Application of deep learning reconstruction at prone position chest scanning of early interstitial lung disease

Abstract

Aim This study was aimed to compare the image quality and radiation dose between images reconstructed with deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) at prone position scanning in patients of early-stage interstitial lung disease (ILD). Methods This study prospectively enrolled 21 patients with early-stage ILD. All patients underwent high-resolution CT (HRCT) and low-dose CT (LDCT) scans. HRCT images were reconstructed with HIR using standard settings, and LDCT images were reconstructed with DLR (lung/bone kernel) in a mild, standard, or strong setting. Overall image quality, image noise, streak artifacts, and visualization of normal and abnormal ILD features were analysed. Results The effective dose of LDCT was 1.22 ± 0.09 mSv, 65.1% less than the HRCT dose. The objective noise of the LDCT DLR images was 33.0–111.8% that of the HRCT HIR images, with a signal-to-noise ratio (SNR) of 0.88 to 3.12 times that of the HRCT HIR images. The LDCT DLR was comparable to the HRCT HIR in terms of overall image quality. LDCT DLR (bone, strong) visualization of bronchiectasis and/or bronchiolectasis was significantly weaker than that of HRCT HIR. The LDCT DLR (all settings) did not significantly differ from the HRCT HIR in the evaluation of other abnormal features, including ground glass opacities (GGOs), architectural distortion, reticulation and honeycombing. Conclusion DLR was promising for maintaning image quality under a lower radiation dose in prone scanning for early ILD patients.