Feiyu Chen

Title: Feiyu Chen: Innovator in Medical Imaging Technology

Introduction

Feiyu Chen is a prominent inventor based in Stanford, CA, known for his contributions to the field of medical imaging technology. He holds a total of 3 patents that focus on enhancing the capabilities of magnetic resonance imaging (MRI) systems through advanced deep learning techniques.

Latest Patents

Chen's latest patents include a method for estimating systematic imperfections in medical imaging systems using deep learning. This innovative approach involves acquiring undersampled magnetic-field-gradient-encoded k-space data through an MRI scanner. The method performs self-calibration of the magnetic-field-gradient-encoding point-spread function using a neural network to estimate systematic waveform errors from the k-space data. It then reconstructs an image using a second neural network based on the computed point-spread function and the k-space data.

Another significant patent by Chen is a method for performing magnetic resonance imaging reconstruction with unsupervised deep learning. This method entails unsupervised training of a deep neural network using a training set of under-sampled MRI scans. The MRI apparatus conducts an under-sampled scan to produce k-space data, updates the deep neural network, and processes the data to reconstruct a final MRI image.

Career Highlights

Feiyu Chen has worked with notable organizations, including Leland Stanford Junior University and General Electric Company. His experience in these institutions has significantly contributed to his expertise in medical imaging technologies.

Collaborations

Some of Chen's notable coworkers include Joseph Yitan Cheng and John Mark Pauly, who have collaborated with him on various projects in the field of medical imaging.

Conclusion

Feiyu Chen's innovative work in medical imaging technology, particularly in the application of deep learning techniques, has made a significant impact on the field. His patents reflect a commitment to advancing MRI technology and improving diagnostic capabilities.