Differentiating kidney stones from phleboliths in unenhanced low-dose computed tomography using radiomics and machine learning

• Published in: European radiology Vol. 29; no. 9; pp. 4776 - 4782
• Main Authors: De Perrot, Thomas, Hofmeister, Jeremy, Burgermeister, Simon, Martin, Steve P., Feutry, Gregoire, Klein, Jacques, Montet, Xavier
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2019; Springer Nature B.V
• Subjects: Accuracy; Acute Pain - etiology; Adult; Aged; Aged, 80 and over; Algorithms; Artificial intelligence; Calcification; Calculi; Classification; Colic; Computed tomography; Diagnosis, Differential; Diagnostic Radiology; Diagnostic software; Diagnostic systems; Feature extraction; Female; Flank Pain - etiology; Humans; Imaging; Imaging Informatics and Artificial Intelligence; Internal Medicine; Interventional Radiology; Kidney Calculi - diagnostic imaging; Kidney stones; Kidneys; Learning algorithms; Lithiasis - diagnostic imaging; Machine Learning; Male; Medicine; Medicine & Public Health; Middle Aged; Nephrolithiasis; Neuroradiology; Pain; Patients; Permutations; Radiology; Radiomics; Segmentation; Tomography, X-Ray Computed - methods; Ultrasound; Young Adult; Lithiasis; Urinary tract; Artificial intelligence; Machine learning
• ISSN: 0938-7994; 1432-1084
• DOI: 10.1007/s00330-019-6004-7

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.