AI Science Tracker
EN

Department of Cardiovascular Surgery, Beijing Anzhen Hospital, Capital Medical University, China

1 discovery from 2024

Discoveries

A deep learning algorithm for the detection of aortic dissection on non-contrast-enhanced computed tomography via the identification and segmentation of the true and false lumens of the aorta.

Source check: Source checked. Not independent scientific confirmation.

Finding: A 3D U-Net segmented aortic lumens on non-contrast CT and detected dissection using a false-lumen volume threshold. In a retrospective three-center study, external testing reported 92.7% accuracy, 90.3% sensitivity and 94.3% specificity; the study did not test patient outcomes.

Technology: A 3D full-resolution U-Net segmented true and false aortic lumens; false-lumen volume was used for dissection detection.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
The segmentation and detection model enabled a specific external-center diagnostic performance result on non-contrast CT.
Test and result
External testing reported 92.7% accuracy, 90.3% sensitivity and 94.3% specificity for dissection detection on non-contrast CT.
Limitation / still unknown
Retrospective three-center study with 256 patients in development/internal testing and 64 in external testing; clinical outcome impact was not evaluated.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11485366/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary full-text Methods and Results in PMC and the publisher record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.