Evaluating the clinical feasibility of magnetic resonance imaging positioning plates for head and neck radiotherapy through image registration

Conventional computed tomography-magnetic resonance imaging (CT-MRI) fusion for head and neck radiotherapy is often limited by registration uncertainty from inconsistent positioning and immobilization between diagnostic MRI and CT simulation. This study evaluates the practicality of using MRI positioning plates for head and neck tumors through image registration. A total of 35 patients with head and neck tumors were retrospectively included. Two sets of MRI data were obtained, with and without the positioning plate. These scans were fused with simulated CT images using either rigid registration (RIR) or deformable registration, generating four image combinations: CT/MRI positioning plate_RIR, CT/MRI positioning plate_DIR, CT/MRI_RIR, and CT/MRI_DIR (referred to as SETS1-4). Gross tumor volume (GTV) and organs at risk (OARs) were delineated on each image set. GTVs, OARs, and dose distributions from SET1 were used as reference values, and the overlap of GTV with OAR and dose variations were compared with SETS2-4. Image registration accuracy was assessed using geometric evaluation metrics, including the dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), Hausdorff distance (HD), and mean distance to agreement (MDA). Compared with the reference registration method, all registration methods for GTVs and most OARs showed statistically significant differences in DSC, JSC, HD, and MDA (p 0.7) and close margin agreement (MDA < 2 mm). For head and neck tumors, MRI images obtained with the positioning plate in the treatment position showed substantial geometric similarity to simulated CT scans through RIR. This similarity enables the use of MRI for radiotherapy target delineation, providing a significant advantage for clinical practice in hospitals without MRI simulators.