Efficient System Design for Cancer Detection and Treatment

About the Project

This project, "Efficient System Design for Cancer Detection and Treatment," has four major goals with the following specific activities:

Goal 1
Building ML-based Advanced Algorithms for Modeling Cancer Growth and Treatment: This goal focuses on developing sophisticated machine learning models that can accurately predict how cancer will grow and respond to different treatments. This could revolutionize personalized medicine by allowing doctors to tailor therapies to individual patients.

Specifically, this will include: Designing algorithms based on Physics Informed Neural Networks (PINN). PINNs incorporate physical laws and constraints (like tumor growth dynamics) into the machine learning model, potentially leading to more accurate and reliable predictions.

Goal 2
Designing ML-based Advanced Algorithms for Image Processing: This involves creating machine learning algorithms that can analyze medical images (like X-rays, MRIs, and CT scans) to detect and diagnose cancer more effectively. This could lead to earlier and more accurate diagnoses, improving patient outcomes.

Specifically, this will include: Developing algorithms for automatic counting of cancer cells on photos taken from built-in microscope cameras. This automation could significantly speed up analysis and improve accuracy in laboratory settings.

Goal 3
Creating Hardware Design for Classical and DL Based Cancer Classification: This goal aims to develop specialized hardware that can efficiently run both traditional and deep learning algorithms for cancer classification. This could speed up diagnosis and make it more accessible, particularly in areas with limited computing resources.
Goal 4
Making Education Plan for Interdisciplinary Education and Research in the foundations and the applications of Machine Learning in the Life STEM: This focuses on developing educational programs that train the next generation of scientists and engineers to apply machine learning to life sciences. This interdisciplinary approach will foster innovation and collaboration between fields.

Specifically, this will include:

  • Conducting summer and normal semester undergraduate research programs to provide hands-on experience.
  • Designing and piloting two new courses:
    1. "Mathematics for Machine Learning" to equip students with the necessary mathematical foundations.
    2. "IoT for Healthcare" to explore the applications of the Internet of Things in healthcare, including remote monitoring and data collection.

By pursuing these four goals with these specific activities, the project hopes to make significant contributions to the fight against cancer.

The project in NSF Website is this https://www.nsf.gov/awardsearch/showAward?AWD_ID=2318573

Methodology

Details about the methodologies used in the project.

Results

Summary of the results obtained from the project.

Conclusion

Final thoughts and future directions for the project.