Titles and Affiliations

Professor of Medicine and Engineering
University of Southern California
Founding Director and CEO
Lawrence J. Ellison Institute for Transformative Medicine

Research area

Using machine learning to analyze tissue structure in order to predict outcomes and guide treatment decisions for patients with breast cancer.


Microscopic analysis of tumor biopsy images can tell us a lot about the biology of a patient’s tumor, but artificial intelligence is expanding the potential information we might be able to glean from those images. Dr. Agus and his team are utilizing machine learning to extract clinical information about a tumor and patient from solely observing the structure and organization of the cancer. This is done with the goal of generating more meaningful and precise diagnoses. In addition, data sharing and biobanks of patient specimens are playing increasingly important roles in the research, diagnosis, and treatment of cancers. However, the patient samples and data within these biobanks have not been standardized or annotated in a universally accessible way, and relevant data elements can change over time. The work of Dr. Agus’ team may be able to fill in those gaps. 

Progress thus far

In Dr. Agus’ previous BCRF-supported work, he explored the possibility of revealing relevant clinical information using machine learning—to predict the status of certain disease biomarkers as well as nodal status from images of primary biopsies. He and his team successfully demonstrated the value of this approach and built a scalable computational pipeline to perform these types of analyses. Recently, they expanded this approach by reconstructing the three-dimensional architecture of the tumor. He and his team built and fine-tuned a machine learning pipeline to extract shape and appearance characteristics of cell nuclei from microscopic cancer tissue images. From these, they generated “social networks” of cancerous and noncancerous cells that can be fed into machine learning algorithms.  

What's next

Dr. Agus aims to develop a machine learning algorithm to identify tissue architectures that correlate to clinical observations. He then will validate the power of the algorithms to be clinically informative by comparing the algorithm’s predictions to the clinical records of a cohort of more than 400 cancer patients. These advancements could add tremendous utility to existing tissue collections to inform future research and treatments, and they could serve as a new diagnostic or prognostic tool. 


David Agus is professor of medicine and engineering at the University of Southern California, where he is the founding CEO of USC’s Lawrence J. Ellison Institute for Transformative Medicine. Dr. Agus leads a multidisciplinary team of researchers dedicated to the development and use of technologies to guide doctors in making health-care decisions tailored to individual needs, and directs a National Cancer Institute Physical Sciences in Oncology Center at USC.  He is a medical oncologist and an international leader in new technologies and approaches for personalized healthcare. He serves as a CBS News contributor. Dr. Agus’ first book, The End of Illness, was published in 2012 and is a New York Times #1 and international best seller, and subject of a PBS special. His second book, New York Times best-selling A Short Guide to a Long Life, was published January 2014, and his newest book The Lucky Years: How to thrive in the brave new world of health, also a New York Times bestseller was published in 2016.  He is a 2017 recipient of the Ellis Island Medal of Honor.

BCRF Investigator Since


Donor Recognition

The AutoNation DRV PNK Award