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.

Surgery is a major contributor to healthcare, but it must be continually optimised to maximise its effectiveness while minimising risk and cost. Complex surgical outcomes, which often require significant healthcare resources, highlight the need for constant improvements in safety and precision. Every surgical procedure consists of a series of critical steps that rely on surgeon judgement as well as technical dexterity and skill. Decisions are made predominantly through visual interpretation of findings in the context of patient specific factors (including those profiled preoperatively) and the operator's own experience (which includes formal training and accumulated expertise). This is especially true for minimally invasive surgery which uses a camera placed internally to display the internal scene along with the operator's actions on a screen for viewing (the digitised image is created by a computer for interpretation by a human). Crucial to the success of the operation is making the most accurate decisions as possible to ensure the patients gets a safe, successful operation that cures the problem with as little functional loss as possible. For colorectal resectional surgery, this means knowing the residual tissues are sufficiently perfused to heal, as non-healing of anastomoses is associated with significant morbidity and mortality.

Near-infrared laparoscopy is an established technology that aims to improve clinical outcomes by providing a means of seeing certain tissue characteristics that would otherwise be invisible to the human eye to aid intraoperative decision-making. This technology uses energy in the NIR range (780-820nm) to visualise tissues alongside standard white light interrogation. Energy in this wavelength causes no cellular damage and can penetrate some tissue to a depth of some millimetres. At this wavelength, there is no biological reflectance from the tissue so presence of a responsive agent administered systemically can be confirmed if the agent is capable of fluorescence (that is absorption of energy at one wavelength and its re-emission at a different wavelength). While new fluorescence agents are in development, right now the most useful and safest agent approved for use is indocyanine green (ICG), which has long been approved and proven safe for circulatory assessment including microvascular tissue perfusion. When administered systemically, the dye circulates through the body in seconds, providing real-time information that can be repeatedly assessed at various stages throughout the surgery. To date, many studies, including randomised controlled trials, have demonstrated that the use of indocyanine green fluorescence angiography (ICGFA) is associated with lower rates of anastomotic leak in major colorectal resectional surgery. Subjective interpretations of dynamically changing scenes can be difficult, especially where differing areas of the screen may need to be tracked over time. However, given that the use of ICGFA is associated with lower leak rates, interpretation of signal patterns by expert users must be consistent and this has also been demonstrated in work looking at inter-user variability.

"Digital surgery" as a concept relates to the application of technology for real-time data analytics during operations. The term Artificial Intelligence (AI) refers to technology that attempts to mimic human cognition. Computer vision refers to the conversion of visual display into numeric datasets than then become available for machine learning via its application of statistical models based on a sample of data to apply decision-making to situations without being explicitly designed to perform the task. A predictive model can weigh different paths and a classifier can then present decision support suggestion alongside its confidence levels. In previous work, we have trained AI models based on expert interpretation of fluorescence signal patterns in patients who were known not to suffer a post-operative anastomotic leak. We have subsequently tested this method prospectively, intra-operatively in consecutive patients on a laptop (with NVIDIA T500 2GB GPU). The software method proved 100% accurate at object-level and matched the actual stapler site placement by the operating surgeon. We have also shown that it can learn from interpretations of multiple surgeons and is generalizable to other surgeons and imaging systems. Since then, we have built a software platform on NVIDIA Jetson.

We aim to test the AI-based software in providing how an expert surgeon would interpret ICGFA signals in real time, in-theatre during surgery. Surgeons will be blinded to the predictions made by the AI algorithm.

To do this, ICGFA will be used as approved in patients undergoing open, laparoscopic or robotic major colorectal resectional surgery as per usual clinical care protocols. Video recordings will be analysed by the AI model alongside the operation, however the surgeon will be blinded to the representation.

Finally, after the procedure is completed, the information generated by the model will be compared with the interpretations made intra-operatively by the surgeon. The initial phase of the study will involve testing the AI model that has already been developed. The subsequent phases will involve concurrent testing of new AI models developed using interpretations from the participating sites.

