Zhi-Cheng Li1, Guangtao Zhai2, Jinheng Zhang1, Zhongqiu Wang3, Guiqin Liu4, Guang-Yu Wu5, Dong Liang1, Hairong Zheng1. 1. Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. 2. Institute of Image Communication and Network Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China. 3. Department of Radiology, The Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China. 4. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 1630, Dongfang Road, Pudong, Shanghai, 200120, China. sdzclgq@126.com. 5. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No. 1630, Dongfang Road, Pudong, Shanghai, 200120, China. danielrau@163.com.
Abstract
OBJECTIVES: To develop a radiomics model with all-relevant imaging features from multiphasic computed tomography (CT) for differentiating clear cell renal cell carcinoma (ccRCC) from non-ccRCC and to investigate the possible radiogenomics link between the imaging features and a key ccRCC driver gene-the von Hippel-Lindau (VHL) gene mutation. METHODS: In this retrospective two-center study, two radiomics models were built using random forest from a training cohort (170 patients), where one model was built with all-relevant features and the other with minimum redundancy maximum relevance (mRMR) features. A model combining all-relevant features and clinical factors (sex, age) was also built. The radiogenomics association between selected features and VHL mutation was investigated by Wilcoxon rank-sum test. All models were tested on an independent validation cohort (85 patients) with ROC curves analysis. RESULTS: The model with eight all-relevant features from corticomedullary phase CT achieved an AUC of 0.949 and an accuracy of 92.9% in the validation cohort, which significantly outperformed the model with eight mRMR features (seven from nephrographic phase and one from corticomedullary phase) with an AUC of 0.851 and an accuracy of 81.2%. Combining age and sex did not benefit the performance. Five out of eight all-relevant features were significantly associated with VHL mutation, while all eight mRMR features were significantly associated with VHL mutation (false discovery rate-adjusted p < 0.05). CONCLUSIONS: All-relevant features in corticomedullary phase CT can be used to differentiate ccRCC from non-ccRCC. Most subtype-discriminative imaging features were found to be significantly associated with VHL mutation, which may underlie the molecular basis of the radiomics features. KEY POINTS: • All-relevant features in corticomedullary phase CT can be used to differentiate ccRCC from non-ccRCC with high accuracy. • Most RCC-subtype-discriminative CT features were associated with the key RCC-driven gene-the VHL gene mutation. • Radiomics model can be more accurate and interpretable when the imaging features could reflect underlying molecular basis of RCC.
OBJECTIVES: To develop a radiomics model with all-relevant imaging features from multiphasic computed tomography (CT) for differentiating clear cell renal cell carcinoma (ccRCC) from non-ccRCC and to investigate the possible radiogenomics link between the imaging features and a key ccRCC driver gene-the von Hippel-Lindau (VHL) gene mutation. METHODS: In this retrospective two-center study, two radiomics models were built using random forest from a training cohort (170 patients), where one model was built with all-relevant features and the other with minimum redundancy maximum relevance (mRMR) features. A model combining all-relevant features and clinical factors (sex, age) was also built. The radiogenomics association between selected features and VHL mutation was investigated by Wilcoxon rank-sum test. All models were tested on an independent validation cohort (85 patients) with ROC curves analysis. RESULTS: The model with eight all-relevant features from corticomedullary phase CT achieved an AUC of 0.949 and an accuracy of 92.9% in the validation cohort, which significantly outperformed the model with eight mRMR features (seven from nephrographic phase and one from corticomedullary phase) with an AUC of 0.851 and an accuracy of 81.2%. Combining age and sex did not benefit the performance. Five out of eight all-relevant features were significantly associated with VHL mutation, while all eight mRMR features were significantly associated with VHL mutation (false discovery rate-adjusted p < 0.05). CONCLUSIONS: All-relevant features in corticomedullary phase CT can be used to differentiate ccRCC from non-ccRCC. Most subtype-discriminative imaging features were found to be significantly associated with VHL mutation, which may underlie the molecular basis of the radiomics features. KEY POINTS: • All-relevant features in corticomedullary phase CT can be used to differentiate ccRCC from non-ccRCC with high accuracy. • Most RCC-subtype-discriminative CT features were associated with the key RCC-driven gene-the VHL gene mutation. • Radiomics model can be more accurate and interpretable when the imaging features could reflect underlying molecular basis of RCC.
Entities:
Keywords:
Diagnostic imaging; Radiomics; Renal cell carcinomas; von Hippel-Lindau disease
Authors: Pari V Pandharipande; Debra A Gervais; Rebecca I Hartman; Mukesh G Harisinghani; Adam S Feldman; Peter R Mueller; G Scott Gazelle Journal: Radiology Date: 2010-09 Impact factor: 11.105
Authors: Nicolas De Jay; Simon Papillon-Cavanagh; Catharina Olsen; Nehme El-Hachem; Gianluca Bontempi; Benjamin Haibe-Kains Journal: Bioinformatics Date: 2013-07-03 Impact factor: 6.937
Authors: Michael J Leveridge; Antonio Finelli; John R Kachura; Andrew Evans; Hannah Chung; Daniel A Shiff; Kimberly Fernandes; Michael A S Jewett Journal: Eur Urol Date: 2011-06-24 Impact factor: 20.096
Authors: A Ari Hakimi; Ying-Bei Chen; James Wren; Mithat Gonen; Omar Abdel-Wahab; Adriana Heguy; Han Liu; Shugaku Takeda; Satish K Tickoo; Victor E Reuter; Martin H Voss; Robert J Motzer; Jonathan A Coleman; Emily H Cheng; Paul Russo; James J Hsieh Journal: Eur Urol Date: 2012-09-27 Impact factor: 20.096
Authors: Jonathan R Young; Daniel Margolis; Steven Sauk; Allan J Pantuck; James Sayre; Steven S Raman Journal: Radiology Date: 2013-02-04 Impact factor: 11.105
Authors: Natally Horvat; Joao Miranda; Maria El Homsi; Jacob J Peoples; Niamh M Long; Amber L Simpson; Richard K G Do Journal: Abdom Radiol (NY) Date: 2021-11-26
Authors: Felix Y Yap; Bino A Varghese; Steven Y Cen; Darryl H Hwang; Xiaomeng Lei; Bhushan Desai; Christopher Lau; Lindsay L Yang; Austin J Fullenkamp; Simin Hajian; Marielena Rivas; Megha Nayyar Gupta; Brian D Quinn; Manju Aron; Mihir M Desai; Monish Aron; Assad A Oberai; Inderbir S Gill; Vinay A Duddalwar Journal: Eur Radiol Date: 2020-08-15 Impact factor: 5.315
Authors: Shiqi Zhang; Tao Zeng; Bin Hu; Yu-Hang Zhang; Kaiyan Feng; Lei Chen; Zhibin Niu; Jianhao Li; Tao Huang; Yu-Dong Cai Journal: Front Bioeng Biotechnol Date: 2020-05-26