Xiao Li

Title: Innovations of Inventor Xiao Li

Introduction

Xiao Li is an accomplished inventor based in Foster City, CA (US). He has made significant contributions to the field of digital pathology through his innovative patent. His work focuses on utilizing neural networks to predict disease progression, showcasing the intersection of technology and healthcare.

Latest Patents

Xiao Li holds a patent for "Attention-based multiple instance learning." This invention relates to predicting disease progression by processing digital pathology images using neural networks. The patent describes a method where a digital pathology image, depicting a specimen stained with one or more stains, is accessed. A set of patches is defined for the digital pathology image, with each patch representing a portion of the image. An attention-score neural network generates attention scores for each patch, trained to minimize variability across patches in training images labeled to indicate no or low subsequent disease progression. Ultimately, a result-prediction neural network uses these attention scores to predict the extent to which a disease may progress in the subject.

Career Highlights

Throughout his career, Xiao Li has worked with prominent companies in the biotechnology sector, including Genentech, Inc. and Hoffmann-La Roche Inc. His experience in these organizations has allowed him to develop and refine his innovative ideas in the field of digital pathology.

Collaborations

Xiao Li has collaborated with talented individuals such as Yao Nie and Trung Kien Nguyen. These partnerships have contributed to the advancement of his research and the successful development of his patent.

Conclusion

Xiao Li's innovative work in digital pathology exemplifies the potential of technology to enhance healthcare outcomes. His patent on attention-based multiple instance learning is a testament to his expertise and dedication to improving disease prediction methods.