San Ramon, CA, United States of America

Shiyu Xu

This inventor holds 1 USPTO granted patent and 4 published patent applications. Top assignee: Neuraltrak, INC. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Shiyu Xu. Retrieved from https://idiyas.com/inventor/shiyu-xu-tfetabao

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 1 

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Shiyu Xu and Medical 3D Imaging Reconstruction

Introduction

Shiyu Xu is an inventor based in San Ramon, California. His patent work focuses on medical 3D imaging reconstruction using a dual-domain neural network, with the goal of producing useful volumetric images from limited-angle 2D projections.

Latest Patents

Xu is associated with 1 patent: “System and Method for 3D Imaging Reconstruction Using Dual-Domain Neural Network.” The application describes capturing 2D projections across a limited angle, calibrating those projections, and generating a sinogram from them. A dual-domain neural network then processes the sinogram to produce a geometrically corrected and calibrated 3D volumetric image.

The described approach uses only 30–50% of the data required by traditional scanner-based 3D reconstruction. By reducing the amount of acquired data, it aims to lower radiation-dose requirements and improve clinical efficiency.

Career Highlights

Xu is associated with Neuraltrak, Inc. His patent application addresses a technical challenge in medical imaging: reconstructing 3D images when only limited-angle projection data is available.

Collaborations

Xu’s coworker, Linxi Shi, is identified as a woman. The provided information does not specify her role in the patent or the imaging system.

Conclusion

Shiyu Xu’s patent work centers on neural-network-based medical imaging reconstruction, combining calibrated projection data and sinogram processing to create 3D images with less acquired data.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…