American Statistical Association
New York City
Metropolitan Area Chapter

Levin Lecture Series: Fall 2019 Colloquium Seminars
Department of Biostatistics
Mailman School of Public Health
Columbia University



Dr. Peng Zhang
Research Assistant Professor
Department of Surgery
University of Michigan

Host: Min Qian


Many body composition features, such as decreased muscle quality, decreased bone density, and increased central abdominal adiposity, are associated with an array of adverse clinical outcomes in the field of surgery, cancer, and many chronic diseases. Although the exact etiology and temporal pattern of these changes are not well-understood, these high-dimensional phenotypes can greatly improve our ability to quantify patients' heterogeneity and help develop better personalized risk profiling models and individualized treatment algorithms. However, majority of historical studies have been based upon manual segmentation of medical images. Therefore, it only allows investigation of mostly single determinant of body composition features. By leveraging advances in machine learning and deep learning, we have developed new statistical methods and software that extracts and indexes anatomical measurements from archival CT data and then records their location into 3D space. Granular information about individual geometry, tissue characteristics, and various organ properties are obtained through a semi-automated and high-throughput process. I will present several applications to demonstrate our proposed methods and algorithms.

Date: Monday, November 4, 2019
Time: 1:00 - 2:00 P.M.
Location: Mailman School of Public Health
Department of Biostatistics
722 West 168th Street
AR Building
6th Floor, Room 657
New York, New York

Home Page | Chapter News | Chapter Officers | Chapter Events
Other Metro Area Events | ASA National Home Page | Links To Other Websites
NYC ASA Chapter Constitution | NYC ASA Chapter By-Laws

Page last modified on November 1, 2019
Copyright © 1998-2019 by New York City Metropolitan Area Chapter of the ASA
Designed and maintained by Cynthia Scherer
Send questions or comments to