AI-assisted photoacoustic imaging to check tumor margins during surgery

Deep-learning assisted photoacoustic histology for real-time intraoperative pathological diagnosis

NIH-funded research Case Western Reserve University · NIH-11179472

This project will use a fast light-and-sound imaging method plus AI to give surgeons real-time, microscope-like images of bone and other tissues so people having cancer surgery get more accurate tumor margin checks.

Quick facts

Grant typeNIH-funded research
Study typeNIH-funded research
Funding institutionCase Western Reserve University NIH-funded
Lab location1 site (Cleveland, United States)
Project IDNIH-11179472 on NIH RePORTER

What this research studies

If I'm having cancer surgery, this project would use a fast light-and-sound imaging technique called 3D ultraviolet photoacoustic microscopy to make microscope-like images of tissue and bone taken during the operation. Engineers will speed up the scanning and add deep-learning software to automatically produce and interpret those images in real time so pathologists and surgeons can see tumor margins before the wound is closed. The team has already shown these images match standard H&E-stained slides for bone samples, and now plans to improve imaging speed and AI interpretation for routine intraoperative use. The work involves collecting surgical tissue samples and comparing the new images and AI reads directly to conventional pathology results.

Who could benefit from this research

Good fit: Ideal candidates would be people undergoing surgery for localized cancers where checking tissue or bone margins during the operation is important.

Not a fit: Patients who are not having surgery, who have widespread metastatic disease, or whose tumors are not sampled during surgery are unlikely to benefit directly from this approach.

Why it matters

Potential benefit: If successful, surgeons could get fast, reliable margin information during the operation, lowering the chance of repeat surgeries and improving local cancer control.

How similar studies have performed: Early work shows photoacoustic images can match conventional histology for bone samples, but combining rapid 3D photoacoustic imaging with real-time deep-learning interpretation for intraoperative use is relatively new.

Where this research is happening

Cleveland, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Conditions Cancer PatientCancer TreatmentCancerousCancers
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.