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

De Perrot, Thomas Benoît; Hofmeister, Jérémy; Burgermeister, Simon; Martin, Steve Philippe; Feutry, Grégoire; Klein, Jacques; Montet, Xavier Cédric Rodolphe

doi:10.1007/s00330-019-6004-7

Professional article

English

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

ContributorsDe Perrot, Thomas Benoît; Hofmeister, Jérémy

; Burgermeister, Simon; Martin, Steve Philippe; Feutry, Grégoire; Klein, Jacques; Montet, Xavier Cédric Rodolphe

Published inEuropean Radiology, vol. 29, no. 9, p. 4776-4782

Publication date2019

Abstract

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.

Keywords

Acute Pain/etiology
Adult
Aged
Aged
80 and over
Algorithms
Diagnosis
Differential
Female
Flank Pain/etiology
Humans
Kidney Calculi/diagnostic imaging
Lithiasis/diagnostic imaging
Machine Learning
Male
Middle Aged
Tomography
X-Ray Computed/methods
Young Adult

Affiliation

Research group

Citation (ISO format)

DE PERROT, Thomas Benoît et al. Differentiating kidney stones from phleboliths in unenhanced low-dose computed tomography using radiomics and machine learning. In: European Radiology, 2019, vol. 29, n° 9, p. 4776–4782. doi: 10.1007/s00330-019-6004-7

Article (Published version)

Identifiers

PID : unige:146623
DOI : 10.1007/s00330-019-6004-7
PMID : 30747299

ISSN of the journal0938-7994

191views

0downloads

Creation12/17/2020 10:06:00 AM

First validation12/17/2020 10:06:00 AM

Update time03/15/2023 11:44:24 PM

Status update03/15/2023 11:44:23 PM

Last indexation01/17/2024 11:59:42 AM

Archive ouverte UNIGE

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

Technical informations