Monitoring wound healing remains a significant challenge for clinicians. Traditional methods, like visual inspection and manual measurements, are often subjective and lack the precision needed to fully understand the complex biological processes at play. Biopsies, even as informative, are invasive and unsuitable for repeated assessments. Now, a collaborative effort between Duke University and Nokia Bell Labs is offering a fresh approach: an artificial intelligence-driven optical coherence tomography (OCT) imaging system that promises to objectively track wound healing with unprecedented detail.
The technology, detailed in a recent study published in Cell Biomaterials on March 20, combines the high-resolution imaging capabilities of OCT – commonly used in ophthalmology to visualize the retina – with the analytical power of AI. This allows researchers to not only visualize tissue structure and blood flow beneath the skin’s surface but also to quantitatively assess the progress of healing over time. The system is already yielding insights into how biomaterials can be optimized to promote more effective tissue regeneration, specifically demonstrating that a stiffer hydrogel formulation enhances initial wound closure.
“Wound healing is a complex process, and what we see on the surface doesn’t always reflect what’s happening underneath,” explained Sharon Gerecht, chair and the Paul M. Gross Distinguished Professor of Biomedical Engineering at Duke University. “For more than a decade, my lab has developed hydrogel-based therapies to guide tissue healing and regeneration. Partnering with Nokia Bell Labs allowed us to combine advanced optical imaging and AI, giving us unprecedented insights into how biomaterials induce healing beneath the surface.”
Beyond Visual Inspection: The Power of OCT and AI
Optical coherence tomography works by using light waves to create cross-sectional images of tissue, similar to an ultrasound but with much higher resolution. While OCT has long been a mainstay in ophthalmology – the National Eye Institute explains its use in diagnosing and monitoring retinal diseases – adapting it for wound healing required overcoming several hurdles. The primary challenge was translating the rich data generated by OCT into meaningful biological information.
“Turning those rich scans into meaningful biological insights requires more than imaging alone,” researchers noted. “Parsing through the information demands quantitative tools that can rapidly interpret large volumes of complex data.” What we have is where the collaboration with Nokia Bell Labs proved crucial. Over a multi-year project, researchers at Nokia Bell Labs developed a custom OCT system and AI-driven analytical methods specifically trained on imaging datasets generated in Gerecht’s lab. This platform automates the quantification of tissue structure and vascular dynamics, providing an objective measure of healing progress.
Hydrogel Stiffness and Wound Regeneration
To validate the technology, the team applied it to wounds in mice treated with a hydrogel developed at Duke. Hydrogels are water-based materials often used in wound care to provide a moist environment conducive to healing. The researchers compared hydrogels with varying mechanical properties – specifically, differing levels of stiffness – to determine their impact on the healing process.
Over two weeks, the OCT-AI platform provided a detailed look at the formation and maturation of granulation tissue, the initial tissue that fills a wound. The data revealed that the stiffer hydrogel promoted faster formation of granulation tissue and accelerated the transition to fully regenerated tissue. This finding suggests that the mechanical properties of biomaterials play a critical role in guiding tissue regeneration.
“With our developmental technology, we were able to monitor the blood flow near the wound and collectively understand the structural and vascular changes that were happening in real-time,” said Jiyeon Song, a postdoctoral researcher in Gerecht’s laboratory and co-first author of the paper. “The AI helped us quantitatively track those changes and acquire more objective results rather than us trying to manually analyze the images ourselves.”
Looking Ahead: From Mouse Models to Clinical Applications
While the OCT-AI platform has demonstrated promising results in a mouse model, researchers emphasize that significant work remains before it can be translated into clinical practice. The current system is a proof-of-concept, and further development is needed to adapt it for use in humans and to expand its predictive capabilities.
The team is particularly interested in applying this technology to predict the healing of chronic wounds, such as those commonly seen in patients with diabetes. Diabetic wounds are notoriously difficult to heal and often lead to complications like amputation. According to the American Diabetes Association, approximately 15% of people with diabetes develop a foot ulcer, and these ulcers can have devastating consequences.
Gerecht and her team are actively seeking funding to further develop the system and conduct clinical trials. The ultimate goal is to create a non-invasive tool that can accurately assess wound healing, predict potential complications, and guide treatment decisions, ultimately improving outcomes for patients with both acute and chronic wounds.
This research was supported by the P30 Cancer Center Support Grant (P30 CA014236), the American Heart Association, the Duke Regeneration Center (DRC), Duke Science and Technology (DST), and Nokia Bell Labs.
Disclaimer: This article provides information for general knowledge and informational purposes only, and does not constitute medical advice. It is essential to consult with a qualified healthcare professional for any health concerns or before making any decisions related to your health or treatment.
The development of this AI-driven imaging system represents a significant step forward in our understanding of wound healing. As research progresses, this technology has the potential to revolutionize wound care and improve the lives of millions affected by both acute and chronic wounds. We encourage readers to share this information and join the conversation about the future of regenerative medicine.
