Enhancing Non-Contrast CT Interpretation for Acute Anterior Circulation Stroke: A Deep Learning Approach for Grayscale Image Transformation

<h3>BACKGROUND AND PURPOSE:</h3> To develop a two-stage framework that combines deep learning-based super-resolution with subsequent image processing to generate high-contrast thin-slice CT (HCCT) from NCCT, thereby improving the detection of early ischemic changes (EICs) in acute anterior circulation stroke. <h3>MATERIALS AND METHODS:</h3> A retrospective study was conducted on patients with large vessel occlusion stroke between 2020 and 2024 across four medical centers. NCCT images were converted to HCCT using the two-stage framework. Two neuroradiologists (NRADs) independently assessed ASPECTS and ischemic volumes on both NCCT and HCCT-assisted interpretation, with diagnostic accuracy measured using Tmax &gt; 6 seconds as a reference standard. <h3>RESULTS:</h3> The study included 303 participants (mean age, 67.2 years ± 12.7; 187 male). The mean Tmax-ASPECTS was 4.9 ± 2.7, and the median ischemic volume was 50.36 mL (IQR, 29.36–72.49 mL). The inter-rater ASPECTS correlation improved significantly from 0.72 on NCCT to 0.94 on HCCT-assisted (<i>p</i> &lt; 0.001). The intra-class correlation coefficient (ICC) for HCCT-assisted ASPECTS was 0.85 (95% CI: 0.80 to 0.89; <i>p</i> &lt; 0.001), and for Tmax-ASPECTS, it was 0.90 (95% CI: 0.87 to 0.93; <i>p</i> &lt; 0.001), as evaluated by two NRADs. Two NRADs reported strong correlations observed of ischemic volumes between the HCCT-assisted group and Tmax (NRAD1: r = 0.83, NRAD2: r = 0.83; both <i>p</i> &lt; 0.001). ASPECTS ≥6 in the HCCT-assisted group showed the strongest association with favorable outcome (NRAD1: OR 2.87, 95% CI 1.97-5.21; NRAD2: OR 2.74, 95% CI 1.78-5.55; both <i>p</i> &lt;0.001), outperforming conventional NCCT. <h3>CONCLUSION:</h3> HCCT significantly improves the interpretation of EICs, improving inter-rater agreement for ASPECTS scoring in acute anterior circulation stroke.