Faster, Better, Stronger: Speeding up Medical Imagery

By: Craig Kubicek, CIS Compliance Associate
craigkubicek@cis-partners.com

It is absolutely amazing to think about what computers can do nowadays. They allow us to stay in contact with others, check our bank accounts, read the news, follow our favorite teams, etcetera, etcetera.

Our lives have become so easy as we sit down in front of our computers to perform our jobs. However, I am not here to make you read about how personal computing has shaped our lives. I would like to touch on a topic that not many of us stop to think about, or for that matter, care about: Computing for Researchers.

Computers have become such a staple of our lives that even researchers rely on them. However, researchers are power hungry and require many computers linked up to provide them enough processing power to perform their biological researched functions and mathematical calculations. Fortunately, a corporation named Nvidia has created a huge breakthrough in the realm of supercomputers.

Nvidia’s specialty is Graphical Processing Units (GPU’s). Just recently, Nvidia produced the Tesla, which brings supercomputing to the level of personal computing. A supercomputer can now sit on a desk, instead of taking up a whole room. The concept is quite simple. The Tesla GPU is used inside a computer to reduce the amount of calculations and graphics processing that the Central Processing Unit (CPU) must perform. By taking away this heavy load of instructions, the CPU is given some room to breathe. Actually, lots of room to breathe.

What does this mean for the world? It means that the possibilities are becoming endless. Researchers can “simulate the delivery of novel nanoparticle chemotherapy drug to cancerous tissue. Simulation allows scientists to predict experimental outcomes and thus reduce the cost of development and time to clinical relevance.” [i] Boston Scientific, a worldwide producer of medical devices, also needs to simulate its products for results. With the use of Nvidia’s Tesla GPU it was able to process its simulations 25 times faster.[ii] It is not all about simulating things faster, “these advances also foster the development of new algorithms for simulating biomedical processes inside the body.” The ability to have a computer perform operations faster means that analyzing protein syntheses and chemical structures can occur quicker.

The more companies like Nvidia that can cut down on computational time, the better. "Time on a supercomputer can be extremely difficult to get, especially since some of our computations run for weeks to months. Also, buying a supercomputer is expensive for every university research group," said Axel Kohlmeyer, associate director at the Center for Molecular Modeling at the University of Pennsylvania. Kohlmeyer and the research team were able run their “molecular dynamics algorithms up to 100X faster and more importantly run bigger and more complex simulations and do research that was impossible to do before.”[iii] Of course, only with the help of Nvidia’s Tesla GPU.

No, I am not, nor have I ever been a Nvidia salesman, but I must confess that new innovations in technology have always thrilled me. It is exciting to think that clinical trials, medical procedures, cancer research simulations and much more can be sped up with only a desktop computer. Here’s to the future.

[i] http://www.accelereyes.com/success_story/drug_delivery_model.php
[ii] http://www.nvidia.com/object/acceleware_boston_scientific.html
[iii] http://www.reuters.com/article/pressRelease/idUS106675+04-May-2009+PRN20090504