You are here
Tracking Cancer Tumors Digitally
Northeastern University Associate Professor of Electrical and Computer Engineering Jennifer Dy is on a quest to reveal the mysteries of the body by programming computers to “learn” from the data they collect, ultimately helping physicians better treat tumors and early-stage skin cancers.
Dy, who has already received more than $1 million in research grants, including a prestigious National Science Foundation CAREER Award in 2004, is applying her expertise in machine learning, data mining, statistical pattern recognition and medical image analysis, to two highly interdisciplinary research projects.
Dy is collaborating with Associate Professor of Radiology Bin Jiang of the University of California-San Diego and Gregory Sharp of Massachusetts General Hospital’s radiation oncology department in an effort to build computer algorithms that can predict the movement of a tumor in the body, such as a lung tumor that moves as a patient breathes.
If that movement can be tracked and recorded in a computer so a predictive pattern emerges, physicians would be better able to pinpoint the location of the tumor at any time, and therefore, pinpoint treatment.
“The idea is that the radiation [treatment] can be targeted specifically at the cancer cells” and avoid healthy cells, she said.
In another major collaboration, Dy is working with an electrical and computer engineering colleague, Professor Dana Brooks, and Dr. Allan Halpern, with the dermatology department of Memorial Sloan-Kettering Cancer Center, on a project to improve the imaging—and early detection—of skin cancers.
The goal of the project, “3-D Segmentation and Classification of Skin Images from Confocal Laser Scanning Microscope,” is to detect the epidermis/dermis boundary—a hard-to-see area between skin layers where cancer develops, she said. “It’s not easy because different skin types look different in the images,” and skin images are often blurry.
Dy explained that she and her colleagues are developing data mining algorithms that will allow a computer to “learn” where skin cancer may lurk. They hope the computer algorithms lead to enhancement of image-tracking techniques, which, among other benefits, will improve the contrast and clarity of images.
Her work on this project is supported by the National Institutes of Health’s Center for Integrative Biomedical Computing.
Dy grew up in the Philippines, and earned her bachelor’s degree at the University of the Philippines in electrical engineering. She went on to earn her master’s and doctoral degrees in electrical and computer engineering from Purdue University.
For more information, please contact Susan Salk at 617-373-5446 or at email@example.com.