Systematic Review and Meta-analysis: The Three-year Post-colonoscopy Colorectal Cancer Rate as per the World Endoscopy Organization Methodology.

BACKGROUND & AIMS: In 2018, the World Endoscopy Organization (WEO) introduced standardized methods for calculating post-colonoscopy colorectal cancer-3yr rates (PCCRC-3yr). This systematic review aimed to calculate the global PCCRC-3yr according to the WEO methodology, its change over time, and to measure the association between risk factors and PCCRC occurrences. METHODS: We searched 5 databases from inception until January 2024 for PCCRC-3yr studies that strictly adhered to the WEO methodology. The overall pooled PCCRC-3yr was calculated. For risk factors and time-trend analyses, the pooled PCCRC-3yr and odds ratios (ORs) of subgroups were compared. RESULTS: Several studies failed to adhere to the WEO methodology. Eight studies from 4 Western European and 2 Northern American countries were included, totalling 220,106 detected-colorectal cancers (CRCs) and 18,148 PCCRCs between 2002 and 2017. The pooled Western World PCCRC-3yr was 7.5% (95% confidence interval [CI], 6.4%-8.7%). The PCCRC-3yr significantly (P < .05) decreased from 7.9% (95% CI, 6.6%-9.4%) in 2006 to 6.7% (95% CI, 6.1%-7.3%) in 2012 (OR, 0.79; 95% CI, 0.72-0.87). There were significantly higher rates for people with inflammatory bowel disease (PCCRC-3yr, 29.3%; OR, 6.17; 95% CI, 4.73-8.06), prior CRC (PCCRC-3yr, 29.8%; OR, 3.03; 95% CI, 1.34-4.72), proximal CRC (PCCRC-3yr, 8.6%; OR, 1.51; 95% CI, 1.41-1.61), diverticular disease (PCCRC 3-yr, 11.6%; OR, 1.74; 95% CI, 1.37-2.10), and female sex (PCCRC-3yr, 7.9%; OR, 1.15; 95% CI, 1.11-1.20). CONCLUSION: According to the WEO methodology, the Western World PCCRC-3yr was 7.5%. Reassuringly, this has decreased over time, but further work is required to identify the reasons for PCCRCs, especially in higher-risk groups. We devised a WEO methodology checklist to increase its adoption and standardise the categorization of patients in future PCCRC-3yr studies.

Computer-aided characterization of early cancer in Barrett's esophagus on i-scan magnification imaging: a multicenter international study.

BACKGROUND AND AIMS: We aimed to develop a computer-aided characterization system that could support the diagnosis of dysplasia in Barrett's esophagus (BE) on magnification endoscopy. METHODS: Videos were collected in high-definition magnification white-light and virtual chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and nondysplastic BE (NDBE) from 4 centers. We trained a neural network with a Resnet101 architecture to classify frames as dysplastic or nondysplastic. The network was tested on 3 different scenarios: high-quality still images, all available video frames, and a selected sequence within each video. RESULTS: Fifty-seven patients, each with videos of magnification areas of BE (34 dysplasia, 23 NDBE), were included. Performance was evaluated by a leave-1-patient-out cross-validation method. In all, 60,174 (39,347 dysplasia, 20,827 NDBE) magnification video frames were used to train the network. The testing set included 49,726 i-scan-3/optical enhancement magnification frames. On 350 high-quality still images, the network achieved a sensitivity of 94%, specificity of 86%, and area under the receiver operator curve (AUROC) of 96%. On all 49,726 available video frames, the network achieved a sensitivity of 92%, specificity of 82%, and AUROC of 95%. On a selected sequence of frames per case (total of 11,471 frames), we used an exponentially weighted moving average of classifications on consecutive frames to characterize dysplasia. The network achieved a sensitivity of 92%, specificity of 84%, and AUROC of 96%. The mean assessment speed per frame was 0.0135 seconds (SD ± 0.006). CONCLUSION: Our network can characterize BE dysplasia with high accuracy and speed on high-quality magnification images and sequence of video frames, moving it toward real-time automated diagnosis.

Identifying key mechanisms leading to visual recognition errors for missed colorectal polyps using eye-tracking technology.

