**Code used in this article is available here on my GitHub.

The Problem

The process of developing and releasing a new pharmaceutical is an absolutely tremendous feat. Oftentimes the first step in drug discovery is the testing of hundreds of thousands of candidate drugs in vitro through the use of high-throughput screening — automated processes that conduct simple pharmacological experiments in parallel on a drug target. As would imagine, this process is ridiculously expensive, time-consuming, and resource-intensive. Computational approaches that allow for the screening of drug candidates in silico are therefore highly sought after; this type of system could reduce the number…

Miraculously, we’ve come as a species to accept our own mortality. A fundamental part of our development into emotionally mature adults is the realization and understanding that all of us will one day cease to exist; our loved ones, our friends, our pets, anything and everything that lives, will die. The rationalization of this prospect and the way we individually come to realize this differs greatly from person to person — a family member will die, a pet will “run away,” or some variation on the theme, and maybe we believe we’ll see them again in paradise, or maybe they’re…

During my sophomore year of undergrad, I had the honor and privilege of working under the guidance of Professor Laurent Itti, PhD at the USC iLabs. It is here that I was given the opportunity to conduct research that I’d been dreaming of doing since high school: applying deep learning to electroencephalography (EEG). I was really happy with the results of the research, and I eventually presented at the Harvard National Collegiate Research Conference. I am pleased to write about my research here as well.

Introduction and Overview

The Viterbi iLabs had recently ordered two Emotiv EPOC portable EEGs, and I was allowed…


I’ve debated writing this article for a very, very long time. The mechanisms behind MRIs was one of the first articles I really wanted to write, but approaching and explaining this technology is quite different than other articles I’ve written. To understand why I’ve had difficulty writing this article, and before we get into the meat of how MRIs work, it may help to outline some comparisons between CT scans and MRIs. CT scans operate on very familiar and (relatively) intuitive principles: x-rays. A normal 2D x-ray is already well understood by most people — x-rays are blocked more by…

A while ago during my freshman year of undergraduate studies, I wrote a paper with my professor, Dr. Erin P.J. Pearse, detailing lengthy proofs on the relation between certain sequences of the trigonometric function cosine, and its relation to something known as the “irrationality measure” of 𝜋. A lot of my friends/peers get curious about this particular paper, because the bulk of it looks like unintelligible nonsense to the untrained eye. In reality, a lot of the concepts and results behind the paper are very approachable with as little as a high school level mathematics! …

Positron emission tomography is a modern day scanning tool often used to observe the metabolic processes of tissue in 3D. The scans the physician receives look quite similar to X-ray computed tomography (CT scans), but the mechanism behind each are quite different. Take a look at the PET scan below, showing levels of consciousness based on brain tissue metabolic activity.


Pulse oximetry (PulseOx) is fundamental to telemetry in modern hospitals. Having a real-time reading of SpO2 (oxygen saturation) allows physicians to get a rough understanding of respiratory function, as well as heart rate. As a bonus, PulseOx is quite cheap (you can buy one on Amazon for around $20) and can be done through a non-invasive clip-on device on either the fingertip or ear lobe.

PulseOx works by shining visible and infrared light through tissue and detecting the amounts of light that make it all the way through the tissue to the detector. This technique is known as absorption spectroscopy

Computed tomography (the CT or CAT scan) has become an absolutely fundamental tool in the modern diagnosis of disease. Unlike the X-Ray scan, which presents a two dimensional view of the general tissue density in a scanned region, a CT scan allows doctors to see a detailed 3D scan of a patient’s body, essentially peering into the body without exploratory surgery. Take a look at the image below to see the dramatic difference between a normal 2D X-ray (left) and a CT scan (right).

Image courtesy of EmergencyMD

The Principles Behind Computed Tomography

CT scans work by taking multiple X-rays and using the “overlapping” information to combine them into…

Questions related to this repository from a project I created almost three years ago are among the most numerous questions I receive. The repository itself is really nothing too special, just an implementation of an Nvidia paper that was released about a year prior. A graduate student later managed to implement my code in an actual full-sized car, which is really cool. The story behind my code’s creation is the interesting part.

My fascination with machine learning began in early 2015, when I stumbled across genetic algorithms and neural networks. Popular videos on YouTube showed virtual organisms seemingly magically evolving…

Sully Chen

Machine learning, mathematics, medicine. I do research in biotech.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store