AI Imaging Tracks Wound Healing & Reveals Hydrogel Insights
Wound healing, a process often taken for granted, remains a significant clinical challenge. Traditional methods of monitoring progress – visual inspection, measurements, and, in some cases, invasive biopsies – offer limited insight into what’s happening beneath the skin’s surface. Now, a new approach combining advanced optical imaging with artificial intelligence is offering a more detailed, objective view of tissue regeneration, and revealing nuances in how different therapies perform. This technology, developed through a collaboration between Duke University and Nokia Bell Labs, promises to refine our understanding of wound healing and accelerate the development of more effective treatments.
A Deeper Look Beneath the Surface
For clinicians, assessing a wound often relies on what can be seen – redness, swelling, the presence of granulation tissue. But these surface observations don’t always accurately reflect the complex biological processes unfolding within the tissue. Biopsies, whereas providing more detailed information, are invasive and can disrupt the healing process. Existing medical imaging techniques are often expensive, inaccessible, or not ideally suited for monitoring subtle changes over time.
The Duke University team, led by biomedical engineer Sharon Gerecht, has been working for over a decade on hydrogel-based therapies to guide tissue healing and regeneration. Their research focuses on creating biomaterials that stimulate the body’s natural healing mechanisms. The challenge, however, was finding a way to objectively measure the impact of these therapies at a microscopic level, without disrupting the healing process.
The solution came through a collaboration with Nokia Bell Labs, resulting in a custom-built optical coherence tomography (OCT) imaging system coupled with sophisticated AI models. OCT, commonly used in ophthalmology to image the retina, uses light waves to create high-resolution, three-dimensional images of tissue structure. Adapting this technology for wound healing allows researchers to visualize blood flow and tissue architecture beneath the skin’s surface non-invasively. As Medical Xpress reported, this approach offers a potential “virtual biopsy” for assessing wound healing.
AI Decodes the Complexities of Healing
While OCT provides a wealth of visual data, interpreting it requires powerful analytical tools. That’s where the AI component comes in. Researchers at Nokia Bell Labs developed AI models trained on imaging datasets acquired in Gerecht’s lab. These models can automatically quantify changes in tissue structure and vascular dynamics over time, providing objective measurements of healing progress. This automated analysis is crucial, as manually analyzing the complex OCT images would be time-consuming and prone to subjective interpretation.
“Wound healing is a complex process, and what we observe on the surface doesn’t always reflect what’s happening underneath,” Gerecht explained. “Partnering with Nokia Bell Labs allowed us to combine advanced optical imaging and AI and has given us unprecedented insights into how biomaterials induce healing beneath the surface.”
To test the platform, the team applied it to wounds in mice treated with a hydrogel designed to improve healing. They specifically investigated the impact of hydrogel stiffness on the healing process. The results, published in Cell Biomaterials on March 20, revealed that a stiffer hydrogel promoted faster formation of granulation tissue – the initial tissue that fills a wound – and accelerated the transition to fully regenerated tissue.
Granulation Tissue and Vascular Dynamics
The OCT-AI platform provided a detailed look at how granulation tissue filled the wound space over two weeks. The data showed that the stiffer hydrogel not only led to quicker granulation tissue formation but also facilitated a more efficient transition to mature, regenerated tissue. This suggests that the mechanical properties of biomaterials play a critical role in guiding the healing process.
Jiyeon Song, a postdoctoral researcher in Gerecht’s laboratory and co-first author of the study, highlighted the power of the AI-driven analysis. “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,” she said. “The AI helped us quantitatively track those changes and get more objective results rather than us trying to manually analyze the images ourselves.”
Beyond Hydrogels: A Platform for Future Research
The development of this OCT-AI platform represents more than just a refinement in wound healing research; it’s a versatile tool with the potential to accelerate the development of a wide range of regenerative medicine therapies. The researchers envision using the platform to evaluate other biomaterials, drug delivery systems, and even gene therapies designed to promote tissue repair.
The team at Duke and Nokia Bell Labs are now focused on refining the platform for potential clinical utilize. While the current study demonstrated its effectiveness in a controlled laboratory setting, significant work remains to be done before it can be deployed in a clinical environment. Future research will focus on expanding the platform’s capabilities to predict healing outcomes in more complex scenarios, such as chronic wounds in diabetic patients. The Segura Lab at Duke University continues to explore the potential of therapeutic materials for wound healing and tissue regeneration, aiming to bring “Wolverine-like” healing capabilities closer to reality.
Looking Ahead: Predictive Healing The next phase of research will center on securing funding to adapt the system for predicting healing outcomes in patients with chronic wounds, particularly those with diabetes, a condition that often severely impairs the healing process.