TY  - JOUR
AU  - Faust, Jonas Frederik
AU  - Krafft, Axel Joachim
AU  - Polak, Daniel
AU  - Speier, Peter
AU  - Behl, Nicolas Gerhard Roland
AU  - Ooms, Nathan
AU  - Roll, Jesse
AU  - Krieger, Joshua
AU  - Ladd, Mark Edward
AU  - Maier, Florian
TI  - Rapid CNN-based needle localization for automatic slice alignment in MR-guided interventions using 3D undersampled radial white-marker imaging.
JO  - Medical physics
VL  - 51
IS  - 11
SN  - 0094-2405
CY  - College Park, Md.
PB  - AAPM
M1  - DKFZ-2024-01887
SP  - 8018-8033
PY  - 2024
N1  - 2024 Nov;51(11):8018-8033
AB  - In MR-guided in-bore percutaneous needle interventions, typically 2D interactive real-time imaging is used for navigating the needle into the target. Misaligned 2D imaging planes can result in losing visibility of the needle in the 2D images, which impedes successful targeting. Necessary iterative manual slice adjustment can prolong interventional workflows. Therefore, rapid automatic alignment of the imaging planes with the needle would be preferable to improve such workflows.To investigate rapid 3D localization of needles in MR-guided interventions via a convolutional neural network (CNN)-based localization algorithm using an undersampled white-marker contrast acquisition for the purpose of automatic imaging slice alignment.A radial 3D rf-spoiled gradient echo MR pulse sequence with white-marker encoding was implemented and a CNN-based localization algorithm was employed to extract position and orientation of an aspiration needle from the undersampled white-marker images. The CNN was trained using porcine tissue phantoms (257 needle trajectories, four-fold data augmentation, 90
KW  - device localization (Other)
KW  - interventional MRI (Other)
KW  - percutaneous needle intervention (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:39292615
DO  - DOI:10.1002/mp.17376
UR  - https://inrepo02.dkfz.de/record/293339
ER  -