Abstract: A computer-implemented method for transforming magnetic resonance (MR) imaging across multiple vendors is provided. The method comprises: obtaining a training dataset, wherein the training dataset comprises a paired dataset and an un-paired dataset, and wherein the training dataset comprises image data acquired using two or more MR imaging devices; training a deep network model using the training dataset; obtaining an input MR image; and transforming the input MR image to a target image style using the deep network model.

Abstract: A computer-implemented method for transforming magnetic resonance (MR) imaging across multiple vendors is provided. The method comprises: obtaining a training dataset, wherein the training dataset comprises a paired dataset and an un-paired dataset, and wherein the training dataset comprises image data acquired using two or more MR imaging devices; training a deep network model using the training dataset; obtaining an input MR image; and transforming the input MR image to a target image style using the deep network model.

Abstract: The present invention is directed to a method and system of tissue or background suppression for the acquisition of image data from blood flow or tissue perfusion. Background suppression with minimal effects upon inflowing spins is achieved through a series of spin locking low level RF pulses that cause adiabatic demagnetization of tissue with a relaxation time T1-rho that is intermediate between T1 and T2 relaxation times. In this regard, the effective transverse magnetization of static tissue resulting from the application of a series of low level RF pulses is reduced and, with the spin locking, longitudinal magnetization regrowth is minimized. As such, inflowing spins to an imaging volume may be directly imaged with significant background tissue suppression. The present invention is particularly applicable to time-of-flight MRA and MR perfusion imaging.