Pallavi Tiwari’s passion for biomedical engineering started in a garage in India.
When she and a college friend realized the difficulty people with blindness have in navigating their surroundings—especially indoors—they set to work in Tiwari’s garage, teaching themselves how to solder. They then designed, created, tested and honed a prototype of a device that could aid blind people in reaching their destinations with relative ease.
The device—called Divya Drishti, or divine sight—was a high-tech, low-cost, infrared-based system that guided the wearer along a route with the least obstruction, using path location and arrowhead receivers. If the wearer deviated from the infrared route, the sound beacon activated.
The pair took their device to IIT Techfest—now Asia’s largest science and technology festival—where they took home second place in their field.
“That led to me realize that this is my calling; this is what I want to do for the rest of my life,” she said. “I want to build something that will have an impact on people’s lives.”
And so, it was that system that led Tiwari to find her way into biomedical engineering.
Now, just over a decade later, she’s making that impact: Tiwari and a team of researchers created a computer program that was nearly twice as accurate as human neuroradiologists in determining whether abnormal tissue seen on magnetic resonance images (MRI) were benign cancer cells caused by radiation, or if brain cancer had returned. Typically, that determination is so difficult to make that it requires costly—and risky—biopsies.
“When I was finishing up my PhD, I started working with a neurosurgeon, who mentioned this problem with benign occurrences: They look like tumor progression, but they’re not,” Tiwari explained. “Once we realized how big of a problem this is, we thought we’d take a crack at using some of the computational techniques I’d been developing.”
Tiwari and her team employed machine-learning algorithms in conjunction with radiomics, the term used for features extracted from images using computer algorithms. They trained the computer to identify radiomic features that discriminate between brain cancer and benign cells, using routine follow-up MRI scans.
The team then developed algorithms to find the most discriminating radiomic features—in this case, those that can’t be seen by simply eyeballing the images.
The computer algorithm was correct on 80 percent of the scans; the human experts could correctly detect less than half of the time.
Now, Tiwari is co-principal investigator on a three-year, $200,000 Dana Foundation grant to evaluate the technique’s accuracy. If the approach is validated, it could become essential in the treatment and follow-up to brain cancer, reducing the need for unnecessary, dangerous brain biopsies—and helping patients, as Tiwari has always longed to do.
“Since I was young, I’ve always known I was an engineer,” she said. “Getting into biomedical engineering happened more as fate—but I am glad to have found a field that has allowed me to have an impact on people.”
Learn more about Tiwari in this week’s five questions.
1. What’s your favorite spot on the Case Western Reserve campus?
It would be Tinkham Veale University Center. When I am not in my office, you will find me and my laptop in one of the corners there. I love how open and accessible it is. I also really like the Michelson and Morley restaurant and frequently take my family there.
2. If you could live anywhere else in the world, where would you pick?
I would love to live in Shimla, India. Shimla is known for its colonial architecture and beautiful mountain ranges and is nicknamed “Queen of the hills.” I’m drawn to the image of myself working on research ideas while living up in those beautiful mountains.
3. What new skill would you like to learn?
I fantasize about learning to play the Tabla—an Indian percussion instrument—someday. But more practically, I would like to improve my tennis serve.
4. If you could only watch three movies for the rest of your life, what would they be?
Life is Beautiful, Forrest Gump and Udaan. I like movies that showcase the human spirit and how it can overcome seemingly insurmountable odds.
5. What’s your favorite thing about Case Western Reserve?
It’s the people. And I mean everyone—including students, faculty and staff. Case [Western Reserve] is very collaborative and passionate about research, and it shows through in the attitudes of people I work with. Although if I had to pick just one set of people, they would of course be my team! I look forward to working with such a bright and motivated cohort of researchers every day.