Natalie L Demirjian1, Bino A Varghese2, Steven Y Cen2, Darryl H Hwang2, Manju Aron3, Imran Siddiqui3, Brandon K K Fields4, Xiaomeng Lei2, Felix Y Yap5, Marielena Rivas2, Sharath S Reddy6, Haris Zahoor7, Derek H Liu2, Mihir Desai8, Suhn K Rhie9, Inderbir S Gill8, Vinay Duddalwar10,11. 1. College of Medicine - Tucson, University of Arizona, Tucson, AZ, USA. 2. Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. 3. Department of Pathology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. 4. Scripps Mercy Hospital San Diego, San Diego, CA, USA. 5. Radiology Associates of San Luis Obispo, Atascadero, CA, USA. 6. Department of Urology, Yale New Haven Hospital, New Haven, CT, USA. 7. Department of Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. 8. Department of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. 9. Department of Biochemistry and Molecular Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. 10. Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. vinay.duddalwar@med.usc.edu. 11. Department of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA. vinay.duddalwar@med.usc.edu.
Abstract
OBJECTIVES: To evaluate the utility of CT-based radiomics signatures in discriminating low-grade (grades 1-2) clear cell renal cell carcinomas (ccRCC) from high-grade (grades 3-4) and low TNM stage (stages I-II) ccRCC from high TNM stage (stages III-IV). METHODS: A total of 587 subjects (mean age 60.2 years ± 12.2; range 22-88.7 years) with ccRCC were included. A total of 255 tumors were high grade and 153 were high stage. For each subject, one dominant tumor was delineated as the region of interest (ROI). Our institutional radiomics pipeline was then used to extract 2824 radiomics features across 12 texture families from the manually segmented volumes of interest. Separate iterations of the machine learning models using all extracted features (full model) as well as only a subset of previously identified robust metrics (robust model) were developed. Variable of importance (VOI) analysis was performed using the out-of-bag Gini index to identify the top 10 radiomics metrics driving each classifier. Model performance was reported using area under the receiver operating curve (AUC). RESULTS: The highest AUC to distinguish between low- and high-grade ccRCC was 0.70 (95% CI 0.62-0.78) and the highest AUC to distinguish between low- and high-stage ccRCC was 0.80 (95% CI 0.74-0.86). Comparable AUCs of 0.73 (95% CI 0.65-0.8) and 0.77 (95% CI 0.7-0.84) were reported using the robust model for grade and stage classification, respectively. VOI analysis revealed the importance of neighborhood operation-based methods, including GLCM, GLDM, and GLRLM, in driving the performance of the robust models for both grade and stage classification. CONCLUSION: Post-validation, CT-based radiomics signatures may prove to be useful tools to assess ccRCC grade and stage and could potentially add to current prognostic models. Multiphase CT-based radiomics signatures have potential to serve as a non-invasive stratification schema for distinguishing between low- and high-grade as well as low- and high-stage ccRCC. KEY POINTS: • Radiomics signatures derived from clinical multiphase CT images were able to stratify low- from high-grade ccRCC, with an AUC of 0.70 (95% CI 0.62-0.78). • Radiomics signatures derived from multiphase CT images yielded discriminative power to stratify low from high TNM stage in ccRCC, with an AUC of 0.80 (95% CI 0.74-0.86). • Models created using only robust radiomics features achieved comparable AUCs of 0.73 (95% CI 0.65-0.80) and 0.77 (95% CI 0.70-0.84) to the model with all radiomics features in classifying ccRCC grade and stage, respectively.
OBJECTIVES: To evaluate the utility of CT-based radiomics signatures in discriminating low-grade (grades 1-2) clear cell renal cell carcinomas (ccRCC) from high-grade (grades 3-4) and low TNM stage (stages I-II) ccRCC from high TNM stage (stages III-IV). METHODS: A total of 587 subjects (mean age 60.2 years ± 12.2; range 22-88.7 years) with ccRCC were included. A total of 255 tumors were high grade and 153 were high stage. For each subject, one dominant tumor was delineated as the region of interest (ROI). Our institutional radiomics pipeline was then used to extract 2824 radiomics features across 12 texture families from the manually segmented volumes of interest. Separate iterations of the machine learning models using all extracted features (full model) as well as only a subset of previously identified robust metrics (robust model) were developed. Variable of importance (VOI) analysis was performed using the out-of-bag Gini index to identify the top 10 radiomics metrics driving each classifier. Model performance was reported using area under the receiver operating curve (AUC). RESULTS: The highest AUC to distinguish between low- and high-grade ccRCC was 0.70 (95% CI 0.62-0.78) and the highest AUC to distinguish between low- and high-stage ccRCC was 0.80 (95% CI 0.74-0.86). Comparable AUCs of 0.73 (95% CI 0.65-0.8) and 0.77 (95% CI 0.7-0.84) were reported using the robust model for grade and stage classification, respectively. VOI analysis revealed the importance of neighborhood operation-based methods, including GLCM, GLDM, and GLRLM, in driving the performance of the robust models for both grade and stage classification. CONCLUSION: Post-validation, CT-based radiomics signatures may prove to be useful tools to assess ccRCC grade and stage and could potentially add to current prognostic models. Multiphase CT-based radiomics signatures have potential to serve as a non-invasive stratification schema for distinguishing between low- and high-grade as well as low- and high-stage ccRCC. KEY POINTS: • Radiomics signatures derived from clinical multiphase CT images were able to stratify low- from high-grade ccRCC, with an AUC of 0.70 (95% CI 0.62-0.78). • Radiomics signatures derived from multiphase CT images yielded discriminative power to stratify low from high TNM stage in ccRCC, with an AUC of 0.80 (95% CI 0.74-0.86). • Models created using only robust radiomics features achieved comparable AUCs of 0.73 (95% CI 0.65-0.80) and 0.77 (95% CI 0.70-0.84) to the model with all radiomics features in classifying ccRCC grade and stage, respectively.
Authors: Jean-Jacques Patard; Emmanuelle Leray; Nathalie Rioux-Leclercq; Luca Cindolo; Vincenzo Ficarra; Amnon Zisman; Alexandre De La Taille; Jacques Tostain; Walter Artibani; Claude C Abbou; Bernard Lobel; François Guillé; Dominique K Chopin; Peter F A Mulders; Christopher G Wood; David A Swanson; Robert A Figlin; Arie S Belldegrun; Allan J Pantuck Journal: J Clin Oncol Date: 2005-04-20 Impact factor: 44.544
Authors: Kousei Ishigami; Leandro V Leite; Marius G Pakalniskis; Daniel K Lee; Danniele G Holanda; David M Kuehn Journal: Springerplus Date: 2014-11-26
Authors: Bino A Varghese; Darryl Hwang; Steven Y Cen; Joshua Levy; Derek Liu; Christopher Lau; Marielena Rivas; Bhushan Desai; David J Goodenough; Vinay A Duddalwar Journal: J Appl Clin Med Phys Date: 2019-06-20 Impact factor: 2.102