Deep learning versus radiologists for acute aortic dissection on CT: A systematic review and network meta-analysis
In brief
AI reads CT scans for aortic dissection with 90% accuracy, beats radiologists
A systematic review of 23 studies found deep-learning algorithms identified acute aortic dissection on non-contrast CT with roughly 91% sensitivity and 90% specificity, and performed better than radiologists in head-to-head tests. The evidence is low-certainty, derived mainly from case-control data, so prospective trials are needed before clinical adoption.
- Journal
- European journal of radiology (Q1)
- Published
- 25 August 2026
- Study design
- Systematic review of cohort studies
- Evidence level
- Level 2, Moderate (CEBM 2a)
- Authors
- Ting-Wei Wang, Jia-Sheng Hong, Ho-Ren Liu, Kuan-Ting Wu, Hao-Neng Fu, Yung-Tsai Lee, et al.
- PMID
- 42679415
- DOI
- 10.1016/j.ejrad.2026.113189
Why clinicians should know about it
- Picked for Radiology, Radiation Oncology, Nuclear Medicine, Medical Physics and Imaging (paper of the day, 3 September 2026): DL vs radiologists for acute aortic dissection detection on CT
Abstract
Acute aortic dissection (AAD) is a time-sensitive cardiovascular emergency in which delayed recognition remains associated with poor early outcomes, and deep learning (DL) applied to computed tomography (CT) is increasingly proposed for triage support. We synthesized DL detection accuracy on CT, compared DL with radiologists head-to-head, and secondarily pooled CT segmentation accuracy. This Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compliant review searched PubMed, Embase, and Web of Science through February 18, 2026. Detection studies were pooled with bivariate random-effects models; head-to-head comparisons were synthesized with contrast-based network meta-analysis; segmentation Sørensen-Dice coefficients were analyzed with three-level random-effects models. Twenty-three studies were included. For non-contrast CT detection (10 studies; 18 cohorts; 54 algorithm-cohort datasets), pooled sensitivity was 0.91 (95 % confidence interval [CI], 0.87-0.94) and specificity 0.90 (95 % CI, 0.85-0.94). In direct comparisons (5 studies; 11 comparisons), radiologist-to-DL relative sensitivity was 0.72 (95 % CI, 0.57-0.91) and relative specificity 0.88 (95 % CI, 0.83-0.93). For the secondary segmentation synthesis (16 studies; 88 datasets), pooled Dice was 0.863 (95 % CI, 0.795-0.931), lower for true- and false-lumen than for whole-aorta delineation. DL showed encouraging detection accuracy and higher sensitivity and specificity than the radiologist comparators in five head-to-head studies read under experimental conditions, supporting assistive triage rather than replacement; lumen-level segmentation remains more challenging than whole-aorta contouring. Certainty was low - datasets were predominantly case-control with a median prevalence of 50 %, heterogeneity was substantial and small-study effects pronounced - so these estimates are experimental upper bounds requiring prospective confirmation.
Abstract as published, via PubMed.
For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.