Assessment of AI-accelerated T2-weighted brain MRI, based on clinical ratings and image quality evaluation.

OBJECTIVE

To compare clinical ratings and signal-to-noise ratio (SNR) measures of a commercially available Deep Learning-based MRI reconstruction method (T2(DR)) against conventional T2- turbo spin echo brain MRI (T2(CN)).

MATERIALS AND

METHODS

100 consecutive patients with various neurological conditions underwent both T2(DR) and T2(CN) on a Siemens Vida 3 T scanner with a 64-channel head coil in the same examination. Acquisition times were 3.33 min for T2(CN) and 1.04 min for T2(DR). Four neuroradiologists evaluated overall image quality (OIQ), diagnostic safety (DS), and image artifacts (IA), blinded to the acquisition mode. SNR and SNReff (adjusted for acquisition time) were calculated for air, grey- and white matter, and cerebrospinal fluid.

RESULTS

The mean patient age was 43.6 years (SD 20.3), with 54 females. The distribution of non-diagnostic ratings did not differ significantly between T2(CN) and T2(DR) (IA p = 0.108; OIQ: p = 0.700 and DS: p = 0.652). However, when considering the full spectrum of ratings, significant differences favouring T2(CN) emerged in OIQ (p = 0.003) and IA (p < 0.001). T2(CN) had higher SNR (157.9, SD 123.4) than T2(DR) (112.8, SD 82.7), p < 0.001, but T2(DR) demonstrated superior SNReff (14.1, SD 10.3) compared to T2(CN) (10.8, SD 8.5), p < 0.001.

CONCLUSION

Our results suggest that while T2(DR) may be clinically applicable for a diagnostic setting, it does not fully match the quality of high-standard conventional T2(CN), MRI acquisitions.