Decoding the human brain tissue response to radiofrequency excitation using a biophysical-model-free deep MRI on a chip framework
This work addresses the need for faster and more comprehensive MRI scans in clinical diagnosis, particularly for brain pathologies, though it appears incremental as it builds on existing deep learning and MRI techniques.
The authors tackled the problem of lengthy MRI examinations by developing a vision transformer-based framework that decodes brain tissue response to RF excitation, enabling rapid generation of multiple image contrasts after a 28.2-second calibration scan and proving to be 94% faster than alternative protocols.
Magnetic resonance imaging (MRI) relies on radiofrequency (RF) excitation of proton spin. Clinical diagnosis requires a comprehensive collation of biophysical data via multiple MRI contrasts, acquired using a series of RF sequences that lead to lengthy examinations. Here, we developed a vision transformer-based framework that captures the spatiotemporal magnetic signal evolution and decodes the brain tissue response to RF excitation, constituting an MRI on a chip. Following a per-subject rapid calibration scan (28.2 s), a wide variety of image contrasts including fully quantitative molecular, water relaxation, and magnetic field maps can be generated automatically. The method was validated across healthy subjects and a cancer patient in two different imaging sites, and proved to be 94% faster than alternative protocols. The deep MRI on a chip (DeepMonC) framework may reveal the molecular composition of the human brain tissue in a wide range of pathologies, while offering clinically attractive scan times.