Contribution of an artificial intelligence deep-learning reconstruction algorithm for dose optimization in lumbar spine CT examination: A phantom study

•The impact of a new artificial intelligence deep-learning reconstruction algorithm on image quality and dose for lumbar spine CT was compared to a hybrid iterative reconstruction algorithm.•For bone reconstruction kernel, from Standard to Smoother levels, the noise magnitude and the detectability of bone lesions are improved using the new artificial intelligence deep-learning reconstruction.•The use of Smooth and Smoother levels allows a significant dose reduction (up to 72%) with a high detectability for the detection of lytic and sclerotic bone lesions and excellent overall clinical image quality. The purpose of this study was to assess the impact of the new artificial intelligence deep-learning reconstruction (AI-DLR) algorithm on image quality and radiation dose compared with iterative reconstruction algorithm in lumbar spine computed tomography (CT) examination. Acquisitions on phantoms were performed using a tube current modulation system for four DoseRight Indexes (DRI) (i.e., 26/23/20/15). Raw data were reconstructed using the Level 4 of iDose4 (i4) and three levels of AI-DLR (Smoother/Smooth/Standard) with a bone reconstruction kernel. The Noise power spectrum (NPS), task-based transfer function (TTF) and detectability index (d’) were computed (d’ modeled detection of a lytic and a sclerotic bone lesions). Image quality was subjectively assessed on an anthropomorphic phantom by two radiologists. The Noise magnitude was lower with AI-DLR than i4 and decreased from Standard to Smooth (-31 ± 0.1 [SD]%) and Smooth to Smoother (-48 ± 0.1 [SD]%). The average NPS spatial frequency was similar with i4 (0.43 ± 0.01 [SD] mm–1) and Standard (0.42 ± 0.01 [SD] mm–1) but decreased from Standard to Smoother (0.36 ± 0.01 [SD] mm–1). TTF values at 50% decreased as the dose decreased but were similar with i4 and all AI-DLR levels. For both simulated lesions, d’ values increased from Standard to Smoother levels. Higher detectabilities were found with a DRI at 15 and Smooth and Smoother levels than with a DRI at 26 and i4. The images obtained with these dose and AI-DLR levels were rated satisfactory for clinical use by the radiologists. Using Smooth and Smoother levels with CT allows a significant dose reduction (up to 72%) with a high detectability of lytic and sclerotic bone lesions and a clinical overall image quality.