Impact of deep Learning-enhanced contrast on diagnostic accuracy in stroke CT angiography

Sebastian Steinmetz; Mario Alberto Abello Mercado; Sebastian Altmann; Antoine Sanner; Andrea Kronfeld; Marius Frenzel; Dongok Kim; Sergiu Groppa; Timo Uphaus; Marc A Brockmann; Ahmed E Othman

doi:10.1016/j.ejrad.2024.111808

Impact of deep Learning-enhanced contrast on diagnostic accuracy in stroke CT angiography

Eur J Radiol. 2024 Oct 28:181:111808. doi: 10.1016/j.ejrad.2024.111808. Online ahead of print.

Affiliations

¹ Department of Neuroradiology, University Medical Center Mainz, Johannes Gutenberg University, Langenbeckstr. 1, 55131 Mainz, Germany.
² Technical University of Darmstadt, Karolinenpl. 5, 64289 Darmstadt, Germany.
³ Department of Neuroradiology, University Medical Center Mainz, Johannes Gutenberg University, Langenbeckstr. 1, 55131 Mainz, Germany. Electronic address: marius.frenzel@unimedizin-mainz.de.
⁴ Department of Applied Bioengineering, Graduate School of Convergence Science and Technology, Seoul, Republic of Korea.
⁵ Department of Neurology, University Medical Center Mainz, Johannes Gutenberg University, Langenbeckstr. 1, 55131 Mainz, Germany.
⁶ Department of Neuroradiology, University Medical Center Mainz, Johannes Gutenberg University, Langenbeckstr. 1, 55131 Mainz, Germany. Electronic address: ahmed.e.othman@googlemail.com.

PMID: 39520838
DOI: 10.1016/j.ejrad.2024.111808

Abstract

Purpose: To examine the impact of deep learning-augmented contrast enhancement on image quality and diagnostic accuracy of poorly contrasted CT angiography in patients with suspected stroke.

Methods: This retrospective single-centre study included 102 consecutive patients who underwent CT imaging for suspected stroke between 01/2021 and 12/2022, including whole brain volume perfusion CT (VPCT) and, specifically, a poorly contrasted CT angiography (defined as < 350HU in the proximal MCA). CT angiography imaging data was reconstructed using i.) an iterative reconstruction kernel (conventional CTA, c-CTA) as well as ii.) an iodine-based contrast boosting deep learning model (Deep Learning-enhanced CTA, DLe-CTA). For quantitative analysis, the slope, contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR) were determined. Qualitative image analysis was conducted by three readers, rating image quality and vessel-specific parameters on a 4-point Likert scale. Readers evaluated both datasets for cerebral vessel occlusion presence. VPCT served as the reference standard for calculating sensitivity and specificity.

Results: 102 patients were evaluated (mean age 69 ± 13 years; 70 men). DLe-CTA outperformed c-CTA in quantitative (all items p < 0.001) and qualitative image analysis (all items p < 0.05). VPCT revealed 58/102 patients with vascular occlusion. DLe-CTA resulted in significantly higher sensitivity compared to c-CTA (p < 0.001); (all readers put together: c-CTA: 142/174 [81.6 %; 95 % CI: 75.0 %-87.1 %] vs. DLe-CTA 163/174 [94 %; 95 % CI: 89.0 %-96.8 %]). One false positive finding occurred on DLe-CTA (specificity 1/132) [99.2 %; 95 % CI: 95.9 %-100 %].

Conclusions: Deep learning-augmented contrast enhancement improves the image quality and increases the sensitivity of detection vessel occlusions in poorly contrasted CTA.

Keywords: Computed tomography angiography; Deep learning-augmented contrast enhancement; Denoising; Diagnostic accuracy; Stroke; Vessel occlusion.