Han Liu

Title: Han Liu: Advancing Medical Imaging Analysis Through Machine Learning.

Introduction

Han Liu is an inventor based in Nashville, Tennessee, whose patent work focuses on machine learning methods for medical imaging analysis. His invention addresses how models can learn to identify anatomical objects when training datasets have only partial labels.

Latest Patents

Liu is associated with 1 patent: “Learning from Partially Labeled Datasets for Medical Imaging Analysis.” The patent describes systems and methods that receive medical images, perform an analysis task using a machine-learning model, and output the results. The model is trained using medical images and available ground-truth labels, then generates pseudo labels for anatomical objects in those images. It is subsequently fine-tuned using both the original labels and the generated pseudo labels.

Career Highlights

Liu works at Siemens Healthineers AG, a company focused on healthcare technology. His patent reflects an approach to making use of partially labeled medical imaging data in the development of machine-learning models.

Collaborations

Liu’s listed coworker is Sasa Grbic. The patent information provided describes the invention but does not specify the individual contributions of its collaborators.

Conclusion

Han Liu’s patent presents a machine-learning approach that combines ground-truth and pseudo labels to support medical imaging analysis.