Xiao Xue

Title: Xiao Xue and Medical Image Segmentation Innovation.

Introduction

Xiao Xue is an inventor based in Beijing, China, associated with Canon Kabushiki Kaisha. Her patent work includes a method for training segmentation models to identify structures in medical images.

Latest Patents

Xue is credited with 1 patent: “Segmentation Model Learning Method, Processing Circuitry, Computer Program Product, and Medical Information Processing Device.” The invention describes training a segmentation model using both direct supervised learning, which classifies a predetermined structure into multiple categories, and indirect supervised learning, which divides a larger region into blocks. The method uses labeling information for each learning approach and optimizes the model’s network parameters based on a loss function.

Career Highlights

Xue’s listed patent reflects work at the intersection of medical imaging and machine learning. It addresses how different forms of labeled image data can contribute to training a model for segmentation tasks.

Collaborations

Xue’s listed coworkers include Gengwan Li and Bing Han. Her patent is associated with Canon Kabushiki Kaisha.

Conclusion

Xiao Xue’s patent describes a combined supervised-learning approach for medical image segmentation, highlighting her contribution to innovation in medical information processing.