Pancreatic cancer is a highly lethal and incurable disease of which survival rates have not improved significantly in the past 40 years. If diagnosed during an early stage, pancreaticoduodenectomy surgery, chemotherapy, and radiotherapy are used to help treat the disease. Currently, MRI-guided radiotherapy is used to help shrink a tumor, however, due to inter-patient variability and infraction anatomical changes such as breathing, tumors don’t get treated effectively. Despite the benefits of being non-invasive, radiotherapy tools are not becoming popular due for pancreatic cancer to manual intervention, human error, and movement of the pancreas during treatment. Treatment administrators today are often forced to overshoot on the targeted pancreas to attempt controlling tumor size. My research proposes a novel artificial-intelligence based tool to automatically segment out the pancreas in real-time. With a balance between accuracy and efficiency, Pancreatic Cancer Deep Learning System (PCDLS) is able to segment out the pancreas in real-time for execution while a patient is getting treated. It reduces the radiation overlay to 4mm which can save millions of healthy cells, improve patient quality of care, and help cure this deadly disease. To confirm my research, I contacted over 253 doctors from leading institutions who were able to validate my problem statement and provide a “voice from the customer”. I have a 5-year future plan to globally commercialize my innovation, PCDLS, to couple it with an MRI machine to create an end-to-end system and create population-based screening protocols which involve going through the necessary FDA approval processes.
What inspired you (or your team)?
In the past years, I have deeply been moved by a family friend passing away from pancreatic cancer. In 2017, I challenged myself to take on the problem of pancreatic cancer head-on and find a solution. Last summer when I was visiting my brother, a college student in Boston, I got the opportunity to visit a nearby laboratory where I learned about pancreatic cancer. Surprising statistics like the low survival-rate and aggressiveness hooked me in. As a technology enthusiast, I was inspired by Steve Jobs and knew how he had passed away from pancreatic cancer. Over the Summer, I was also learning about machine learning and was curious to learn about the latest devices like the Alexa and Home. I posed a question for myself to see if I could use my knowledge in artificial-intelligence to combat a real-world problem. Thus, my project was born.