BACKGROUND AND AIM: Lack of visual recognition of colorectal polyps may lead to interval cancers. The mechanisms contributing to perceptual variation, particularly for subtle and advanced colorectal neoplasia, have scarcely been investigated. We aimed to evaluate visual recognition errors and provide novel mechanistic insights. METHODS: Eleven participants (seven trainees and four medical students) evaluated images from the UCL polyp perception dataset, containing 25 polyps, using eye-tracking equipment. Gaze errors were defined as those where the lesion was not observed according to eye-tracking technology. Cognitive errors occurred when lesions were observed but not recognized as polyps by participants. A video study was also performed including 39 subtle polyps, where polyp recognition performance was compared with a convolutional neural network. RESULTS: Cognitive errors occurred more frequently than gaze errors overall (65.6%), with a significantly higher proportion in trainees (P = 0.0264). In the video validation, the convolutional neural network detected significantly more polyps than trainees and medical students, with per-polyp sensitivities of 79.5%, 30.0%, and 15.4%, respectively. CONCLUSIONS: Cognitive errors were the most common reason for visual recognition errors. The impact of interventions such as artificial intelligence, particularly on different types of perceptual errors, needs further investigation including potential effects on learning curves. To facilitate future research, a publicly accessible visual perception colonoscopy polyp database was created.

Polyp characterization using deep learning and a publicly accessible polyp video database.

OBJECTIVES: Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow-band imaging (NBI) and NBI-near focus (NBI-NF) and created a publicly accessible polyp video database. METHODS: We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test-sets. Test-set I consists of 14,320 frames (157 polyps, 111 diminutive). Test-set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists. RESULTS: Sensitivity for adenoma characterization was 91.6% in test-set I and 89.7% in test-set II. Specificity was 91.9% and 88.5%. Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI-NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)-1 and PIVI-2 thresholds for each test-set. In the benchmarking of test-set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2-23.6], P = 0.01) with no significant difference with experts. CONCLUSIONS: A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI-NF. A publicly accessible NBI polyp video database was created and benchmarked.

Performance of artificial intelligence for detection of subtle and advanced colorectal neoplasia.

OBJECTIVES: There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field. METHODS: An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp-positive frames and 634,988 polyp-negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK). RESULTS: In the first two video datasets, the algorithm achieved per-polyp sensitivities of 100% and 98.9%. Per-frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG-independent and trainee endoscopists, achieving per-polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average. CONCLUSIONS: The AI based algorithm achieved high per-polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.

SimCol3D - 3D reconstruction during colonoscopy challenge.

Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. Establishing a benchmark dataset, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction from synthetic colonoscopy images is robustly solvable, while pose estimation remains an open research question.

Lynch syndrome: from detection to treatment.

Lynch syndrome (LS) is an inherited cancer predisposition syndrome associated with high lifetime risk of developing tumours, most notably colorectal and endometrial. It arises in the context of pathogenic germline variants in one of the mismatch repair genes, that are necessary to maintain genomic stability. LS remains underdiagnosed in the population despite national recommendations for empirical testing in all new colorectal and endometrial cancer cases. There are now well-established colorectal cancer surveillance programmes, but the high rate of interval cancers identified, coupled with a paucity of high-quality evidence for extra-colonic cancer surveillance, means there is still much that can be achieved in diagnosis, risk-stratification and management. The widespread adoption of preventative pharmacological measures is on the horizon and there are exciting advances in the role of immunotherapy and anti-cancer vaccines for treatment of these highly immunogenic LS-associated tumours. In this review, we explore the current landscape and future perspectives for the identification, risk stratification and optimised management of LS with a focus on the gastrointestinal system. We highlight the current guidelines on diagnosis, surveillance, prevention and treatment and link molecular disease mechanisms to clinical practice recommendations.

Spatio-temporal classification for polyp diagnosis.

Colonoscopy remains the gold standard investigation for colorectal cancer screening as it offers the opportunity to both detect and resect pre-cancerous polyps. Computer-aided polyp characterisation can determine which polyps need polypectomy and recent deep learning-based approaches have shown promising results as clinical decision support tools. Yet polyp appearance during a procedure can vary, making automatic predictions unstable. In this paper, we investigate the use of spatio-temporal information to improve the performance of lesions classification as adenoma or non-adenoma. Two methods are implemented showing an increase in performance and robustness during extensive experiments both on internal and openly available benchmark datasets.

Automated colonoscopy withdrawal phase duration estimation using cecum detection and surgical tasks classification.

