Presidential Lecture - "Deep Learning for Medical Imaging" by Dr. Lily Peng

ABSTRACT:

Deep learning is a family of machine learning techniques in which multiple computational units, organized in layers, work together to model complex systems with high accuracy by learning from examples. Deep convolutional neural networks are a specific subtype of deep learning optimized for images. This technique has produced algorithms that can diagnose melanoma, breast cancer lymph node metastases and diabetic retinopathy from medial images with comparable accuracy to human experts. This talk covers work in applying deep learning to imaging for diabetic retinopathy, cancer screening & diagnosis, including recent work in using different reference standards and techniques to improve explainability. It will also cover how deep learning can be leveraged to make novel predictions such as cardiovascular risk factors and disease progression.

BIOGRAPHY:

Dr. Lily Peng is the physician-scientist lead for the medical imaging team, which applies deep learning to medical imaging for Google AI Healthcare. The team’s work focuses building algorithms and software that detects diabetic eye disease and other diseases in ophthalmology (AMD, glaucoma), pathology (prostate/breast cancer), radiology and dermatology. Before joining the team at Google, she was a Clinical Product Manager at Doximity, a leading health care start up and the largest physician network and a co-founder of Nano Precision Medical (NPM), a medical device start up that is developing a small implantable continuous drug delivery device, where she retains a position as Consulting Vice President of Clinical Development. Dr. Peng completed her M.D. and Ph.D. in Bioengineering at the University of California, San Francisco in the lab of Dr. Tejal Desai, where she studied medical applications of nanostructured material such as TiO2 nanotubes and collagen nanofibers. She has authored numerous publications in both the bioengineering and biological space. In 2017, she was listed as one of WIRED Next’s “20 People Who Are Creating the Future”.

Dr. Dale Webster is staff software engineer for the medical imaging teamat Google AI Healthcare, where he applies deep learning to medicalimaging. Prior to Google, he was a senior software engineer inbioinformatics at Pacific Biosciences. He received his PhD from theUniversity of California, San Francisco.