OVision - The Automatic Assessment of Ovarian Cancer Features & Mesothelin Protein Overexpression from Histopathological Images using Deep Learning
Samaira Mehta
Santa Clara, California
2022 Finalist
Stratford School - Sunnyvale Raynor Middle School
1500 Partridge Ave
Sunnyvale, CA 94087
8th grade | 13 years old
Ovarian cancer (OC) is the deadliest cancer of the female reproductive organs. 65% of ovarian cancer patients die each year in the United States alone. The best way to reduce that number is for doctors to develop a treatment plan that is specific to the patient and their condition. However, to provide patients with the best diagnosis, doctors need to accurately classify the OC subtypes: High-Grade Serous Carcinoma, Low-Grade Serous Carcinoma, Endometrioid Carcinoma, Mucinous Carcinoma, and Clear Cell Carcinoma. By simply looking at histopathological images, it is often difficult for pathologists to distinguish between the subtypes accurately. Samaira’s research project utilizes a Deep Learning Convolutional Neural Network, based on VGG-16, to classify ovarian cancer subtypes and detect whether mesothelin protein was overexpressed, based on histopathological images. Current platforms for uploading histopathological images and getting results on cancer types require a great deal of technical expertise. Aiming to change that, with this platform, any doctor can get access, and receive immediate, accurate results.
Why did you enter the Young Scientist Challenge?
The 3M Young Scientist Challenge is one of the leading science competitions for middle schoolers. I have a lot of confidence in my project and I truly believe it will aid doctors in precision medicine. However, as we continue to work at the intersection of AI and science to shape our future, I believe sharing our ideas is one of the best ways to learn, gain feedback, and grow.
What is your favorite invention of the last 100 years, and why?
AI has been around since the 14th century AD, but it wasn’t until 1955 that the term “Artificial Intelligence” was coined; to date, I would consider it my favorite invention in the last 100 years. AI is not only improving lives, it is saving them. If 20 years ago someone had asked, "What is the Internet, and how will it change the world?" the question could not have even been understood. What AI will do for us is even greater than what the internet has done so far. Learning AI will help users better comprehend the tools and systems used with ever-increasing frequency on a daily basis. Many people are using artificial intelligence to solve problems, cure diseases that were once considered incurable, or at least diagnose them faster. For example, cancer tests, like the Pap, use neural networks to look at an image of cells and decide whether or not there is a risk for cervical cancer. Similarly, my project, OVision, looks at histopathological images and detects which ovarian cancer subtype is present and whether or not there is an MSLN over-expression. People are using AI to revolutionize education, agriculture, and many other fields. I truly believe it is a very powerful tool that, when used correctly, can significantly facilitate human productivity. AI is shaping the world, but the upcoming generation--my generation-- is going to shape AI, one step and one project at a time.
In 15 years I hope to be...
I remain conflicted about where I see myself when I grow older and 15 years down the line when I will be 29. One part of me wants to go to Stanford University, study computer science/business, and by 29, be working on my tech startup in Silicon Valley. Another part of me wants to go to Columbia University and then Harvard Law School, study law, become a human rights lawyer, eventually run for (and become!) governor and then president of the United States. At 29, I will have, hopefully, passed the BAR exam and be starting my work as a human rights lawyer. One more part of me wants to go to MIT and become a scientist who, by 29, will be using the power of tech to work on cancer cures. Maybe I’ll be able to put these together someday. Maybe my tech startup would be working on cancer cures and eventually, I could be a tech entrepreneur, turn governor, and then president. All I know for sure is, whatever I do, I want to be able to make a positive contribution to society and an everlasting impact on the world.
Work while they sleep, learn while they party, live as they dream.”
Samaira Mehta