Does Deep Learning Vascular Segmentation on CTA Improve Vertebral Artery Dissection Detection?
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Purpose
The aims of this study were to develop an externally validated deep learning vascular segmentation model for digital enhancement of vertebral artery dissection detection on CTA and to assess clinical utility of the model through a paired crossover reader study.
Materials and Methods
This retrospective, IRB-approved study conducted from September 2024 to July 2026 included an internal training cohort of 84 manually segmented CTAs plus 17 CTAs from the RSNA Intracranial Aneurysm Challenge (101 CTAs total) and an external testing cohort of 40 CTAs (22 positive, 18 negative for vertebral artery dissection). A nnU-Net (version 2) model was trained using five-fold cross-validation with the entire training cohort. Technical performance was evaluated using the Dice similarity coefficient (DSC). A two-part crossover reader study included 10 readers who assessed diagnostic accuracy, confidence, and interpretation time with and without segmentation-based augmentation. Statistical analyses included McNemar’s exact test (accuracy) and Wilcoxon signed-rank test (confidence, time), with P < .05 considered significant.
Results
The model achieved a DSC of 0.96 ± 0.01. In the reader study, diagnostic accuracy was lower with augmentation than without (0.72 vs 0.84, P < 0.001), while confidence (3.98 vs 3.96, P = .77) and interpretation time (137.3 vs 166.7 seconds, P = .54) did not differ significantly. Subjectively, 7 of 10 readers reported they would use the tool routinely in acute or trauma settings.
Conclusion
Although the deep learning model demonstrated accurate segmentation of vascular structures, further validation is needed to establish its utility for enabling accurate diagnosis of VAD in fast-paced clinical settings.
Key Points
- A deep learning vascular segmentation model trained for Vertebral Artery Dissection achieved a Dice similarity coefficient of 0.96 ± 0.01 on external data.
- Diagnostic accuracy on a follow-up reader study was significantly lower on CTA from the segmentation model compared to conventional CTA (0.72 vs 0.84, p < 0.001).
- Seven out of ten radiology trainees and attendings reported they would routinely use digitally enhanced CTA in acute or trauma settings.
Summary Statement
On direct comparison between conventional CTA and CTA enhanced with deep learning vascular segmentation, radiology trainees and attendings were significantly more accurate at diagnosing vertebral artery dissection on conventional CTA, with no significant difference in interpretation time or confidence.
