MRI offers the gold standard for delineating cancerous lesions in soft tissue. Minimally invasive needle-based interventions require the accurate placement of multiple long, flexible needles at the target site. The manual tracking of needles in MR images is a time-consuming task that is further challenged by needle deflection. Automated needle segmentation offers the means to evaluate the alignment of the needle to the scan plane. This work demonstrates automatic needle tracking using remote scan control to dynamically update the scan plane of a real-time MR sequence. Automatic scan plane alignment is validated, and the feasibility of needle tracking is assessed.
This abstract and the presentation materials are available to members only; a login is required.