Phantom-based performance comparison of two commercial deep learning CT reconstruction algorithms with super- and normal-resolution settings.
Authors
Affiliations (4)
Affiliations (4)
- IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging, Nîmes University Hospital, Nîmes, France. [email protected].
- Diagnostic Imagery Department, Nouvel Hôpital Civil (NHC), Hôpitaux Universitaires de Strasbourg, Strasbourg, France.
- IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging, Nîmes University Hospital, Nîmes, France. [email protected].
- IMAGINE UR UM 103, Montpellier University, Department of Medical Imaging, Nîmes University Hospital, Nîmes, France.
Abstract
We compared a super-resolution deep learning image reconstruction (SR-DLR) algorithm with a normal-resolution (NR)-DLR algorithm according to radiation dose for abdominal computed tomography (CT). An image-quality phantom was scanned with an energy-integrating detectors CT unit at three volume CT dose index radiation dose levels (12.7, 5.9, and 3 mGy). Images were reconstructed using a 1,024<sup>2</sup> matrix for SR-DLR and a 512<sup>2</sup> matrix for NR-DLR, for three DLR levels (level-1, level-2, and level-3). Noise power spectrum (NPS) and task-based transfer function (TTF) for iodine and Solid Water<sup>®</sup> inserts were computed; TTF values at 50% (f<sub>50</sub>, mm<sup>-1</sup>) were used to quantify spatial resolution. The detectability index (d') was computed for two simulated lesions. Noise magnitude values were lower with SR-DLR than with NR-DLR for level-2 (-27.6 ± 3.8%) and level-3 (-43.5 ± 1.4%), the opposite for level-1. Average NPS spatial frequency was higher with SR-DLR than with NR-DLR for all radiation dose levels for level-1 (55.9 ± 16.7%) and level-2 (20.1 ± 13.9%) and the opposite for level-3, except at 12.7 mGy. For both inserts, f<sub>50</sub> was higher with SR-DLR than with NR-DLR at each radiation dose and DLR level. For simulated lesions and all DLR levels, d' values were higher with SR-DLR than with NR-DLR (level-1, 6.0 ± 2.0%; level-2, 45.7 ± 5.0%; level-3, 75.2 ± 7.3%). Compared to NR-DLR, SR-DLR improved spatial resolution and detectability of simulated abdominal lesions; image noise was reduced with SR-DLR only for level-2 and level-3, while image texture was better for level-1 and level-2. Super-resolution DLR with a 1,024<sup>2</sup> matrix size improved spatial resolution and detectability of simulated abdominal lesions compared to normal-resolution DLR. Validation in clinical settings is necessary before translation into routine practice. The performance of a new deep learning super-resolution image reconstruction algorithm (SR-DLR) was compared to a normal-resolution (NR)-DLR algorithm using an image-quality phantom for an abdominal energy-integrating detector CT protocol. SR-DLR with a 1,024<sup>2</sup> matrix improved spatial resolution and detectability of simulated abdominal lesions compared to NR-DLR with a 512<sup>2</sup> matrix. Using SR-DLR, therefore, presents numerous prospects for improving abdominal CT images and a high potential for reducing the radiation doses.