AI Based Scanning For High Quality Temporomandibular Joint Mr Imaging

To compare the value of artificial intelligence-compressed sensing (ACS) with conventional non ACS in patients indicated for temporomandibular joint MRI. This prospective single-center study included consecutive adult patients with temporomandibular disorders who were clinically referred for TMJ MRI between February and July 2024. The study collected 73 samples. Each participant underwent conventional MRI (proton density– and T2-weighted imaging), followed by a prospectively artificial intelligence-compressed sensing (ACS) examination. Three oral and maxillofacial radiologists evaluated images using a four-point Likert scale (1, poor; 4, excellent) for overall image quality, perceived signal-to-noise ratio, sharpness, artifacts, and diagnostic confidence. The frequency of major pathologic features and acquisition times were also compared between the acquisition protocols. The median acquisition time of the ACS-MR protocol was lower than that of the standard non-ACS MR protocol (361 seconds vs 685 seconds, respectively; P < 0.01), achieving a 47.6% lower acquisition time. Overall, the overall image quality (P <0 .01) and articular disc border sharpness (P < 0.01) was significantly higher in ACS compared with N-ACS in both coronal and sagittal position, respectively. Images acquired with ACS showed almost the equivalent ratings to N-ACS-acquired images in terms of diagnostic confidence (P < 0.01) compared to N-ACS in both coronal and sagittal position. ACS protocol demonstrated superior image quality while reducing acquisition time, presents significant clinical advantages in improving the efficiency and accessibility in MRI imaging of TMJ.