Differentiating kidney stones from phleboliths in unenhanced low-dose computed tomography using radiomics and machine learning
Abstract
Objectives
Distinguishing between kidney stones and phleboliths can constitute a diagnostic challenge in patients undergoing unenhanced low-dose CT (LDCT) for acute flank pain. We sought to investigate the accuracy of radiomics and a machine-learning classifier in differentiating between kidney stones and phleboliths on LDCT.
Methods
Radiomics features were extracted following a semi-automatic segmentation of kidney stones and phleboliths for two independent consecutive cohorts of patients undergoing LDCT for acute flank pain.
Radiomics features from the first cohort of patients (n = 369) were ultimately used to train a machine-learning model designed to distinguish kidney stones (n = 211) from phleboliths (n = 201). Classification performance was assessed on the second independent cohort (i.e., testing set) (kidney stones n = 24; phleboliths n = 23) using positive and negative predictive values (PPV and NPV), area under the receiver operating curves (AUC), and permutation testing.
Results
Our machine-learning classification model trained on radiomics features achieved an overall accuracy of 85.1% on the independent testing set, with an AUC of 0.902, PPV of 81.5%, and NPV of 90.0%. Classification accuracy was significantly better than chance on permutation testing (p < 0.05, permutation p value).
Conclusion
Radiomics and machine learning enable accurate differentiation between kidney stones and phleboliths on LDCT in patients presenting with acute flank pain.
Key Points
• Combining a machine-learning algorithm with radiomics features extracted for abdominopelvic calcification on LDCT offers a highly accurate method for discriminating phleboliths from kidney stones.
• Our radiomics and machine-learning model proved robust for CT acquisition and reconstruction protocol when tested in comparison with an external independent cohort of patients with acute flank pain.
• The high performance of the radiomics-based automatic classification model in differentiating phleboliths from kidney stones indicates its potential as a future diagnostic tool for equivocal abdominopelvic calcifications in the setting of suspected renal colic.
Keywords
Urinary tract Lithiasis Machine learning Artificial intelligenceAbbreviations
- AUC
Area under the curve
- CV
Cross-validation
- LDCT
Low-dose computed tomography
- PCA
Principal component analysis
- ROC
Receiver operating characteristics curve
- VOI
Volume of interest
Notes
Compliance with ethical standards
Guarantor
The scientific guarantor of this publication is Prof. Xavier Montet.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise.
Informed consent
Written informed consent was waived by the Institutional Review Board.
Ethical approval
Institutional Review Board approval was obtained.
Methodology
• retrospective
• experimental
• performed at one institution
References
- 1.Ziemba JB, Matlaga BR (2017) Epidemiology and economics of nephrolithiasis. Investig Clin Urol 58:299–306CrossRefGoogle Scholar
- 2.Poletti PA, Platon A, Rutschmann OT, Schmidlin FR, Iselin CE, Becker CD (2007) Low-dose versus standard-dose CT protocol in patients with clinically suspected renal colic. AJR Am J Roentgenol 188:927–933CrossRefGoogle Scholar
- 3.Luk AC, Cleaveland P, Olson L, Neilson D, Srirangam SJ (2017) Pelvic phlebolith: a trivial pursuit for the urologist? J Endourol 31:342–347CrossRefGoogle Scholar
- 4.Traubici J, Neitlich JD, Smith RC (1999) Distinguishing pelvic phleboliths from distal ureteral stones on routine unenhanced helical CT: is there a radiolucent center? AJR Am J Roentgenol 172:13–17CrossRefGoogle Scholar
- 5.Humphry GM (1896) Urinary calculi: their formation and structure. J Anat Physiol 30:296–311PubMedPubMedCentralGoogle Scholar
- 6.Williams JC Jr, McAteer JA, Evan AP, Lingeman JE (2010) Micro-computed tomography for analysis of urinary calculi. Urol Res 38:477–484CrossRefGoogle Scholar
- 7.Prien EL, Prien EL Jr (1968) Composition and structure of urinary stone. Am J Med 45:654–672CrossRefGoogle Scholar
- 8.Summers RM (2016) Texture analysis in radiology: does the emperor have no clothes? Abdom Radiol (NY). https://doi.org/10.1007/s00261-016-0950-1
- 9.Parekh V, Jacobs MA (2016) Radiomics: a new application from established techniques. Expert Rev Precis Med Drug Dev 1:207–226CrossRefGoogle Scholar
- 10.Larue RT, Defraene G, De Ruysscher D, Lambin P, van Elmpt W (2017) Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures. Br J Radiol 90:20160665CrossRefGoogle Scholar
- 11.Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006CrossRefGoogle Scholar
- 12.Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3:610–621Google Scholar
- 13.van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107CrossRefGoogle Scholar
- 14.Cawley GC, Talbot NLC (2010) On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res 11:2079–2107Google Scholar
- 15.Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830Google Scholar
- 16.Kim JC (2001) Central lucency of pelvic phleboliths: comparison of radiographs and noncontrast helical CT. Clin Imaging 25:122–125CrossRefGoogle Scholar
- 17.Williams JC Jr, Lingeman JE, Coe FL, Worcester EM, Evan AP (2015) Micro-CT imaging of Randall’s plaques. Urolithiasis 43(Suppl 1):13–17CrossRefGoogle Scholar
- 18.Zarse CA, McAteer JA, Tann M et al (2004) Helical computed tomography accurately reports urinary stone composition using attenuation values: in vitro verification using high-resolution micro-computed tomography calibrated to fourier transform infrared microspectroscopy. Urology 63:828–833CrossRefGoogle Scholar
- 19.Boridy IC, Nikolaidis P, Kawashima A, Goldman SM, Sandler CM (1999) Ureterolithiasis: value of the tail sign in differentiating phleboliths from ureteral calculi at nonenhanced helical CT. Radiology 211:619–621CrossRefGoogle Scholar
- 20.Heneghan JP, Dalrymple NC, Verga M, Rosenfield AT, Smith RC (1997) Soft-tissue “rim” sign in the diagnosis of ureteral calculi with use of unenhanced helical CT. Radiology 202:709–711CrossRefGoogle Scholar
- 21.Beig N, Patel J, Prasanna P et al (2018) Radiogenomic analysis of hypoxia pathway is predictive of overall survival in glioblastoma. Sci Rep 8(7)Google Scholar
- 22.Thawani R, McLane M, Beig N et al (2018) Radiomics and radiogenomics in lung cancer: a review for the clinician. Lung Cancer 115:34–41CrossRefGoogle Scholar
- 23.Zhao B, Tan Y, Tsai WY et al (2016) Reproducibility of radiomics for deciphering tumor phenotype with imaging. Sci Rep 6:23428CrossRefGoogle Scholar
- 24.Parmar C, Rios Velazquez E, Leijenaar R et al (2014) Robust Radiomics feature quantification using semiautomatic volumetric segmentation. PLoS One 9:e102107CrossRefGoogle Scholar
- 25.Incoronato M, Aiello M, Infante T et al (2017) Radiogenomic analysis of oncological data: a technical survey. Int J Mol Sci 18Google Scholar