An exploration of compressed sensing fMRI time series with 3 different algorithms. Typically, compressed sensing reconstructs a single volume of MRI but fMRI are composed of many volumes; sensing along the time domain could reduce the number of volumes required. Of the 3 algorithms, BSBL-BO performed the best with the error curve elbowing around 30% subsampling.
This Fall 2021, I am taking a course on computational game theory, which insofar is the formulation of various games (e.g. bimatrix, Stackelberg) as mathematical programs and the algorithms that solve them, or approximate solutions. Linear complementarity problems are foundational for computing Nash equilibria of simple games.
StoneAnno is my first published first-authorship paper, presenting at SPIE 2022. With the long-term goal of fully-automated robotic endoscopic surgery, we built a dataset of endoscopic kidney stone removal videos and investigated U-Net, U-Net++, and DenseNet for the segmentation task. We found a U-Net++ model that consistently achieves >0.9 Dice score, with low loss, and produces realistic, convincing segmentations. Moving forward, I am implementing our model on hardware for deployment in ORs, as a part of my master’s thesis, and I helped Dr. Kavoussi submit an R21 grant in October 2021.
Although it will be published after
StoneAnno, this shape analysis is my first completed research project and technically my first first-authorship,
submitted to Brain. I wrote code in R and MATLAB to fit LMMs to the cortical data from T1w MRI of HD patients and then performed statistical analyses on the results using SurfStat and random field theory. We found that, with a novel method for measuring gyrification,
LGI uniquely detects changes in the insula.From knowing very little about webdev to a very small amount more, all in one place! The
Hugo hosting docs and
After Dark tutorial / docs are sufficient but unclear on the finer details. Here, I flesh those out to make this process as easy for prospective users as it truly should be.
Neural network automated verification of a VAE and SegNet using NNV. Although neural networks are promising, they are easily confused, particularly if the input domain is perturbed. In this project, I demonstrate the robustness of MNIST-trained VAE and SegNet against varying brightness attacks.
For most of my life, I’ve been writing poetry when I experience a lightbulb moment. Over time, this habit shapeshifted to mainly haiku & senryū, often composing sequences of 23 - 31 or more on a day out. Although they’re usually reluctant to share, the more people that I’ve met, the more I’ve discovered that also have this practice in one way or another. People are like onions; they have layers. If you peel back enough, you’ll reach the heart – haiku & senryū are the key to mine.