Jun Kong

This paper introduces CycGANRegNet, a deep learning method for registering serial WSIs in different stains, achieving better performance than existing methods on breast cancer patient data.

This paper introduces a framework for real-time 3D tissue block registration in a human atlas, demonstrating its practicality and efficiency through experiments.

This paper develops a deep learning model to segment portal tract regions in liver biopsy images, showing strong correlation with fibrosis staging.

The paper introduces DPLab, a web-based platform for analyzing whole-slide pathology images, enabling 3D tissue reconstruction and sharing of analysis results.

This paper develops a deep learning system to predict pathological complete response in TNBC patients using histopathology images and biomarkers, achieving 93% accuracy.

The paper introduces MultiHeadGAN, a deep learning method for segmenting low contrast RPE cells in impaired flatmount images, achieving high segmentation accuracy.