Ph.D. student in Electrical and Computer Engineering
San José, CA
B.Sc. and M.Sc., Massachusetts Institute of Technology
“I’m a Princeton engineer because the Princeton engineering community is rich with opportunities for interdisciplinary collaboration.”
A first-year student, Sayeri works at the intersection of signal processing and machine learning. In her previous research, she studied methods to improve the quality of fetal brain MRI scans. Because fetuses are constantly moving, scans might be degraded by motion artifacts, impairing their readability. Also, these evaluations are complicated by the fact that fetal brains can be in any stage of development.
To help radiologists better assess if a fetus is at increased risk for neurodevelopmental disabilities, she trained a convolutional neural network, a type of artificial intelligence algorithm, to automatically assess the quality of assess and improve the quality of fetal brain MRI.
Sayeri came to Princeton because of the “strong electrical engineering and computer science departments, as well as the Princeton Neuroscience Institute.” She was looking for a program that “allowed that interdisciplinary collaboration.”
She likes that the campus environment and town of Princeton are not stressful. She enjoys stepping outside to take walks, which is mentally calming. For her, it’s not whether an environment is urban or not that is an important factor. It’s more important that there is a strong intellectual community—which is where she feels Princeton clearly excels.
During her undergraduate degree, she studied both computer science and electrical engineering, which allowed her to combine algorithms and signal processing. Her signal processing background helped her gravitate toward research that was more multidisciplinary, which was a key reason she came to Princeton.
Path to Princeton
She initially became interested in engineering when she joined the programming team for the FIRST Robotics Competition during high school.
During those four years, she had the opportunity to get exposure to electrical engineering and work with engineering mentors who encouraged her to study challenging college-level topics such as proportional-integral-derivative (PID) controllers. From this, she learned how to program machines using these types of algorithms.
She learned computer vision algorithms that program robots to recognize objects needed to perform a given task. This opportunity excited her about artificial intelligence, which lead her to study computer science and electrical engineering at MIT with a focus on AI and machine learning.
Sayeri enjoys taking part in the free yoga that is available on campus at Dillon gym. She also participates in on-campus activities like Diwali celebrations. Off-campus, she practices Kathak, a style of North Indian classical dance.
Awards and affiliations
National Science Foundation (NSF) Honorable Mention 2019
Tau Beta Pi, Eta Kappa Nu, Sigma Xi
Society of Women Engineers, IEEE member
Selected presentations and publications
S. Lala, N. Singh, B. Gagoski, E. Turk., P. E. Grant, P. Golland, E. Adalsteinsson. “A Deep Learning Approach for Image Quality Assessment of Fetal Brain MRI,” Proceedings of the 2019 Joint Annual Meeting ISMRM-ESMRMB, May 2019.
S. Lala, M. Shady, A. Belyaeva, M. Liu. “Evaluating Mode Collapse in Generative Adversarial Networks,” Proceedings of the 2018 IEEE High Performance Extreme Computing Conference, Sept. 2018.
S. Lala, B. Gagoski, J. N. Stout, B. Zhao, B. Bilgic, E. P. Grant, P. Golland, E. Adalsteinsson, “A Machine Learning Approach for Mitigating Artifacts in Fetal Imaging due to an Undersampled HASTE Sequence.” Proceedings of the 2018 Joint Annual Meeting ISMRM-ESMRMB, Jun. 2018.