Motion correction for cardiac PET-MRI studies

Motion correction for cardiac PET-MRI studies

We proposed an unsupervised deep learning-based approach for deformable three-dimensional cardiac MR image registration. This method learns a motion model that balances image similarity and motion estimation accuracy. We validated our approach comprehensively on three datasets and demonstrated higher motion estimation and registration accuracy relative to several popular state-of-the-art image registration methods (Morales 2019)

When used for PET motion correction, CarMEN led to an increase in the contrast-to-noise ratio in the simulated perfusion lesions (Morales et al, ISMRM/SNMMI co-provided PET/MRI Workshop, New York 2019). 

Siemens Biograph mMR

The Biograph mMR scanner (Siemens Healthineers, Erlangen, Germany) consists of a 3T whole-body superconductive magnet with active shielding and external interference shielding and a whole-body PET scanner. It is equipped with a gradient system with a maximum gradient amplitude of 45 mT/m and a maximal slew rate of 200 T/m/s.  Separate cooling channels that simultaneously cool primary and secondary coils allow the application of extremely gradient intensive techniques. 

This scanner is equipped with the “TIM” RF coils that were custom designed to minimize the 511 keV photons attenuation. The fully-integrated PET detectors use avalanche photodiode (APD) technology and LSO scintillator crystals (eight rings with 56 detectors blocks per ring, each consisting of 8×8 arrays of 4×4×20 mm3crystals read out by a 3×3 array of APDs).  The PET scanner’s transaxial and axial fields of view are 594 mm and 25.8 cm, respectively.

The Biograph mMR was installed at the Martinos Center in June 2011.