AUGUR-AI - Indocyanine Green Fluorescence Angiography Representer

Condition(s) studied

Study summary

Surgery can effectively treat colorectal cancer, but it is a complex procedure with risks and complications. Surgeons often rely on cameras to visually guide their instruments during operations, especially in minimally invasive ("keyhole") and endoscopic procedures. The camera is connected to a computer and generates the internal scene onto a display screen, which the surgeon looks at throughout the procedure, helping them make informed decisions throughout the operation. Fluorescence-guided surgery uses a particular type of camera that can detect images in both normal light and in the near-infrared range. To work, it needs the administration of an agent called indocyanine green to a patient and then the camera can see if the agent is in the tissue of interest to the operation at the time of the surgery. In this way, decisions regarding blood supply ("perfusion") can be helped, especially related to safety in joining together portions of tissue after removal of disease. The equipment and agent are approved for use in this way and have very good safety profiles. Many international studies have already demonstrated that the use of fluorescence-guided surgery is associated with lower rates of leaks when disease bowel segments are removed, and the healthy ends are joined back together.

Previous work we have done has shown that sophisticated computing methods can learn to interpret the fluorescence patterns to a similar standard as a surgeon who is very experienced in fluorescence-guided surgery.

In this study, we aim to assess whether the computer system we have developed work in real-time, in theatre to provide a reliable interpretation of the fluorescence pattern, that would match how an expert would interpret the same pattern. The system's analysis will not impact on the operation; instead, video images will be recorded, processed and analysed by our computer system. The results of the interpretation will not be shown to the operating surgeon during the procedure to avoid any impact on decision-making.

Eligibility

Primary outcome measure(s)

• Accuracy of AI interpretation relative to intra-operative decision made by operating surgeon — Within 12 months of study commencement
  Accuracy of the initial AI-based system, with concurrent development and testing of new AI models using the data generated from participating sites. The performance of the algorithm will be analysed at both object and pixel level. At the object level, accuracy will be assessed based on whether the actual stapler placement by the operating surgeon falls within the boundaries of the "expert" zone predicted by the algorithm. Pixel level analysis will measure the overlap between the predicted and actual zones.

Trial sites (1)

More Mater Misericordiae University Hospital trials in Ireland