Scholarlink

Purpose <p>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&#xa0;secondary objective was to determine the potential influence of reconstruction algorithm on ASPECT scoring relative to automated e-ASPECT score.</p> Methods <p>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.</p> Results <p>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&#xa0;trend toward higher specificity and reduced bias for ASPECTS ≥6 was observed with DLIR, but mixed-model analysis did not confirm statistical significance.</p> Conclusion <p>DLIR improves subjective image quality in acute stroke NCCT but does not significantly improve detection accuracy or ASPECTS scoring compared with ASIR-V. A&#xa0;tendency toward improved specificity was observed; further studies with larger cohorts are needed.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Performance of Deep Learning Reconstruction for Detection of Early Ischemic Changes in NCCT: Comparison with ASIR-V in Acute Stroke

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Michal Pula,
  • Adrian Korbecki,
  • Krzysztof Winiarczyk,
  • Arkadiusz Kacała,
  • Kamil Litwinowicz,
  • Michal Sobanski,
  • Julita Nadwodna,
  • Agata Zdanowicz-Ratajczyk,
  • Maciej Guziński

摘要

Purpose

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.

Methods

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.

Results

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.

Conclusion

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.