Adrian Celaya

About Me

I am currently a Ph.D. student in the Department of Computational and Applied Mathematics (CAAM) at Rice University in Houston, TX. My research focuses on developing novel techniques for 3D medical image segmentation. Previously, I served as the Information System Security Manager onboard the U.S. Navy aircraft carrier USS Carl Vinson. After leaving the Navy in August 2020, I became a research assistant in the Department of Imaging Physics at The University of Texas MD Anderson Cancer Center.

Research Interests

  • Optimization
  • Numerical linear algebra
  • Scientific computing
  • Biomedical image segmentation
  • Deep learning

Current Research Topics

PocketNet: A Smaller Neural Network for 3D Medical Image Analysis

Ground truth Model prediction (~150K parameters)

The automatic segmentation of medical images aims to associate a pixel to a label within a medical image without human interaction. Convolutional neural networks (CNNs) and deep learning have helped facilitate enormous strides in the efficacy of automatic segmentation for medical imaging over the last several years. However, modern deep learning paradigms for 3D medical image segmentation are computationally expensive, often requiring high-end computing resources and several days of training time on those resources. My research explores ways to reduce this computational cost while also preserving segmentation accuracy. By exploiting similarities between CNNs and numerical discretizations for solving partial differential equations, we can create neural networks capable of achieving comparable segmentation accuracy to conventional CNNs while requiring substantially fewer parameters. The figure above highlights the results of our model for the task of labeling a brain tumor (shown in red). A preprint of these results is available here.

Publications and Presentations

Publications

PocketNet: A Smaller Neural Network for 3D Medical Image Analysis
Celaya, A., Actor, J. A., Muthusivarajan, R., Gates, E., Chung, C., Schellingerhout, D., Riviere, B, and Fuentes, D.
Under review, 2021
Correlation Between Image Quality Metrics of Magnetic Resonance Images and Neural Network Segmentation Accuracy
Muthusivarajan, R., Celaya, A., Yung, J., Chung, C., and Fuentes, D.
Under review, 2021
Technical Note: An efficient MR image data quality screening dashboard
Gates, E., Celaya, A., Suki, D., Schellingerhout, D., and Fuentes, D.
Under review, 2021
Cellular Density in Adult Glioma, estimated with MR imaging data, has prognostic power approaching WHO histological grading in a cohort of 1,181 patients
Gates, E., Suki, D., Celaya, A., Weinberg, J., Prabhu, S., Sawaya, R., Huse, J., Long, J., Fuentes, D., and Schellingerhout, D.
Under review, 2021

Presentations

Small Convolutional Neural Networks for Efficient 3D Medical Image Segmentation
Celaya, A., Actor, J. A., Muthusivarajan, R., Gates, E., Chung, C., Schellingerhout, D., Riviere, B, and Fuentes, D.
63rd American Association of Physicists in Medicine Annual Meeting, July 2021
Imaging Based Prediction of Proliferative Foci as a Target for Surgical Intervention Across Glioma Grades
Gates, E., Celaya, A., Suki, D., Weinberg, J., Prabhu, S., Fuentes, D., and Schellingerhout, D.
63rd American Association of Physicists in Medicine Annual Meeting, July 2021
Automated Cerebrospinal Fluid ROI Selection on Brain Magnetic Resonance Images
Gates, E., Celaya, A., Schellingerhout, D., and Fuentes, D.
Keck Research Conference, October 2020

Contact Me

  • Houston, TX
  • aecelaya@rice.edu
  • aecelaya@mdanderson.org