Literature DB >> 25906183

Can Quantitative CT Texture Analysis be Used to Differentiate Fat-poor Renal Angiomyolipoma from Renal Cell Carcinoma on Unenhanced CT Images?

Taryn Hodgdon1, Matthew D F McInnes1, Nicola Schieda1, Trevor A Flood1, Leslie Lamb1, Rebecca E Thornhill1.   

Abstract

PURPOSE: To determine the accuracy of texture analysis to differentiate fat-poor angiomyolipoma (fp-AML) from renal cell carcinoma (RCC) on unenhanced computed tomography (CT) images.
MATERIALS AND METHODS: In this institutional review board-approved retrospective case-control study, patients with AML and RCC were identified from the pathology database: there were 16 patients with fp-AML (no visible fat at unenhanced CT) and 84 patients with RCC. Axial unenhanced CT images were contoured manually by two independent analysts. Texture analysis was performed for each lesion, and reproducibility was assessed. Texture features related to the gray-level histogram, gray-level co-occurrence, and run-length matrix statistics were evaluated. The most discriminative features were used to generate support vector machine (SVM) classifiers. Diagnostic accuracy of textural features was assessed and 10-fold cross validation was performed. Unenhanced CT images for each patient were independently reviewed by two blinded radiologists who subjectively graded lesion heterogeneity on a five-point scale. Differences in area under the receiver operating characteristic curve (AUC) between subjective heterogeneity ratings and textural features were evaluated by using the DeLong method.
RESULTS: There was lower lesion homogeneity and higher lesion entropy in RCCs (P ≤ .01). A model incorporating several texture features resulted in an AUC of 0.89 ± 0.04. The average SVM accuracy of textural features ranged from 83% to 91% (after 10-fold cross validation). An optimal subjective heterogeneity rating of 2 or higher was identified as a predictor of RCC for both readers, with no significant difference in AUC between readers (P = .06). Each of the three textural-based classifiers was more accurate than either radiologists' subjective heterogeneity ratings for the models incorporating a subset of the top three textural features (difference in AUC between textural features and subjective visual heterogeneity, 0.25; 95% confidence interval: 0.02, 0.47; P = .03).
CONCLUSION: CT texture analysis can be used to accurately differentiate fp-AML from RCC on unenhanced CT images.

Entities:  

Mesh:

Year:  2015        PMID: 25906183     DOI: 10.1148/radiol.2015142215

Source DB:  PubMed          Journal:  Radiology        ISSN: 0033-8419            Impact factor:   11.105


  81 in total

Review 1.  Renal angiomyolipoma without visible fat: Can we make the diagnosis using CT and MRI?

Authors:  Robert S Lim; Trevor A Flood; Matthew D F McInnes; Luke T Lavallee; Nicola Schieda
Journal:  Eur Radiol       Date:  2017-08-04       Impact factor: 5.315

2.  Point Shear Wave Elastography Using Machine Learning to Differentiate Renal Cell Carcinoma and Angiomyolipoma.

Authors:  Hersh Sagreiya; Alireza Akhbardeh; Dandan Li; Rosa Sigrist; Benjamin I Chung; Geoffrey A Sonn; Lu Tian; Daniel L Rubin; Jürgen K Willmann
Journal:  Ultrasound Med Biol       Date:  2019-05-25       Impact factor: 2.998

3.  Differentiating solid, non-macroscopic fat containing, enhancing renal masses using fast Fourier transform analysis of multiphase CT.

Authors:  Bino A Varghese; Frank Chen; Darryl H Hwang; Steven Y Cen; Inderbir S Gill; Vinay A Duddalwar
Journal:  Br J Radiol       Date:  2018-06-21       Impact factor: 3.039

4.  Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas.

Authors:  Burak Kocak; Ece Ates; Emine Sebnem Durmaz; Melis Baykara Ulusan; Ozgur Kilickesmez
Journal:  Eur Radiol       Date:  2019-02-12       Impact factor: 5.315

5.  Angiomyolipoma (AML) without visible fat: Ultrasound, CT and MR imaging features with pathological correlation.

Authors:  Shaheed W Hakim; Nicola Schieda; Taryn Hodgdon; Matthew D F McInnes; Marc Dilauro; Trevor A Flood
Journal:  Eur Radiol       Date:  2015-06-03       Impact factor: 5.315

6.  Machine learning-based texture analysis for differentiation of radiologically indeterminate small adrenal tumors on adrenal protocol CT scans.

Authors:  Ahmed W Moawad; Ayahallah Ahmed; David T Fuentes; John D Hazle; Mouhammed A Habra; Khaled M Elsayes
Journal:  Abdom Radiol (NY)       Date:  2021-06-03

7.  Quantitative Assessment of Variation in CT Parameters on Texture Features: Pilot Study Using a Nonanatomic Phantom.

Authors:  K Buch; B Li; M M Qureshi; H Kuno; S W Anderson; O Sakai
Journal:  AJNR Am J Neuroradiol       Date:  2017-03-24       Impact factor: 3.825

8.  Spontaneous rupture of angiomyolipoma of the kidney.

Authors:  Friedrich C Prischl; Peter Spöttl
Journal:  Wien Klin Wochenschr       Date:  2017-02-10       Impact factor: 1.704

9.  CT texture analysis of pancreatic cancer.

Authors:  Kumar Sandrasegaran; Yuning Lin; Michael Asare-Sawiri; Tai Taiyini; Mark Tann
Journal:  Eur Radiol       Date:  2018-08-16       Impact factor: 5.315

10.  Radiomics of small renal masses on multiphasic CT: accuracy of machine learning-based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat.

Authors:  Ruimeng Yang; Jialiang Wu; Lei Sun; Shengsheng Lai; Yikai Xu; Xilong Liu; Ying Ma; Xin Zhen
Journal:  Eur Radiol       Date:  2019-08-29       Impact factor: 5.315

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.