Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1725
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-17T18:13:33.009792Z
status: published
lens: g_space
sector: health
headline: UroVision: a new artificial intelligence software for functional magnetic resonance urography evaluation in children with congenital anomalies of the kidney and urinary tract
dek: Objectives This study compared UroVision, a novel AI-based tool for automated three-dimensional (3D) segmentation and magnetic resonance urography (MRU) functional analysis, with the validated ImageJ MRU software, focusing on split renal function (SRF) and drainage curve classification in children with congenital anomalies of the kidney and urinary tract (CAKUT). Materials and methods MRU examinations in children with CAKUT were retrospectively analysed using UroVision and ImageJ MRU. UroVision functional assess…
gain_title: In a retrospective set of 100 kidneys, an AI tool for automated MRU analysis produced results comparable to the validated ImageJ MRU software, with excellent reproducibility between and within readers.
problem_title: (none)
trace_subject: (none)
gain_reading: In a retrospective set of 100 kidneys, an AI tool for automated MRU analysis produced results comparable to the validated ImageJ MRU software, with excellent reproducibility between and within readers.
gain_evidence: UroVision showed excellent agreement with ImageJ MRU | Inter-reader and intra-reader reproducibility were excellent | Full 3D analysis enabled reclassification of borderline curves in 16 out of 23 kidneys
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers compared UroVision, an AI tool that automatically segments kidneys in three dimensions and analyses functional magnetic resonance urography, with the validated ImageJ MRU software. They retrospectively studied scans from 50 children with congenital anomalies of the kidney and urinary tract, giving 100 kidneys, and two paediatric radiologists performed the evaluations independently.

Automated, reproducible analysis could make functional kidney imaging in children less dependent on the operator and more standardised. The evidence comes from a retrospective comparison against an existing software, not from a trial of patient outcomes, so the effect on clinical care remains unproven.
limitation: The study was retrospective and small (50 patients), and the functional parameters showed only moderate correlation with the reference software, so agreement was not uniformly strong.
tag: Evidence-backed gain
key_points: Renal volume correlation between UroVision and ImageJ MRU was high (r = 0.99). | Functional parameters correlated only moderately: glomerular slope r = 0.63 and Patlak coefficient r = 0.57. | Drainage curve classification agreement was high, with a weighted kappa of 0.86. | Full 3D analysis allowed borderline drainage curves to be reclassified in 16 of 23 kidneys.
rundown: The cohort had 28 males and 22 females, with a mean age of 2.4 years and a range of 0 to 18 years. Agreement was tested with Pearson correlation, linear regression, Bland-Altman analysis and intraclass correlation coefficients.

For comparability with the ImageJ MRU workflow, UroVision functional assessment was limited to the two-dimensional slice showing the most renal parenchyma. Drainage curve morphology was evaluated by an expert paediatric radiologist, with inter-method agreement measured by weighted Cohen's kappa.

Inter-reader intraclass correlation coefficients ranged from 0.87 to 1.00 and intra-reader from 0.89 to 0.99. The authors conclude that the tool offers automated analysis and improved reproducibility, with minimal bias in the Bland-Altman analysis.
sources:
- peer_reviewed | European Radiology | https://doi.org/10.1007/s00330-026-12950-5 | 2026-10-08
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

1593c5e360d938ac56a3d16e40ad21aa6f15d3c145abe176ecfd14f2297c49cb

previous

0000000000000000000000000000000000000000000000000000000000000000