Performance of Deep Learning Reconstruction for Detection of Early Ischemic Changes in NCCT: Comparison with ASIR-V in Acute Stroke.
Authors
Affiliations (5)
Affiliations (5)
- Department of General Radiology, Interventional Radiology and Neuroradiology, Wroclaw Medical University Hospital, Wrocław, Poland. [email protected].
- Department of General Radiology, Interventional Radiology and Neuroradiology, Wroclaw Medical University Hospital, Wrocław, Poland.
- Emergency Medicine Center, Lower Silesian Specialist Hospital T. Marciniak, Wrocław, Poland.
- Hetalox sp. z o.o., Wrocław, Poland.
- Department of General Radiology, Interventional Radiology and Neuroradiology, Wroclaw Medical University, Wrocław, Poland.
Abstract
Evaluation of the impact of Deep Learning Image Reconstruction (DLIR) compared to Adaptive Statistical Iterative Reconstruction-Veo (ASIR-V) on image quality and early ischemic changes detection on non-contrast computed tomography (NCCT) in stroke suspected patients. A secondary objective was to determine the potential influence of reconstruction algorithm on ASPECT scoring relative to automated e-ASPECT score. Consecutive patients undergoing NCCT within 6 hours of symptom onset were retrospectively included. Images were reconstructed using ASIR-V and high-strength DLIR. Four readers with varying experience independently assessed subjective image quality, gray-white matter differentiation, diagnostic confidence, presence of ischemic lesions and ASPECTS scoring. Diagnostic performance (accuracy, sensitivity, specificity) was calculated using e-ASPECTS as reference. Evaluation time was recorded. DLIR significantly improved subjective image quality and gray-white matter contrast compared with ASIR-V (odds ratios 2.96-3.96; p 0.001). Diagnostic performance for detecting early ischemic changes showed no significant difference, with similar accuracy, sensitivity and specificity. Evaluation time did not differ. A trend toward higher specificity and reduced bias for ASPECTS ≥6 was observed with DLIR, but mixed-model analysis did not confirm statistical significance. DLIR improves subjective image quality in acute stroke NCCT but does not significantly improve detection accuracy or ASPECTS scoring compared with ASIR-V. A tendency toward improved specificity was observed; further studies with larger cohorts are needed.