The General Hospital Corporation

Bruce Fischl

Andre Van Der Kouwe

Jonathan R Polimeni

Lawrence Leroy Wald

Matthew Tisdall

Olivia M Viessmann

Anatomical, physiological, instrumental, and other related biases are removed from functional magnetic resonance imaging ('fMRI') signal data using deep learning algorithms and/or models, such as a neural network. Bias characterization data are used as an auxiliary input to the neural network. The bias characterization data can be subject-specific bias characterization data (e.g., cortical thickness maps, cortical orientation angle maps, vasculature maps), hardware-specific bias characterization data (e.g., coil sensitivity maps, coil transmission profiles), or both. The subject-specific bias characterization data can be extracted from the fMRI signal data using a second neural network. The bias-reduced fMRI signal data can include time-series signals, functional activation maps, functional connectivity maps, or combinations thereof.

Subject-specific and hardware-specific bias removal from functional magnetic resonance imaging signals using deep learning

Systems and methods for performing fast multi-contrast magnetic resonance imaging ('MRI') are provided. In general, data are acquired from both multiple echo times ('TEs') and at multiple effective inversion times (&#x201c;TIs&#x201d;). Following the application of a magnetization preparation radio frequency (&#x201c;RF&#x201d;) pulse, a plurality of different multi-echo acquisitions are performed, thereby acquiring data from multiple different TEs during different portions of the longitudinal magnetization recovery curve. Data acquisition in these inner encoding loops (i.e., during each multi-echo acquisition) can be accelerated to efficiently provide for the acquisition of multiple contrasts in the time normally required to acquire a single contrast.

System and methods for fast multi-contrast magnetic resonance imaging

A system and method for performing an MRI or MRS scan that is optimized for a particular target structure. A prescan is conducted during a first session in which an image that is optimized for segmentation is acquired along with an alignment scout image or a 2D or 3D navigator signal. The segmentation process is employed to locate and define the target structure. During a second session the alignment scout image or navigator signal is reacquired and the information is used to determine the position transformation needed to align images from the two sessions. The position transformation information and the segmentation information are then employed to tailor a prescribed pulse sequence to examine the target structure.

Selective MR imaging of segmented anatomy

A system and method for medical imaging includes an improvement to the MP-RAGE pulse sequence that enables the readout bandwidth thereof to be matched to that of other pulse sequences used in the same examination without a significant loss in SNR. More specifically, the present invention includes using a multi-echo MP-RAGE pulse sequence in which multiple gradient-recalled NMR signals are acquired at the desired 'matching' bandwidth and combining selected ones of the NMR signals to reconstruct an image. By selecting and combining NMR signals acquired at each phase encoding, the SNR of the resulting reconstructed image can be maintained.

Growing community of inventors

Cambridge, MA, United States of America

Bruce Fischl