About

I am a Research Engineer and the project lead for BisQue, an open source NSF funded project in the UCSB Electrical and Computer Engineering Department. My research is centered around two main areas:

  • Computer Vision and machine learning applied to Biomedical, Materials Science, and Biology
  • Building large web-scale Machine Learning systems for image and video processing

If you are interested in joining the BisQue Team, we are always looking for motivated students so feel free to reach out.

Research

Automated Segmentation and Connectivity Analysis for Normal Pressure Hydrocephalus

We propose an automated method of predicting Normal Pressure Hydrocephalus (NPH) from CT scans. A deep convolutional network segments regions of interest from the scans, which are combined with MRI information to predict NPH. To our knowledge, this is the first method which automatically predicts NPH from CT scans, and incorporates diffusion tractography information for prediction.

3DMaterialGAN: Learning 3D Shape Representation from Latent Space for Materials Science Applications

We propose a 3DMaterialGAN network that is capable of recognizing and synthesizing individual grains whose morphology conforms to a given 3D polycrystalline material microstructure. The value of our algorithm is demonstrated with analysis on experimental real-world data, namely generating 3D grain structures found in a commercially relevant wrought titanium alloy, which were validated through statistical shape comparison.

Improving patch-based convolutional neural networks for MRI brain tumor segmentation by leveraging location information

In this paper, we introduce a novel method to integrate location information with the state-of-the-art patch-based neural networks for brain tumor segmentation. Our proposed ensemble also achieves better segmentation performance compared to the state-of-the-art networks in BraTS 2017 and rivals state-of-the-art networks in BraTS 2018.

BisQue for 3D Materials Science in the Cloud: Microstructure–Property Linkages

In this work, we develop a module for BisQue that enables microstructure-sensitive predictions of effective yield strength of two-phase materials. The capabilities of the module for rapid property screening are demonstrated in case studies with two different methodologies based on datasets containing 3D microstructure information from (i) synthetic generation and (ii) sampling large 3D volumes obtained in experiments.

ML Systems

BisQue Architecture. BisQue is built on popular open source projects such as Python, Kubernetes, NumPy, and many others!

The BisQue platform allows the students in our lab to deploy the ML and computer vision methods they develop for researchers around the world to use. One of the main issues in our community is the lack of reproducible code–it works on my machine, it should work on yours.