Age: 17Herndon, VA
Project Title: MRI Image Synthesis for the Diagnosis of Parkinson's Disease using Deep Learning
Parkinson's disease is the second most common neurodegenerative disorder and affects millions of patients across the world. Unfortunately, due to the lack of concrete, objective diagnostic tools, the disease is not diagnosed until its later, irreversible stages. Neeyanth's project, PDGAN, presents the first automatic diagnosis system for Parkinson's disease from an MRI scan with a 96.6% accuracy. The end-to-end system also has the capability to synthetically generate lifelike MRI images to aid future research attempts at understanding Parkinson's Disease. PDGAN integrates powerful technology to assist neurologists and Parkinson's Disease patients with the diagnosis and their lives.
Neeyanth Kopparapu is a 17-year old student at Thomas Jefferson High School for Science and Technology from Herndon, Virginia. Neeyanth's lifelong passion for mathematics and computer science paired with his curiosity of medical problems allowed him to develop a passion for computational biology. Neeyanth enjoys collaborating with peers to work together to solve biological problems and make a positive impact on society. Neeyanth is excited and humbled to be recognized as a 2019 Davidson Fellow. He is incredibly grateful to the Davidson Institute for this recognition of his work in artificial intelligence, and is looking forward to meeting other Fellows and becoming part of the Davidson community.
Neeyanth's project presents an end-to-end pipeline to assist neurologists with the diagnosis of Parkinson's Disease through MRI scans. Diagnosing at a 96.6% accuracy, the system provides a robust second opinion for neurologists to give potential Parkinson's Disease patients.
Neeyanth's project, PDGAN, improves on the current diagnosis pipeline by identifying a crucial problem: the inherent post-symptomatic diagnosis that Parkinson's Disease patients are often given, and many are diagnosed too late for common treatment to be effective. PDGAN is able to diagnose early-stage patients accurately, quickly, and affordably. To be a robust diagnosis machine, PDGAN utilizes state-of-the-art image processing and generation techniques to synthesize life-like MRI scans to aid its diagnosis. Neeyanth was driven to tackle this problem after his grandfather was given a late diagnosis of Parkinson's Disease and is now unable to use common medication to treat the disease.
Neeyanth was met with adversity while completing his project. Neeyanth had to adapt his work to be usable for MRI scans around the world, regardless of quality and price. Although traditional deep learning frameworks are unable to justify their decision, Neeyanth worked to ensure there was biological explainability to the work he had done. Throughout all of his work, Neeyanth valued the tremendous help of the research community. From gathering a diverse starting dataset for his project through a research contract with the University of Southern California, or having conversations with Mr. Mark Hannum of Thomas Jefferson High School and Dr. Gil Alterovitz of Harvard University to find solutions to the many problems Neeyanth faced during his research, Neeyanth learned the invaluable lessons of collaboration and teamwork during his research.
Neeyanth's project helps improve the lives of millions of potential Parkinson's Disease patients by providing an avenue for a quick and accurate early-detection system. PDGAN not only provides help for so many patients and neurologists with a end-to-end diagnosis pipeline, but it also contains tools for future researchers in the field of Parkinson's Disease including a generative model capable of synthesizing new MRI images. PDGAN is a part of movement for a more computer-based attempt at helping millions of patients with neurological diseases like Parkinson's Disease have a future.
As a rising senior at Thomas Jefferson High School for Science and Technology, Neeyanth has benefited from many advanced STEM resources, classes, and teachers. At TJ, Neeyanth took classes like Artificial Intelligence, Computer Vision, Multivariable Calculus, and Differential Equations in addition to his future work in the Neurological Research Lab in the 19-20 school year. He credits attendance at TJ to many of his accomplishments, as he had countless resources in STEM, from passionate teachers to advanced laboratory equipment to in-depth classes in computer science, biology, and mathematics.
For his artificial intelligence projects, Neeyanth was recognized as a Conrad Spirit of Innovation Challenge First Place Winner, and Third Award Winner at Intel ISEF. He has presented his work at conferences including the NVIDIA GPU Technology Conferences in San Jose and DC, as well as the The AI Conference in New York City and the Tom Tom Applied Machine Leaming Conference in Virginia. Outside of research, Neeyanth is a captain of the Math Team and Senior Computer Teams at Thomas Jefferson, two of the biggest STEM clubs. Neeyanth loves working with his classmates as he competes in international math and computer science competitions across the nation. Neeyanth is a four time USA(J)MO qualifier and USACO platinum competitor.
As a co-founder of GirlsComputingLeague, a non-profit organization dedicated towards bridging the diversity disparity in computer science. Neeyanth works to host events for hundreds of students in a variety of topics, ranging from basic HTML concepts to machine learning frameworks. In the future, Neeyanth hopes to continue his avid advocacy for diversity and inclusion in the STEM fields and make a difference through medical research. In his free time, Neeyanth loves playing card games with his friends and family, watching Friends and playing lacrosse.
Where do you see yourself in 10 years?
I hope to complete college majoring in computer science (and potentially mathematics) and work at a small health-tech startup with large potential societal impact.
If you could have dinner with the five most interesting people in the world, living or dead, who would they be?
Yann LeCun, Stan Lee, Matthew Perry, Peng Yiliang, Augustin-Louis Cauchy
If you could be on any TV show, which one would it be?
I would love to be on Psych - the wittiness and of James Roday and Dule Hill would be inspiring in real life.
In the News
Neeyanth Kopparapu and Siona Prasad each awarded $25,000 as 2019 Davidson Fellow Scholarship Winners
Fairfax, Va. – The Davidson Institute for Talent Development has announced the 2019 Davidson Fellows Scholarship winners. Among the honorees are Neeyanth Kopparapu, 17, of Herndon and Siona Prasad, 18, of Vienna. Only 20 students across the country are recognized as scholarship winners each year.
“I am incredibly grateful to the Davidson Institute for this recognition of my work in artificial intelligence,” said Kopparapu, a rising senior at Thomas Jefferson High School for Science and Technology in Alexandria. “I am looking forward to meeting other Fellows and becoming part of the Davidson Fellows Scholarship community.”
Kopparapu’s project, MRI Image Synthesis for the Diagnosis of Parkinson's Disease using Deep Learning, presents the first automatic diagnosis system for early-stage Parkinson's disease from an MRI scan with a 96.6 percent accuracy. Kopparapu was driven to tackle this problem after his grandfather was given a late diagnosis of Parkinson's Disease and is now unable to use common medication to treat the disease.
Click here to download the full press release
Click the image to download hi-res photos of Neeyanth:
Started in 1999, the Davidson Institute for Talent Development is a 501(c)3 private operating foundation. Our mission is to recognize, nurture and support profoundly intelligent young people ages 18 and under, and to provide opportunities for them to develop their talents to make a positive difference.
Profoundly gifted students are those who score in the 99.9th percentile on IQ and achievement tests. Read more about this population in this article.