Accelerated Deep Learning Reconstructed Turbo Spin-Echo MRI for Temporomandibular Joint: A Prospective Study

Motivation: Patients with temporomandibular joint (TMJ) disorders often cannot endure long magnetic resonance imaging (MRI) examination due to facial pain and can result in image artifacts and examination failures, thus necessitating time reduction and image quality improvement of MRI. Goal(s): To investigate the image quality of deep learning (DL) reconstruction in TMJ turbo spin-echo (TSE) MRI. Approach: Image quality of standard TSE and TSEDL protocols of 19 participants with bilateral temporomandibular joint were evaluated. Results: Most structures sharpness of TSEDL protocol and overall image quality were equivalent or significantly higher than standard TSE protocol. Readers' diagnostic confidence in the coronary T2WI images increased significantly. Impact: This study demonstrated that accelerated TSE DL MRI reduced acquisition time of TMJ and held great image quality and comparable diagnostic confidence, which has great potential in optimizing clinical protocols and improving the comfort level of patients with TMJ disorders.