In brief, in this study, patients having open, laparoscopic or robotic surgery for colorectal disease will receive ICG for the purposes of intestinal perfusion sufficiency determination. Video recordings of these images will be examined mathematically in real-time regarding fluorescence patterns and compared with surgeon interpretation and clinical course both to test the model and to build further its learning set.

No change in management will be made based on the new analytical information being generated for patients in this study - the study therefore is a prospective observational cohort study. AI modelling will require relevant pseudonymised data be sent off site in the form of the video and classifying metadata to research partners in University College Dublin.

All potential participating patients will be explicitly consented regarding study aims, protocols and pathways. Data sharing will be compliant with GDPR regulations and the processes in this study have been mapped by the hospital's GDPR officer. No personally identifying information will leave the research group or be available to any non-involved staff.

NIR laparoscopy and ICGFA involves the systemic administration of ICG within its licence - i.e. primary characterisation of tissue perfusion, this therefore is a non-CTIMP study. The dose used will be at the discretion of the operating surgeon as per their standard clinical practice.

ICGFA has been used for bowel perfusion sufficiency assessment in several studies and is being evaluated in randomised trials to establish it benefit. The agent used, ICG, has been in clinical use for several decades with additional applications in ophthalmology, critical care, hepatology (liver volume assessment) and intraoperatively for biliary tree anatomy definition. As a cancer labelling agent it has been used for liver cancer and metastases, lung and pancreas cancer as well as being recently FDA approved for lymphatic mapping for gynaecological malignancy. It has also been used as an endoscopic tattooing agent. It is in general well tolerated with a low anaphylaxis rate and high safety profile being excreted unmetabolized by the liver.

NIR illumination is inbuilt now into system made by several major commercial corporations including Stryker, Arthrex, Karl Storz, Olympus and Intuitive with extensive experience of use without tissue toxicity. In this study, NIR videos will be recorded using either the Stryker/Arthrex system.

Inclusion Criteria:

• Participant is willing and able to give informed consent for participation in the study.
• Aged 18 years or above.
• Colorectal disease requiring segmental resection with anastomosis.
• Participant has clinically acceptable laboratory results, including liver function tests.
• In the Investigator's opinion, is able and willing to comply with all study requirements.
• Willing to allow his or her General Practitioner and consultant, if appropriate, to be notified of participation in the study.

Exclusion Criteria:

The participant may not enter the study if ANY of the following apply:

• Participant who is pregnant, lactating or planning pregnancy during the course of the study.
• Significant renal or hepatic impairment.
• Any other significant disease or disorder which, in the opinion of the Investigator, may either put the participants at risk because of participation in the study, or may influence the result of the study, or the participant's ability to participate in the study.
• Allergy to intravenous contrast agent or indocyanine green.
• Concurrent use of anticonvulsants, bisulphite containing drugs, methadone and nitrofurantoin.

Adult patients with colorectal disease undergoing segmental resection via an open, laparoscopic or robotic approach will be approached for inclusion in the trial. Participants must be able and willing to comply with the terms of the protocol.

Such patients will be identified from referral letters, outpatient clinics, endoscopy lists, and multidisciplinary cancer meetings. Patients will undergo standard preoperative work-up, including colonic visualisation by either colonoscopy or CT colonogram, staging CT scan of the chest, abdomen and pelvis, MRI of the rectum, and assessment of fitness for surgery as per standard practice. The optimal management of the patient will be determined based on institutional protocols.

Given the sensitive nature of the data being collected (health data) individual participant data will not be shared, in line with GDPR and as described in the patient information leaflet. However, should the algorithm work, the intention is to aggregate the video data sets with further pseudonymisation so that these could then be shared with stakeholders. This would be to help with any future deployment as a medical device to allow what we learn to be put into clinical practice and to answer related new research questions in the future, specifically related to computer vision and AI advancements in the field of surgery and healthcare. These stakeholders include hospital groups, universities and/or industry (including multinational commercial entities). This will only occur with the permission of the research team and principal investigator in keeping with research ethics approval.