and 0.92, respectively. CONCLUSION: Texture analysis is a promising non-invasive tool for distinguishing renal tumors on CT images. These results were further improved upon application of machine learning, and support the further development of texture analysis as a quantitative biomarker for distinguishing various renal tumors.
PURPOSE: To evaluate the utility of texture analysis for the differentiation of renal tumors, including the various renal cell carcinoma subtypes and oncocytoma. MATERIALS AND METHODS: Following IRB approval, a retrospective analysis was performed, including all patients with pathology-proven renal tumors and an abdominal computed tomography (CT) examination. CT images of the tumors were manually segmented, and texture analysis of the segmented tumors was performed. A support vector machine (SVM) method was also applied to classify tumor types. Texture analysis results were compared to the various tumors and areas under the curve (AUC) were calculated. Similar calculations were performed with the SVM data. RESULTS: One hundred nineteen patients were included. Excellent discriminators of tumors were identified among the histogram-based features noting features skewness and kurtosis, which demonstrated AUCs of 0.91 and 0.93 (p < 0.0001), respectively, for differentiating clear cell subtype from oncocytoma. Histogram feature median demonstrated an AUC of 0.99 (p < 0.0001) for differentiating papillary subtype from oncocytoma and an AUC of 0.92 for differentiating oncocytoma from other tumors. Machine learning further improved the results achieving very good to excellent discrimination of tumor subtypes. The ability of machine learning to distinguish clear cell subtype from other tumors and papillary subtype from other tumors was excellent with AUCs of 0.91 and 0.92, respectively. CONCLUSION: Texture analysis is a promising non-invasive tool for distinguishing renal tumors on CT images. These results were further improved upon application of machine learning, and support the further development of texture analysis as a quantitative biomarker for distinguishing various renal tumors.
Authors: Bino A Varghese; Frank Chen; Darryl H Hwang; Steven Y Cen; Inderbir S Gill; Vinay A Duddalwar Journal: Br J Radiol Date: 2018-06-21 Impact factor: 3.039
Authors: Matthew S Davenport; Hersh Chandarana; Nicole E Curci; Ankur Doshi; Samuel D Kaffenberger; Ivan Pedrosa; Erick M Remer; Nicola Schieda; Atul B Shinagare; Andrew D Smith; Zhen J Wang; Shane A Wells; Stuart G Silverman Journal: Abdom Radiol (NY) Date: 2018-09
Authors: Amir A Borhani; Rohit Dewan; Alessandro Furlan; Natalie Seiser; Amer H Zureikat; Aatur D Singhi; Brian Boone; Nathan Bahary; Melissa E Hogg; Michael Lotze; Herbert J Zeh; Mitchell E Tublin Journal: AJR Am J Roentgenol Date: 2019-12-04 Impact factor: 3.959