Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data.

PURPOSE

The purpose of this study was to compare the effect of two deep learning image reconstruction (DLR) algorithms in chest computed tomography (CT) with different clinical indications.

MATERIAL AND METHODS

Acquisitions on image quality and anthropomorphic phantoms were performed at six dose levels (CTDI: 10/7.5/5/2.5/1/0.5mGy) on two CT scanners equipped with two different DLR algorithms (TrueFidelity and AiCE). Raw data were reconstructed using the filtered back-projection (FBP) and the lowest/intermediate/highest DLR levels (L-DLR/M-DLR/H-DLR) of each algorithm. Noise power spectrum, task-based transfer function (TTF) and detectability index (d') were computed: d' modelled detection of a soft tissue mediastinal nodule, ground-glass opacity, or high-contrast pulmonary lesion. Subjective image quality of anthropomorphic phantom images was analyzed by two radiologists.

RESULTS

For the L-DLR/M-DLR levels, the noise magnitude was lower with TrueFidelity than with AiCE from 2.5 to 10 mGy. For H-DLR, noise magnitude was lower with AiCE . For L-DLR and M-DLR, the average NPS spatial frequency (f) values were greater for AiCE except for 0.5 mGy. For H-DLR levels, f was greater for TrueFidelity than for AiCE. TTF values were greater with AiCE for the air insert, and lower than TrueFidelity for the polyethylene insert. From 2.5 to10 mGy, d' was greater for AiCE than for TrueFidelity for H-DLR for all lesions, but similar for L-DLR and M-DLR. Image quality was rated clinically appropriate for all levels of both algorithms, for dose from 2.5 to 10 mGy, except for L-DLR of AiCE.

CONCLUSION

DLR algorithms reduce the image-noise and improve lesion detectability. Their operations and properties impacted both noise-texture and spatial resolution.