Developing algorithms and learning-based systems to support potentially life-saving biomedical devices is more than abstract research for Stevens Institute of Technology electrical and computer engineering assistant professor and senior IEEE member Negar Tavassolian.
"I've always been interested in solving medical problems with commercially viable technology," says Tavassolian, whose work is affiliated with the Stevens Institute for Artificial Intelligence. "I like to make things and see how they can help somebody."
Tavassolian was granted a National Science Foundation (NSF) CAREER Award to leverage millimeter-wave technology in her quest to use artificial intelligence and other emerging technologies to develop an innovative, portable dermatological application to create a high-resolution image of a patient's skin for early detection of skin cancers.
Millimeter-wave imaging (at a frequency of 30 to 300 GHz) is cheaper, safer, less power-intensive and much more portable than other types of body imaging. It can't penetrate deeply to internal organs, but it's ideally suited for superficial imaging. Tavassolian and graduate assistant Amir Mirbeik are splitting millimeter-wave bandwidths into smaller channels, then processing and reassembling the slices to create detailed images for medical diagnoses.
"The doctor will hold the device over the tissue to see whether a lesion is a malignant cancer or not," she explains. "Our technology provides in-depth visualization that can go up to two and a half millimeters deep into the skin to see a 3D profile of any tumor. Healthy skin has lower water content than a tumor, and the millimeter-wave-created image can detect that difference with higher contrast than currently possible. A lot of times, there's discoloration with a tumor, but around the discoloration are more cancer cells that you won't see with your eyes—but we can see with this technology. It's meant to ensure consistent, accurate care by reducing unnecessary biopsies and finding tumors earlier, and our goal is to make a device for $1,000, so every dermatologist can have one."
Tavassolian is also hunting for heartbeat irregularities by using tiny yet powerful motion sensors, strapped over people's chests or placed like an earbud in their ears. These sensors collect huge quantities of data, which are run through intelligent digital signal processing techniques that reduce or even cancel the impact of walking and breathing from the heartbeat signals. Machine-learning-driven algorithms differentiate the signals of healthy patients from those who may be at risk for heart attack, heart failure or hypertensive heart disease. Early testing with Columbia University Medical Center has demonstrated accurate classification up to 99.5 percent. Her doctoral student, Chenxi Yang, has published extensively on this technology in reputable journals as well as presented in various conferences.
"The device has a gyroscope and accelerometer that deliver data about linear and rotational motions of the chest wall," Tavassolian explains, "providing highly accurate heartbeat measurements that can provide an early, real-time warning for potential cardiovascular issues."
And if you don't want to–or can't–sport even a miniscule heart monitor, Tavassolian has a solution for you too. She and doctoral student Mehrdad Nosrati are developing technology to use low-cost, innovative Doppler radars to sense and measure heartbeats and respiration rates even in noisy, crowded settings, without ever touching the individual being monitored.
"If we can find heartbeat abnormalities in high-risk populations in real time, we could save lives," Tavassolian says. "We're increasing the capacity of radar detection using the same multiple-input and multiple-output signal processing that's used in cell phones, but has never been used before in radar. We've deployed the system to reach acceptable accuracy at roughly 4½ feet. So far, we're focusing on biomedical applications such as multiple heartbeats, but we see other applications, such as measuring velocity and scanning multiple lanes and vehicles at a toll gate."
Impressive as these applications are, Tavassolian doesn’t think of them as successful until they become commercially available. "I design everything with commercialization in mind," she says.
"I like to see results."
Professor Tavassolian joined Stevens Institute of Technology in 2013. Her research interests include electromagnetic modeling and optimization, bio-electromagnetics, antennas, mobile health and personalized healthcare. She is a senior member of IEEE and a technical program committee member of IEEE MTT-10 (Biological Effects and Medical Applications of RF and Microwaves). She has been honored with Stevens' Provost Early Career Award for Research Excellence, and earned the NSF CAREER award.