Quantitative Evaluation of Low-Dose CT Image Quality Using Deep Learning Reconstruction: A Comparative Study of Philips Precise Image and GE TrueFidelity

Reducing radiation exposure in CT imaging is critical, particularly in routine and repeat examinations. Deep learning image reconstruction (DLIR) has emerged as a key approach for maintaining diagnostic quality at low-dose acquisition settings. This study compared two DLIR algorithms of Philips Precise Image (PI) and GE TrueFidelity (TF) under an 80 kVp low-dose CT scenario, using the AAPM CIRS-610 phantom to replicate clinical imaging conditions. The phantom's linearity, high-resolution, and artifact modules were scanned with Philips CT 5300 and GE Revolution CT scanners at low-dose parameters. Images were reconstructed using five DLIR presets, including PI (Smoother, Standard, Sharper) and TF (Middle, High), and evaluated with eight quantitative metrics, including SNR, CNR, nRMSE, PSNR, SSIM, FSIM, UQI, GMSD, and gradient magnitude. TF-High delivered the highest SNR (115.0-118.0 across modules), representing a 54-57% improvement over PI-Smoother, and achieved superior PSNR and the lowest GMSD, reflecting better preservation of structure in low-dose images. PI-Sharper provided the strongest gradient magnitude, emphasizing fine edge detail. Under low-dose CT conditions, TF-High offered the optimal balance of noise suppression and structure fidelity, while PI-Sharper highlighted fine detail enhancement. These findings show that DLIR settings must be tailored to clinical needs when operating under low-dose imaging protocols.