Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Search Publications by: Derek Juba (Fed)

Search Title, Abstract, Conference, Citation, Keyword or Author
Displaying 1 - 6 of 6

Trojan Detection Evaluation: Finding Hidden Behavior in AI Models

October 10, 2020
Michael Paul Majurski, Derek Juba, Timothy Blattner, Peter Bajcsy, Walid Keyrouz
Neural Networks are trained on data, learn relationships in that data, and then are deployed to the world to operate on new data. For example, a traffic sign classification AI can differentiate stop signs and speed limit signs. One potential problem is

3D Cellular Morphotyping of Cell Niches

August 31, 2017
Stephen J. Florczyk, Mylene H. Simon, Derek Juba, Patrick S. Pine, Sumona Sarkar, Desu Chen, Paula J. Baker, Subhadip Bodhak, Antonio Cardone, Mary C. Brady, Peter Bajcsy, Carl G. Simon Jr.
Three-dimensional (3D) cellular morphotyping is introduced for assessing and comparing the niches provided by biomaterial scaffolds. Many scaffold systems have been advanced to provide synthetic cell niches for tissue engineering and drug screening

Acceleration and Parallelization of ZENO/Walk-on-Spheres

June 1, 2016
Derek Juba, Walid Keyrouz, Michael V. Mascagni, Mary C. Brady, Michael Mascagni
This paper describes our on-going work to accelerate ZENO, a software tool based on Monte Carlo methods (MCMs), used for computing material properties at the nanoscale. ZENO employs three main algorithms: (1)Walk on Spheres (WoS), (2)interior sampling, and

3D Segmentation of Stem Cells from Thousands of Confocal Microscopy Images

March 1, 2016
Peter Bajcsy, Mylene H. Simon, Stephen J. Florczyk, Carl G. Simon Jr., Derek Juba, Mary C. Brady
We address the problem of estimating 3D segmentation performance when segmentation is applied to thousands of confocal microscopy images (z-stacks) of cells. With a very large number of z-stacks, manual inputs to validate each segmentation result are

Survey Statistics of Automated Segmentations Applied to Optical Imaging of Mammalian Cells

January 8, 2016
Peter Bajcsy, Antonio Cardone, Joe Chalfoun, Michael W. Halter, Derek Juba, Marcin Kociolek, Michael P. Majurski, Adele P. Peskin, Carl G. Simon Jr., Mylene H. Simon, Antoine Vandecreme, Anne L. Plant, Mary C. Brady
The goal of this survey paper is to overview cellular measurements using optical microscopy imaging followed by automated image segmentation. The cellular measurements of primary interest are taken from mammalian cells and their components. They are