Highly Scalable Image Reconstruction using Deep Neural Networks with Bandpass Filtering
This work addresses the need for faster and more scalable MRI reconstruction for medical imaging applications, but it appears incremental as it builds on existing methods with a specific adaptation.
The paper tackled the problem of improving the flexibility and scalability of deep neural networks for image reconstruction by proposing a framework based on bandpass filtering, which increased MRI subsampling rates to speed up acquisitions and enable visualization of rapid hemodynamics.
To increase the flexibility and scalability of deep neural networks for image reconstruction, a framework is proposed based on bandpass filtering. For many applications, sensing measurements are performed indirectly. For example, in magnetic resonance imaging, data are sampled in the frequency domain. The introduction of bandpass filtering enables leveraging known imaging physics while ensuring that the final reconstruction is consistent with actual measurements to maintain reconstruction accuracy. We demonstrate this flexible architecture for reconstructing subsampled datasets of MRI scans. The resulting high subsampling rates increase the speed of MRI acquisitions and enable the visualization rapid hemodynamics.