Literature DB >> 31822969

Texture analysis and machine learning algorithms accurately predict histologic grade in small (< 4 cm) clear cell renal cell carcinomas: a pilot study.

Shawn Haji-Momenian1, Zixian Lin2, Bhumi Patel3, Nicole Law3, Adam Michalak4, Anishsanjay Nayak2, James Earls3, Murray Loew2.   

Abstract

PURPOSE: To predict the histologic grade of small clear cell renal cell carcinomas (ccRCCs) using texture analysis and machine learning algorithms.
METHODS: Fifty-two noncontrast (NC), 26 corticomedullary (CM) phase, and 35 nephrographic (NG) phase CTs of small (< 4 cm) surgically resected ccRCCs were retrospectively identified. Surgical pathology classified the tumors as low- or high-Fuhrman histologic grade. The axial image with the largest cross-sectional tumor area was exported and segmented. Six histogram and 31 texture (gray-level co-occurrences (GLC) and gray-level run-lengths (GLRL)) features were calculated for each tumor in each phase. T testing compared feature values in low- and high-grade ccRCCs, with a (Benjamini-Hochberg) false discovery rate of 10%. Area under the receiver operating curve (AUC) was calculated for each feature to assess prediction of low- and high-grade ccRCCs in each phase. Histogram, texture, and combined histogram and texture data sets were used to train and test four algorithms (k-nearest neighbor (KNN), support vector machine (SVM), random forests, and decision tree) with tenfold cross-validation; AUCs were calculated for each algorithm in each phase to assess prediction of low- and high-grade ccRCCs.
RESULTS: Zero, 23, and 0 features in the NC, CM, and NG phases had statistically significant differences between low and high-grade ccRCCs. CM histogram skewness and GLRL short run emphasis had the highest AUCs (0.82) in predicting histologic grade. All four algorithms had the highest AUCs (0.97) predicting histologic grade using CM histogram features. The algorithms' AUCs decreased using histogram or texture features from NC or NG phases.
CONCLUSION: The histologic grade of small ccRCCs can be accurately predicted with machine learning algorithms using CM histogram features, which outperform NC and NG phase image data.

Entities:  

Keywords:  Clear cell renal cell carcinoma; Histology; Machine learning; Texture

Mesh:

Year:  2020        PMID: 31822969     DOI: 10.1007/s00261-019-02336-1

Source DB:  PubMed          Journal:  Abdom Radiol (NY)


  36 in total

1.  Prognostic ability of simplified nuclear grading of renal cell carcinoma.

Authors:  Nathalie Rioux-Leclercq; Pierre I Karakiewicz; Quoc-Dien Trinh; Vincenzo Ficarra; Luca Cindolo; Alexandre de la Taille; Jacques Tostain; Richard Zigeuner; Arnaud Mejean; Jean-Jacques Patard
Journal:  Cancer       Date:  2007-03-01       Impact factor: 6.860

2.  Metastatic potential in renal cell carcinomas ≤7 cm: Swedish Kidney Cancer Quality Register data.

Authors:  Eirikur Guðmundsson; Henrik Hellborg; Sven Lundstam; Stina Erikson; Börje Ljungberg
Journal:  Eur Urol       Date:  2011-07-01       Impact factor: 20.096

3.  Renal Mass and Localized Renal Cancer: AUA Guideline.

Authors:  Steven Campbell; Robert G Uzzo; Mohamad E Allaf; Eric B Bass; Jeffrey A Cadeddu; Anthony Chang; Peter E Clark; Brian J Davis; Ithaar H Derweesh; Leo Giambarresi; Debra A Gervais; Susie L Hu; Brian R Lane; Bradley C Leibovich; Philip M Pierorazio
Journal:  J Urol       Date:  2017-05-04       Impact factor: 7.450

4.  Improved prognostication of renal cell carcinoma using an integrated staging system.

Authors:  A Zisman; A J Pantuck; F Dorey; J W Said; O Shvarts; D Quintana; B J Gitlitz; J B deKernion; R A Figlin; A S Belldegrun
Journal:  J Clin Oncol       Date:  2001-03-15       Impact factor: 44.544

5.  Rising incidence of small renal masses: a need to reassess treatment effect.

Authors:  John M Hollingsworth; David C Miller; Stephanie Daignault; Brent K Hollenbeck
Journal:  J Natl Cancer Inst       Date:  2006-09-20       Impact factor: 13.506

6.  Prognostic value of renal cell carcinoma nuclear grading: multivariate analysis of 333 cases.

Authors:  V Ficarra; R Righetti; G Martignoni; A D'Amico; S Pilloni; E Rubilotta; G Malossini; G Mobilio
Journal:  Urol Int       Date:  2001       Impact factor: 2.089

Review 7.  Increased incidence of serendipitously discovered renal cell carcinoma.

Authors:  M Jayson; H Sanders
Journal:  Urology       Date:  1998-02       Impact factor: 2.649

8.  The evolving presentation of renal carcinoma in the United States: trends from the Surveillance, Epidemiology, and End Results program.

Authors:  Mike M Nguyen; Inderbir S Gill; Lars M Ellison
Journal:  J Urol       Date:  2006-12       Impact factor: 7.450

9.  Decreasing size at diagnosis of stage 1 renal cell carcinoma: analysis from the National Cancer Data Base, 1993 to 2004.

Authors:  Matthew R Cooperberg; Katherine Mallin; Jamie Ritchey; Jacqueline D Villalta; Peter R Carroll; Christopher J Kane
Journal:  J Urol       Date:  2008-06       Impact factor: 7.450

10.  Prognostic significance of morphologic parameters in renal cell carcinoma.

Authors:  S A Fuhrman; L C Lasky; C Limas
Journal:  Am J Surg Pathol       Date:  1982-10       Impact factor: 6.394

View more
  2 in total

1.  Accuracy of CT texture analysis for differentiating low-grade and high-grade renal cell carcinoma: systematic review and meta-analysis.

Authors:  Wei Yu; Gao Liang; Lichuan Zeng; Yang Yang; Yinghua Wu
Journal:  BMJ Open       Date:  2021-12-22       Impact factor: 2.692

2.  A CT-Based Radiomics Approach for the Differential Diagnosis of Sarcomatoid and Clear Cell Renal Cell Carcinoma.

Authors:  Xiaoli Meng; Jun Shu; Yuwei Xia; Ruwu Yang
Journal:  Biomed Res Int       Date:  2020-07-24       Impact factor: 3.411

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.