Stephen TC Wong

Title: Stephen TC Wong: Advancing CT Denoising Through Deep Learning.

Introduction

Stephen TC Wong is an inventor based in Houston, Texas, whose work includes applying deep learning to improve the quality of computed tomography (CT) images. His patent describes a denoising method intended to support clearer imaging for disease detection in patients with acute ischemic stroke.

Latest Patents

Wong is associated with 1 patent: “Method of CT Denoising Employing Deep Learning of Multiple Co-Registered Scans of the Same Person and Group Convolutional Neural Network Analyses.” The invention uses multiple co-registered scans and a group convolutional neural network to reduce noise in non-contrast head CT images while preserving anatomical detail.

According to the disclosed results, the method improved signal-to-noise ratios in gray matter, white matter, and deep gray matter by 2.47×, 2.83×, and 2.64×, respectively, compared with the original images. It also improved contrast-to-noise ratios in deep gray matter relative to white matter and gray matter relative to white matter by 2.30× and 2.16×, respectively. The patent reports that the approach outperformed BM3D denoising and produced visually clearer scans across 380 previously unseen head CT cases.

Career Highlights

Wong works at The Methodist Hospital. His patent highlights the use of deep learning in medical imaging, with a focus on reducing CT image noise while retaining features that may be important for clinical interpretation.

Collaborations

The provided information identifies John J. Volpi and Kelvin Wong as Wong’s coworkers. It does not specify their roles in the patent or the development of the denoising method.

Conclusion

Stephen TC Wong’s patented CT denoising method applies deep learning to improve image clarity and signal quality while preserving anatomy, illustrating a practical innovation in medical imaging.