Literature DB >> 35723716

Differentiation of benign from malignant solid renal lesions with MRI-based radiomics and machine learning.

Ruben Ngnitewe Massa'a1, Elizabeth M Stoeckl1, Meghan G Lubner1, David Smith1, Lu Mao2, Daniel D Shapiro3, E Jason Abel3, Andrew L Wentland4,5,6.   

Abstract

BACKGROUND: Solid renal masses are often indeterminate for benignity versus malignancy on magnetic resonance imaging. Such masses are typically evaluated with either percutaneous biopsy or surgical resection. Percutaneous biopsy can be non-diagnostic and some surgically resected lesions are inadvertently benign.
PURPOSE: To assess the performance of ten machine learning (ML) algorithms trained with MRI-based radiomics features in distinguishing benign from malignant solid renal masses.
METHODS: Patients with solid renal masses identified on pre-intervention MRI were curated from our institutional database. Masses with a definitive diagnosis via imaging (for angiomyolipomas) or via biopsy or surgical resection (for oncocytomas or renal cell carcinomas) were selected. Each mass was segmented for both T2- and post-contrast T1-weighted images. Radiomics features were derived from the segmented masses for each imaging sequence. Ten ML algorithms were trained with the radiomics features gleaned from each MR sequence, as well as the combination of MR sequences.
RESULTS: In total, 182 renal masses in 160 patients were included in the study. The support vector machine algorithm trained on radiomics features from T2-weighted images performed superiorly, with an accuracy of 0.80 and an area under the curve (AUC) of 0.79. Linear discriminant analysis (accuracy = 0.84 and AUC = 0.77) and logistic regression (accuracy = 0.78 and AUC = 0.78) algorithms trained on T2-based radiomics features performed similarly. ML algorithms trained on radiomics features from post-contrast T1-weighted images or the combination of radiomics features from T2- and post-contrast T1-weighted images yielded lower performance.
CONCLUSION: Machine learning models trained with radiomics features derived from T2-weighted images can provide high accuracy for distinguishing benign from malignant solid renal masses. CLINICAL IMPACT: Machine learning models derived from MRI-based radiomics features may improve the clinical management of solid renal masses and have the potential to reduce the frequency with which benign solid renal masses are biopsied or surgically resected.
© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Entities:  

Keywords:  Artificial intelligence; Machine learning; Magnetic resonance imaging; Radiomics; Renal cell carcinoma; Solid renal masses

Mesh:

Year:  2022        PMID: 35723716     DOI: 10.1007/s00261-022-03577-3

Source DB:  PubMed          Journal:  Abdom Radiol (NY)


  17 in total

Review 1.  Contemporary approach to the classification of renal epithelial tumors.

Authors:  V E Reuter; J C Presti
Journal:  Semin Oncol       Date:  2000-04       Impact factor: 4.929

Review 2.  Update on the epidemiology and biology of renal cortical neoplasms.

Authors:  Sean Collins; James McKiernan; Jaime Landman
Journal:  J Endourol       Date:  2006-12       Impact factor: 2.942

3.  Guideline for management of the clinical T1 renal mass.

Authors:  Steven C Campbell; Andrew C Novick; Arie Belldegrun; Michael L Blute; George K Chow; Ithaar H Derweesh; Martha M Faraday; Jihad H Kaouk; Raymond J Leveillee; Surena F Matin; Paul Russo; Robert G Uzzo
Journal:  J Urol       Date:  2009-08-14       Impact factor: 7.450

Review 4.  Solid renal masses: what the numbers tell us.

Authors:  Stella K Kang; William C Huang; Pari V Pandharipande; Hersh Chandarana
Journal:  AJR Am J Roentgenol       Date:  2014-06       Impact factor: 3.959

Review 5.  Radiomics in Kidney Cancer: MR Imaging.

Authors:  Alberto Diaz de Leon; Payal Kapur; Ivan Pedrosa
Journal:  Magn Reson Imaging Clin N Am       Date:  2019-02       Impact factor: 2.266

6.  The use of opposed-phase chemical shift MRI in the diagnosis of renal angiomyolipomas.

Authors:  Gary M Israel; Nicole Hindman; Elizabeth Hecht; Glenn Krinsky
Journal:  AJR Am J Roentgenol       Date:  2005-06       Impact factor: 3.959

7.  Diagnostic Performance and Interreader Agreement of a Standardized MR Imaging Approach in the Prediction of Small Renal Mass Histology.

Authors:  Fernando U Kay; Noah E Canvasser; Yin Xi; Daniella F Pinho; Daniel N Costa; Alberto Diaz de Leon; Gaurav Khatri; John R Leyendecker; Takeshi Yokoo; Aaron H Lay; Nicholas Kavoussi; Ersin Koseoglu; Jeffrey A Cadeddu; Ivan Pedrosa
Journal:  Radiology       Date:  2018-02-01       Impact factor: 11.105

8.  Tumor size is associated with malignant potential in renal cell carcinoma cases.

Authors:  R Houston Thompson; Jordan M Kurta; Matthew Kaag; Satish K Tickoo; Shilajit Kundu; Darren Katz; Lucas Nogueira; Victor E Reuter; Paul Russo
Journal:  J Urol       Date:  2009-03-14       Impact factor: 7.450

9.  Characterization of solid renal neoplasms using MRI-based quantitative radiomics features.

Authors:  Daniela Said; Stefanie J Hectors; Eric Wilck; Ally Rosen; Daniel Stocker; Octavia Bane; Alp Tuna Beksaç; Sara Lewis; Ketan Badani; Bachir Taouli
Journal:  Abdom Radiol (NY)       Date:  2020-09

Review 10.  Preoperatively misclassified, surgically removed benign renal masses: a systematic review of surgical series and United States population level burden estimate.

Authors:  David C Johnson; Josip Vukina; Angela B Smith; Anne-Marie Meyer; Stephanie B Wheeler; Tzy-Mey Kuo; Hung-Jui Tan; Michael E Woods; Mathew C Raynor; Eric M Wallen; Raj S Pruthi; Matthew E Nielsen
Journal:  J Urol       Date:  2014-07-27       Impact factor: 7.450

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.