Current diagnosis of temporomandibular disorders includes clinical examination and MRI; however, static MR images in only two key positions are not sufficient for detection of some cases of temporomandibular disk displacement. We acquired jaw opening and closure movements for 5 healthy volunteers with a real-time MRI in axial plane. The condyles were segmented with a convolutional neural network approach and motion curves of their mass centers were calculated. It was shown that the proposed protocol gives straighforward evaluation of condylar motion assymetry.
This abstract and the presentation materials are available to members only; a login is required.