USC Scientists Are Using Quantum Computing to Rethink Cancer Detection #
While many researchers are racing to prove what quantum computers can do faster than today’s machines, Amir Kalev is focused on a different question: How can quantum computing help doctors find cancer earlier, treat it more precisely and reduce human suffering? As lead quantum scientist at USC Viterbi’s Information Sciences Institute in the USC Stevens School of Computing and Artificial Intelligence and an adjunct research professor in USC’s Department of Physics and Astronomy in the USC Dornsife College of Letters, Arts and Science Kalev believes quantum computing could transform medical imaging, giving physicians more accurate information when diagnosing cancer and planning treatment.
“We chose to focus on healthcare because medical imaging is an area where precise predictions are essential,” Kalev said.
That conviction has led Kalev and his collaborators to develop new ways of combining quantum computing with artificial intelligence. Their latest research explores whether a hybrid quantum-classical approach can improve how AI analyzes medical images, laying the groundwork for future tools that could assist physicians in diagnosing and treating cancer.
The work is still in its early stages, but its potential is enormous.
Giving doctors a clearer picture #
Every day, physicians rely on MRI, CT and ultrasound scans to diagnose disease and plan treatment. Increasingly, they also rely on artificial intelligence to help interpret those images.
Before AI can help physicians decide how to treat a patient, however, it must perform a critical task called image segmentation.
The term sounds technical, but the idea is simple. Instead of merely identifying a tumor, image segmentation traces its exact outline, pixel by pixel, separating cancerous tissue from healthy tissue.
Those boundaries can make all the difference.
The more accurately doctors can see where a tumor begins and ends, the more precisely they can target radiation, plan surgery and measure whether treatment is working. Better segmentation can also reduce unnecessary damage to nearby organs, improving both outcomes and quality of life.
Kalev suspected that quantum computing could help AI produce those sharper boundaries.
To test the idea, he teamed with his former student, Naman Jain, who earned a master’s degree in quantum information science in 2025. Together, they created Quantum Feature Extraction, or QuFeX, a new quantum module designed to strengthen existing AI systems rather than replace them.
Their work culminated in the paper, “QuFeX: Quantum Feature Extraction Module for Hybrid Quantum-Classical Deep Neural Networks,” published in the journal “Quantum Science and Technology.”
“The real insight was the data problem,” Jain said. “In medicine, datasets are really small and often of very low quality. Traditional AI methods need massive amounts of data to be reliable. We wanted to see if quantum could close that gap.”
Doing more with less #
After developing QuFeX, Kalev and Jain integrated it into U-Net, one of the most widely used AI systems for analyzing medical images. The result was Qu-Net, a hybrid system that combines conventional artificial intelligence with quantum computing.
The researchers tested Qu-Net against a leading classical AI model on several image segmentation benchmarks, including medical datasets.
“What surprised us the most wasn’t just that it beat the classical baseline by roughly 7%, but that it did so using only about 250,000 parameters, compared to 1.5 million parameters for U-Net” Kalev said.
The finding suggests quantum-enhanced AI may be able to do more with far less. Qu-Net outperformed the classical model while using roughly one sixth as many parameters, a result that could lower computing costs, shorten training times and make advanced AI more practical for hospitals.
“The game we’re playing isn’t just about whether quantum is fast,” Jain said. “It’s whether it’s also efficient.”
More importantly, Qu-Net produced more accurate boundaries around suspicious tissue, giving physicians a clearer map of what should be treated and what should be left alone.
Turning research into better cancer care #
To move beyond the laboratory, Kalev has begun working with physicians at the Keck School of Medicine of USC to determine whether quantum-enhanced AI can improve clinical care.
The collaboration pairs Kalev with Dr. Eric Chang, chair of the Department of Radiation Oncology at Keck. Together, they are exploring whether quantum machine learning can speed one of the most critical steps in radiation treatment planning: outlining tumors and healthy organs before treatment begins.
“The most exciting aspect of this research is that it could begin to tackle the laborious processes involved in delivering radiation therapy, such as manual image segmentation of a patient’s organs and tumors,” Chang said.
The collaboration is already moving beyond the laboratory. The researchers soon plan to test their technology using simulated scans and real patient images. If those studies succeed, they hope to build a system that helps doctors update radiation treatment plans as tumors change over time.
Kalev’s long-term goal is even more ambitious: shrinking the time it takes to create a personalized radiation treatment plan from days to a single clinic visit, allowing patients to be scanned, have a treatment plan developed and begin therapy much more quickly.
Although cancer is the immediate focus, Kalev believes the technology could eventually improve many other forms of medical imaging, including brain disorders, cardiovascular disease and surgical planning. Beyond medicine, the same advances could strengthen computer vision systems used in autonomous vehicles and satellite imaging.
“For me, projects like QuFeX and Qu-Net aren’t about proving a theoretical physics concept,” Kalev said. “They are about the tangible, real-world impact of quantum technology on human lives.”
Published on August 11th, 2026
Last updated on August 11th, 2026