Google Summer of Code - Monica's Introduction
About Me
My name is Monica and I am currently an undergraduate student at Harvey Mudd College (located in the beautiful Southern California).
I am joining the Whitaker Lab as a part of the Google Summer of Code program.
My interests for computer science are very recent - a year ago, I had wanted to be a surgeon!
I have discovered so many useful computer science applications for the medical field.
Through working with the tedana library, I hope to assist in denoising fMRI data, and dive deeper into the real life applications of CS!
Outside of the combinations of CS + medicine, I am also very interested in computer systems engineering!
During my free time, I like to explore trendy food places and take pictures of them (I need to learn how to edit photos though)!
Hometown
I lived in Shenzhen, a city in China that connects Hong Kong and the mainland, for 8 years. I then moved to the states. Specifically, I moved to the Bay Area into the San Mateo district. The location was wonderful, as it was close to both San Francisco and San Jose, and there is a vast array of places to be explored.
Google Summer of Code (GSoC)
Why GSoC?
Open source is intimidating - especially for someone who has never helped develop a product used by others. What if something breaks and I’m responsible for that? (Of course, there are code reviews… but still!) GSoC enables me to make a contribution to open source world. The program is amazing in that I am paired up with mentors, and could connect to a community that will actively help.
I am in awe of contributors who dive into the world themselves, but I am thankful for GSoC in that I will be guided along the way.
Nonetheless, I am ready to learn from this experience and become a regular contributor in the open source world!
Why tedana and what do I want to achieve?
I am excited about helping tedana because it is a very small, personal project.
The science and process behind it is very specific (and difficult to understand).
The reason why I chose tedana is because I have always been practicing Test-Driven Development whether in school or in my own projects, and utilizing the skills in the real world, on an actual library, is something I wanted to experience.
I have taken multiple machine learning classes, and reading about the progress in machine learning in medical imaging piqued my interests in the other steps of the pipeline. How does one make sure that the data fed into machine learning is good, with no noise?
That is exactly what tedana does! tedana denoises the data from multi-echo fMRI, and produces clean data that is useful for statistical analysis.
Of course, this will be helpful for neuroscientists, but it is also a step for analyzing medical data with machine learning (which is groundbreaking).
From this summer, I wish to achieve a couple of things:
- Learn about the awesome and neat science behind multi-echo fMRI
- How this library could be advanced in the future, should there be a new publication about denoising ME fMRI data
- Adding lots and lots of tests to the library so that contributors in the future could extend the library without worries
- Familiarizing myself with open source, and continue adding onto libraries as a regular contributor!