Colorectal cancer remains a leading cause of cancer-related morbidity and mortality worldwide, despite the widespread uptake of population surveillance strategies. This is in part due to the persistent development of ‘interval colorectal cancers’, where patients develop colorectal cancer despite appropriate surveillance intervals, implying pre-malignant polyps were not resected at a prior colonoscopy. Multiple techniques have been developed to improve the sensitivity and accuracy of lesion detection and characterisation in an effort to improve the efficacy of colorectal cancer screening, thereby reducing the incidence of interval colorectal cancers. This article presents a comprehensive review of the transformative role of artificial intelligence (AI), which has recently emerged as one such solution for improving the quality of screening and surveillance colonoscopy. Firstly, AI-driven algorithms demonstrate remarkable potential in addressing the challenge of overlooked polyps, particularly polyp subtypes infamous for escaping human detection because of their inconspicuous appearance. Secondly, AI empowers gastroenterologists without exhaustive training in advanced mucosal imaging to characterise polyps with accuracy similar to that of expert interventionalists, reducing the dependence on pathologic evaluation and guiding appropriate resection techniques or referrals for more complex resections. AI in colonoscopy holds the potential to advance the detection and characterisation of polyps, addressing current limitations and improving patient outcomes. The integration of AI technologies into routine colonoscopy represents a promising step towards more effective colorectal cancer screening and prevention.

Background and Aims: Artificial Intelligence (AI) is rapidly evolving in gastrointestinal (GI) endoscopy. We undertook a systematic review and meta-analysis to assess the performance of AI at detecting early Barrett's neoplasia.Methods: We searched Medline, EMBASE and Cochrane Central Register of controlled trials database from inception to the 28th Jan 2022 to identify studies on the detection of early Barrett's neoplasia using AI. Study quality was assessed using Quality Assessment of Diagnostic Accuracy Studies – 2 (QUADAS-2). A random-effects model was used to calculate pooled sensitivity, specificity, and diagnostics odds ratio (DOR). Forest plots and a summary of the receiving operating characteristics (SROC) curves displayed the outcomes. Heterogeneity was determined by I², Tau² statistics and p-value. The funnel plots and Deek's test were used to assess publication bias.Results: Twelve studies comprising of 1,361 patients (utilizing 532,328 images on which the various AI models were trained) were used. The SROC was 0.94 (95% CI: 0.92–0.96). Pooled sensitivity, specificity and diagnostic odds ratio were 90.3% (95% CI: 87.1–92.7%), 84.4% (95% CI: 80.2–87.9%) and 48.1 (95% CI: 28.4–81.5), respectively. Subgroup analysis of AI models trained only on white light endoscopy was similar with pooled sensitivity and specificity of 91.2% (95% CI: 85.7–94.7%) and 85.1% (95% CI: 81.6%−88.1%), respectively.Conclusions: AI is highly accurate at detecting early Barrett's neoplasia and validated for patients with at least high-grade dysplasia and above. Further well-designed prospective randomized controlled studies of all histopathological subtypes of early Barrett's neoplasia are needed to confirm these findings further.

Background and study aims: To determine the utility of narrow-band imaging with optical magnification (NBI-Z) in the evaluation of villous morphology. Patients and methods: Patients considered at risk of having celiac disease were invited. After standard endoscopy, they underwent further evaluation with NBI-Z which was digitally recorded. Targeted biopsies of each area videoed with NBI-Z were performed and tissue sent for histopathological analysis. Two expert endoscopists then selected the best representative videos (developmental phase). Next, 41 representative images of these videos were classified as follows: villous patterns present (N) or absent (A). Images showing absence of villi were then classified as cerebriform (C) or flat (F), corresponding to partial or total villous atrophy respectively. Three NBI-Z-naïve endoscopists then graded the videos. They underwent an interactive training session (learning phase) with video and images from a digital library before embarking on the actual assessment. To test for reproducibility, all videos were randomly reordered and graded again after a week. Results: Forty-one videos (10 celiac disease, 31 normal) from 21 patients (3 celiac disease, 18 normal) were analyzed. The overall sensitivity and specificity in correctly distinguishing the presence or absence of villi were 93.3 % and 97.8 % respectively, with interobserver and intraobserver agreement (kappa, κ) at 0.82 and 0.86. The sensitivity and specificity in differentiating partial from total villous atrophy were 83.3 % and 100 %, κ at 0.73 and 0.68 respectively. Conclusions: Using a simplified classification, we demonstrated the feasibility of using NBI-Z to detect villous atrophy in patients presenting with suspected celiac disease.

It is currently known that colorectal cancers (CRC) arise from 3 different pathways: the adenoma to carcinoma chromosomal instability pathway (50%-70%); the mutator “Lynch syndrome” route (3%-5%); and the serrated pathway (30%-35%). The World Health Organization has classified serrated polyps into three types of lesions: hyperplastic polyps (HP), sessile serrated adenomas/polyps (SSA/P) and traditional serrated adenomas (TSA), the latter two strongly associated with development of CRCs. HPs do not cause cancer and TSAs are rare. SSA/P appear to be the responsible precursor lesion for the development of cancers through the serrated pathway. Both HPs and SSA/Ps appear morphologically similar. SSA/P are difficult to detect. The margins are normally inconspicuous. En bloc resection of these polyps can hence be troublesome. A careful examination of borders, submucosal injection of a dye solution (for larger lesions) and resection of a rim of normal tissue around the lesion may ensure total eradication of these lesions.

Over the last few years, improvements in endoscopic imaging technology have enabled identification of dysplasia and early cancer in Barrett's oesophagus. New techniques should exhibit high sensitivities and specificities and have good interobserver agreement. They should also be affordable and easily applicable to the community gastroenterologist. Ideally, these modalities must exhibit the capability of imaging wide areas in real time whilst enabling the endoscopist to specifically target abnormal areas. This review will specifically focus on some of the novel endoscopic imaging modalities currently available in routine practice which includes chromoendoscopy, autofluorescence imaging and narrow band imaging.