Colorectal cancer (CRC) is a leading cause of death in the Western world. It can be effectively prevented by removal of pre-malignant polyps during colonoscopy. Large (≥20mm) non-pedunculated colorectal polyps (LNPCPs) represent 2-3% of colorectal polyps and require special attention prior to treatment. If submucosal invasive cancer (SMI) is suspected, careful decision making is required to exclude features which unacceptably increase the risk of lymph node metastases and render local treatment (endoscopic) non-curative. Such patients require a multi-disciplinary approach and consideration of surgery +/- systemic therapy.

Unfortunately, current classification systems are complex, require extensive training and technology not available in the majority of non-tertiary hospitals. They are therefore underused leading to incorrect decision making and negative patient outcomes (e.g. piecemeal resection without the chance of endoscopic cure or unnecessary further procedures in referral centres with resultant surgery anyway or surgery for benign disease).

Studies from the field of psychology show that humans are often capable of making correct decision based on their Blink (first) impression. It is also suggested that this Blink impression is based on experience and training. This might suggest that experienced or specialist endoscopist are better at diagnosing SMI within colorectal polyp at Blink impression.

The investigators hypothesize that by training the Blink impression, endoscopist of varying experience are able to detect cancer within LNPCPs. This can be proven by assessing the Blink impression of endoscopist of varying experience regarding the presence of SMI within LNPCPs.

Increasing the accuracy of the determination of SMI within colon polyps would directly translate into improvements in patient care and outcome.

For example, if SMI is present and is not suspected, patients may undergo unnecessary endoscopic procedures for an LNPCP which will eventually require surgery anyway (inconvenience, delayed correct treatment). If the incorrect technique is performed in the context of superficial SMI, adequate assessment of complete excision or extent and type of SMI may not be possible and a patient who would otherwise have been cured may require surgery anyway (under-treatment, below standard of care outcome, delay to treatment). Conversely, if SMI is suspected in its absence patients may undergo unnecessary surgery, increased healthcare spends and mortality (over-treatment, unnecessary risk). If the presence of SMI could be accurately determined in real-time using endoscopic imaging, delays to treatment, over-treatment and the associated morbidity for patients could be avoided.

Inclusion Criteria:

• Endoscopists of varying abilities and grades (participant endoscopist) that consents electronically
• Patients with LNPCPs who signed the ICF of UZ Ghent Hospital for the anonymous use images of their polyp taken during colonoscopy

Exclusion Criteria:

• Endoscopist does not consent to inclusion (participant endoscopist)
• Image of inadequate quality as per opinion of the principal investigator
• Patient does not consent to data collection for the study (participant patient)

• Endoscopists of varying experience (trainees, consultants, expert endoscopists, interventional endoscopists.
• Patients with LNPCPs