Biomedical engineer at Rochester Institute of Technology develops advanced AI techniques to improve disease diagnosis and medical decision-making

Rochester, New York – In a quiet lab tucked away at the Rochester Institute of Technology, a major shift in diagnostic medicine is taking shape—not through more machines or scans, but through better use of the data already in front of us. Cristian Linte, a professor of biomedical engineering at RIT’s Kate Gleason College of Engineering, is spearheading research that could change how doctors detect diseases and decide on treatments, using artificial intelligence (AI) and data science.

Linte and his research team are developing advanced AI techniques to extract deeper meaning from existing biomedical imaging—like MRIs, CT scans, and ultrasounds—that are already widely used in hospitals and clinics. Their goal is to help clinicians see more, understand more, and act with greater confidence, all while minimizing how invasive procedures need to be.

“The future of medicine is not necessarily about acquiring more data but rather having access to effective tools to make use of the data, and this is where biomedical computing plays a critical role,” said Linte.

Read also: State Police respond to evening two-vehicle crash that caused traffic delays in the town of Colonie

This statement reflects a larger movement within healthcare. Medical imaging has become the backbone of diagnosis and intervention, but making sense of those images still relies heavily on experience, interpretation, and subjective judgment. Linte’s work aims to make the process more objective and precise, letting machines assist doctors by analyzing massive sets of medical data and revealing patterns that are easy to miss with the human eye.

Linte’s team includes a dynamic group of imaging science doctoral students—Bipasha Kundu, Bidur Khanal, Zixin Yang, Nakul Poudel, and Richard Simon—who have been publishing results in leading academic journals, including SPIE Medical Imaging 2025. Their work is at the intersection of biomedical imaging, physics, computer science, and clinical application. But at the core of it all is a question: how can we better understand what’s already in front of us?

Medical images generate vast amounts of data. But without proper analysis tools, much of this data goes underutilized. Linte’s lab is developing methods to process this raw data—cleaning it up, organizing it, and feeding it into AI models that can detect subtle indicators of disease or suggest optimal treatment paths.

“Imaging accounts for the majority of biomedical data,” Linte said. “It has transformed diagnostic and interventional medicine from a subjective, perceptual skill based on physicians’ experience to an objective science driven by large-scale, heterogeneous data.”

One of the most promising aspects of Linte’s research is how it supports computer-integrated diagnosis and therapy, an emerging field that uses computational tools to help doctors make real-time decisions. These tools don’t just help diagnose a disease—they can assist in surgical planning, guide a robotic tool during an operation, or monitor patient progress after treatment.

Despite the promise, building reliable AI models in medicine isn’t easy. High-quality medical data is difficult to come by, and it often needs to be labeled by experts—a time-consuming and expensive process. There’s also the issue of user variability—differences in how doctors interpret images or describe symptoms—that makes it harder for algorithms to learn from consistent patterns.

“Many physics-based biomedical models are hampered by their computational expense, which constitutes a major setback to clinical adoption, limiting their use as interactive simulation tools for therapy planning or monitoring,” Linte explained. “AI techniques, on the other hand, can learn from large patient-specific datasets, so combining data science with physics-based models has the potential to yield more accurate and more computationally efficient simulations.”

Linte and his team are doing just that—combining the raw analytical power of AI with the precision of physics-based modeling to develop simulation tools that work faster and better. These tools could one day be used by surgeons to practice complex procedures virtually or by radiologists to catch early signs of disease that even experienced eyes might overlook.

The implications of Linte’s work reach beyond the academic walls of RIT. By improving diagnostic speed and accuracy, and by supporting less invasive therapies, patients could benefit from faster treatment, fewer complications, and better outcomes. These improvements could also reduce costs by avoiding unnecessary procedures and hospital stays.

“Effective utilization of biomedical informatics to develop versatile biomedical computing and visualization tools will lead to solutions that enable more accurate and timely disease diagnosis and less invasive therapies,” said Linte. “These tools will help lay a foundation for advances in computer-aided diagnosis and therapy across a wide spectrum of diseases and organ systems that can impact a larger patient population.”

Read also: Greater Rochester Chamber announces fourteen finalists who are leading the way in inclusive workplace leadership for 2025

To support this ambitious work, Linte’s lab—officially called the Biomedical Imaging, Modeling, Visualization and Image-guided Navigation Laboratory—has secured major funding from the National Institutes of Health (NIH) and the National Science Foundation (NSF). Most recently, he received a nearly $2.4 million grant from the NIH, a five-year competitive renewal to continue building biomedical computing tools and mentoring the next generation of engineers and researchers.

That mentorship is a key part of the lab’s mission. Many of Linte’s students have gone on to work at leading hospitals, research centers, and national laboratories.

“Mentoring and training high caliber students who will join tomorrow’s biomedical and academic workforce constitutes by far the greatest impact of our careers as academics and scientists and we’re thrilled to see them succeed,” said Linte.

With continued innovation and growing support, Linte’s team is positioned to shape the future of AI in medicine. Their work may not grab headlines in the way new machines or drugs do, but it sits at the foundation of a healthcare system that is smarter, more personalized, and less invasive.

By combining the power of data with the empathy and decision-making of human clinicians, Linte’s vision reflects the best of what technology and medicine can achieve together.

And in a world where time is often the difference between life and loss, those few extra insights hidden inside a scan could one day save thousands.