Dr. Yang Song is a Lecturer in the School of Computer Science and Engineering, University of New South Wales (UNSW), Australia. She graduated with a BEng in Computer Engineering from Nanyang Technological University, Singapore, and obtained her PhD degree in Computer Science (medical imaging) from the University of Sydney in 2013. She received the highly competitive Australian Research Council (ARC) Discovery Early Career Researcher Award (DECRA) in 2015, and was an ARC DECRA Fellow at the University of Sydney before joining UNSW in 2018. She also received the Engineering Dean’s Research Award, The University of Sydney, in 2017. She has over 100 publications including papers in TMI, MedIA, NeuroImage, BMC Bioinformatics, CVPR, ICCV, IJCAI, and MICCAI.
Automated analysis for histopathology images is essential to support efficient, objective, and reproducible disease diagnosis. While deep learning technologies have been successfully applied to many histopathology imaging applications, the difficulty of generating large amounts of well annotated data remains a critical challenge for designing deep learning methodologies. In this talk, I will present some of our recent studies in developing fully- and weakly-supervised deep learning methodologies for various histopathology image analysis applications, including tumor subtyping and cell nuclei segmentation. I will also present a discussion about the future of weakly-supervised deep learning in histopathology and other diagnostic imaging modalities such as CT and MRI.
Institute of Medical Robotics