Image-guided surgery has transformed surgical procedures by enabling minimally invasive approaches and shorter recovery times. However, surgical precision during these operations depends heavily on the ability to accurately measure distances within the body during surgery. Researchers from The Institute for Education Research at UHN evaluated the feasibility and accuracy of a digital tool that uses artificial intelligence (AI) to support more consistent and accurate surgical measurements.
The research team developed a digital ruler using computer vision technology that allows AI models to analyze surgical video footage. The model identifies the tips of surgical instruments and calculates the distance between them based on the known size of the instruments. The AI model was trained using over 1,200 annotated surgical videos and evaluated against measurements estimated by surgeons and physical rulers used in simulated surgical settings.
The results showed that the AI-based tool had less variability than human estimates, especially over longer distances. The tool performed best when used with human oversight, where manual reviews and corrections were made to help the AI correctly identify instruments.
While the tool remains a proof-of-concept, the researchers anticipate future applications in the operating room through integrating on-screen measurements in surgical video feeds. The tool could also be used after surgery to help surgeons review recorded procedures and refine measurement techniques.
Overall, this study demonstrates the potential for AI-based tools to support more objective and consistent measurement during image-guided surgery, which may help improve standardization and quality of surgical care.
Raphael Kwok, first author of the study, is a research assistant in the lab of Dr. Amin Madani.
Dr. Amin Madani, senior author of the study, is an Education Investigator at The Institute for Education Research at UHN. He is also the Director of the Surgical AI Research Academy (SARA) at UHN and an Assistant Professor in the Department of Surgery at the University of Toronto.
This work was supported by UHN Foundation and the Temerty Centre for AI Research and Education in Medicine at the University of Toronto.
Dr. Amin Madani is a consultant for Johnson & Johnson. Dr. Allan Okrainec is a consultant for Medtronics and MedTech Syndicates, holds equity interests in GT Metabolic Solutions and Qaelon Medical, and receives honoraria from Ethicon.
Kwok R, Yoshida T, Hunter J, Laplante S, Brudno M, Fecso A, Okrainec A, Madani A. Development of an artificial intelligence based virtual tool for measuring distances during image-guided surgery. Surg Endosc. Epub 2025 Dec 9. doi: 10.1007/s00464-025-12461-2.