CT-based radiomics stratification of tumor grade and TNM stage of clear cell renal cell carcinoma

被引：71

作者：

Demirjian, Natalie L. ^{[1
]}

Varghese, Bino A. ^{[2
]}

Cen, Steven Y. ^{[2
]}

Hwang, Darryl H. ^{[2
]}

Aron, Manju ^{[3
]}

Siddiqui, Imran ^{[3
]}

Fields, Brandon K. K. ^{[4
]}

Lei, Xiaomeng ^{[2
]}

Yap, Felix Y. ^{[5
]}

Rivas, Marielena ^{[2
]}

Reddy, Sharath S. ^{[6
]}

Zahoor, Haris ^{[7
]}

Liu, Derek H. ^{[2
]}

Desai, Mihir ^{[8
]}

Rhie, Suhn K. ^{[9
]}

Gill, Inderbir S. ^{[8
]}

Duddalwar, Vinay ^{[2
,8
]}

机构：

[1] Univ Arizona, Coll Med Tucson, Tucson, AZ USA

[2] Univ Southern Calif, Dept Radiol, Keck Sch Med, Los Angeles, CA 90007 USA

[3] Univ Southern Calif, Keck Sch Med, Dept Pathol, Los Angeles, CA 90007 USA

[4] Scripps Mercy Hosp San Diego, San Diego, CA USA

[5] Radiol Associates San Luis Obispo, Atascadero, CA USA

[6] Yale New Haven Hosp, Dept Urol, 20 York St, New Haven, CT 06504 USA

[7] Univ Southern Calif, Keck Sch Med, Dept Med, Los Angeles, CA 90007 USA

[8] Univ Southern Calif, Keck Sch Med, Dept Urol, Los Angeles, CA 90007 USA

[9] Univ Southern Calif, Keck Sch Med, Dept Biochem & Mol Med, Los Angeles, CA 90007 USA

来源：

EUROPEAN RADIOLOGY | 2022年 / 32卷 / 04期

关键词：

Carcinoma; Renal cell; Neoplasm grading; Neoplasm staging; radiomics; Machine learning; SYSTEM; SOCIETY; MODEL;

D O I：

10.1007/s00330-021-08344-4

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

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. Summary statement 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.

引用

页码：2552 / 2563

页数：12

共 51 条

[1] The Potential of Radiomic-Based Phenotyping in PrecisionMedicine A Review [J].