Leslie Zatz, radiologist who designed a framework for imaging informatics, dies at 91

Zatz was a radiologist ahead of his time, envisioning the framework behind some of today’s most advanced practices in radiology and AI-powered diagnostics.

Leslie Zatz

Leslie Zatz, MD, professor emeritus of radiology at the School of Medicine, died Feb. 21 at his home in Palo Alto. He was 91.

The cause was cancer, said his son, Jonathan Zatz.

Zatz became an assistant professor of radiology at Stanford in 1962 and a full professor in 1973. During his time at the university, he was a leader in the clinic and served in administrative roles — even after he had become emeritus.

Zatz was known for his keen interest in radiology informatics and his leadership in implementing a then-new, rigorous system of standardizing the way radiologists reported data in the clinic — a system that, today, provides the fundamental framework for artificial intelligence in image-based diagnostics.

 “Leslie’s contributions to radiology were invaluable to our progress in artificial-intelligence-based image diagnostics,” said Lloyd Minor, MD, dean of the School of Medicine. “Leslie’s innovative work will forever serve as a foundation for this aspect of patient care as it benefits countless people around the world.”

Those who worked with him saw him as a forward thinker. “Les was far ahead of his time,” said Daniel Rubin, MD, professor of biomedical data science. “He was a visionary in recognizing the opportunity of mining historical radiology reports for medical discovery and clinical quality improvement.”

Road to radiology

Zatz was born in Schenectady, New York, in 1928. He attended Union College in Schenectady, then moved a half-hour down the road to earn his medical degree at Albany Medical College. He completed an internship at the University of Chicago in 1953 before joining the Air Force for two years. He returned to medicine at the University of Pennsylvania, where he completed his residency with a focus on radiology, and earned a master’s degree in medicine. Zatz then came to Stanford, starting as an instructor in radiology. Fourteen years later, he became a full professor, a title he held for 17 years. Zatz also served as chair of the radiology resident selection committee and of the institutional grant committee.

During his time at Stanford, Zatz designed and implemented the first “structured reporting” in radiology. At the end of each patient report, radiologists assigned a code signifying whether the case was normal, abnormal or critically abnormal. It was originally designed to help clinicians determine the best course of follow-up.

“In the last few years, however, Zatz’s system has been a vital part of our artificial intelligence research program,” said Curtis Langlotz, MD, PhD, professor of radiology and of biomedical informatics research as well as director of the Stanford’s Center for Artificial Intelligence in Medicine and Imaging. AI enables machines to recognize abnormalities on images. “These machine learning methods require large numbers of labeled training examples. Thanks to Les, Stanford has a treasure trove of millions of imaging studies with labels attached.”

Outside of research and academia, Zatz enjoyed skiing, camping and hiking. He played the clarinet, recorder and harmonica, and he enjoyed a good game of bridge. 

His wife of 61 years, Marilyn Zatz, died in 2015.  He is survived by their three children: Sherilyn Ward, Daniel Zatz and Jonathan Zatz.

Memorial services will be private. Donations in Zatz’s memory can be made to the Sierra Club or to a charity of choice.



Stanford Medicine integrates research, medical education and health care at its three institutions - Stanford University School of Medicine, Stanford Health Care (formerly Stanford Hospital & Clinics), and Lucile Packard Children's Hospital Stanford. For more information, please visit the Office of Communication & Public Affairs site at http://mednews.stanford.edu.

COVID-19 Updates

Stanford Medicine is closely monitoring the outbreak of novel coronavirus (COVID-19). A dedicated page provides the latest information and developments related to the pandemic.

Leading In Precision Health

Stanford Medicine is leading the biomedical revolution in precision health, defining and developing the next generation of care that is proactive, predictive and precise.