<![CDATA[Magnetic Resonance Imaging (MRI) is a diagnostic imaging modality with excellent soft-tissue contrast. MRI image quality is influenced by several acquisition parameters, including slice thickness. AIR™ Recon DL (Deep Learning Image Reconstruction) has been developed to improve image quality through noise reduction and deep learning-based reconstruction. This study aimed to analyze the effects of slice thickness variation and AIR™ Recon DL level on the image quality of axial T2-weighted sequences acquired on a 1.5-Tesla MRI system. A quantitative experimental design using a phantom study was employed. Slice thicknesses of 1 mm, 3 mm, and 5 mm were evaluated at four AIR™ Recon DL levels: Off, Low, Medium, and High. Image quality was assessed using Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR), measured with the Region of Interest (ROI) method. Data were analyzed using the Shapiro–Wilk test, Two-Way Repeated Measures ANOVA, and post hoc testing. The results demonstrated that slice thickness, AIR™ Recon DL level, and their interaction significantly affected both SNR and CNR (p<0.001). SNR increased with greater slice thickness and higher AIR™ Recon DL levels, with the highest value observed at 5 mm and the High level. In contrast, CNR tended to decrease as both parameters increased, and the highest CNR was obtained at 1 mm with AIR™ Recon DL Off. These findings indicate that AIR™ Recon DL can effectively improve signal quality; however, protocol optimization should maintain an appropriate balance among signal enhancement, noise reduction, partial-volume effects, and image contrast. The findings may support optimization and clinical studies.]]>
Copyrights © 2026