Colorectal cancer is the third most common type of cancer with almost two million new cases worldwide. They develop from neoplastic polyps, most commonly adenomas, which can be removed during colonoscopy to prevent colorectal cancer from occurring. Unfortunately, up to a quarter of polyps are missed during colonoscopies. Studies have shown that polyp detection during a procedure correlates with the time spent searching for polyps, called the withdrawal time. The different phases of the procedure (cleaning, therapeutic, and exploration phases) make it difficult to precisely measure the withdrawal time, which should only include the exploration phase. Separating this from the other phases requires manual time measurement during the procedure which is rarely performed. In this study, we propose a method to automatically detect the cecum, which is the start of the withdrawal phase, and to classify the different phases of the colonoscopy, which allows precise estimation of the final withdrawal time. This is achieved using a Resnet for both detection and classification trained with two public datasets and a private dataset composed of 96 full procedures. Out of 19 testing procedures, 18 have their withdrawal time correctly estimated, with a mean error of 5.52 seconds per minute per procedure.

Towards NHS Zero: greener gastroenterology and the impact of virtual clinics on carbon emissions and patient outcomes. A multisite, observational, cross-sectional study.

Objective: The National Health Service (NHS) produces more carbon emissions than any public sector organisation in England. In 2020, it became the first health service worldwide to commit to becoming carbon net zero, the same year as the COVID-19 pandemic forced healthcare systems globally to rapidly adapt service delivery. As part of this, outpatient appointments became largely remote. Although the environmental benefit of this change may seem intuitive the impact on patient outcomes must remain a priority. Previous studies have evaluated the impact of telemedicine on emission reduction and patient outcomes but never before in the gastroenterology outpatient setting. Method: 2140 appointments from general gastroenterology clinics across 11 Trusts were retrospectively analysed prior to and during the pandemic. 100 consecutive appointments during two periods of time, from 1 June 2019 (prepandemic) to 1 June 2020 (during the pandemic), were used. Patients were telephoned to confirm the mode of transport used to attend their appointment and electronic patient records reviewed to assess did-not-attend (DNA) rates, 90-day admission rates and 90-day mortality rates. Results: Remote consultations greatly reduced the carbon emissions associated with each appointment. Although more patients DNA their remote consultations and doctors more frequently requested follow-up blood tests when reviewing patients face-to-face, there was no significant difference in patient 90-day admissions or mortality when consultations were remote. Conclusion: Teleconsultations can provide patients with a flexible and safe means of being reviewed in outpatient clinics while simultaneously having a major impact on the reduction of carbon emissions created by the NHS.

Cancer Biology or Ineffective Surveillance? A multicentre retrospective analysis of colitis-associated post-colonoscopy colorectal cancers.

BACKGROUND AND AIMS: Inflammatory bowel disease (IBD) is associated with high rates of post-colonoscopy colorectal cancer (PCCRC), but further in-depth qualitative analyses are required to determine whether they result from inadequate surveillance or aggressive IBD cancer evolution. METHODS: All IBD patients who had a colorectal cancer (CRC) diagnosed between January 2015 to July 2019 and a recent (<4 years) surveillance colonoscopy at one of four English hospital trusts underwent root cause analyses as recommended by the World Endoscopy Organisation to identify plausible PCCRC causative factors. RESULTS: 61% (n=22/36) of the included IBD CRCs were PCCRCs. They developed in patients with high cancer risk factors (77.8%; n=28/36) requiring annual surveillance, yet 57.1% (n=20/35) had inappropriately delayed surveillance. Most PCCRCs developed in situations where (i) an endoscopically unresectable lesion was detected (40.9%; n=9/22), (ii) there was a deviation from the planned management pathway (40.9%; n=9/22) e.g. service, clinician or patient-related delays in acting on a detected lesion, or (iii) lesions were potentially missed as they were typically located within areas of active inflammation or post-inflammatory change (36.4%; n=8/22). CONCLUSIONS: IBD PCCRC prevention will require more proactive strategies to reduce endoscopic inflammatory burden, improve lesion optical characterisation, adherence to recommended surveillance intervals and patient acceptance of prophylactic colectomy. However, the significant proportion appearing to originate from non-adenomatous-looking mucosa which fail to yield neoplasia on biopsy yet display aggressive cancer evolution highlight the limitations of current surveillance. Emerging molecular biomarkers may play a role in enhancing cancer risk stratification in future clinical practice.

Survey on the perceptions of UK gastroenterologists and endoscopists to artificial intelligence.

Background and aims: With the potential integration of artificial intelligence (AI) into clinical practice, it is essential to understand end users' perception of this novel technology. The aim of this study, which was endorsed by the British Society of Gastroenterology (BSG), was to evaluate the UK gastroenterology and endoscopy communities' views on AI. Methods: An online survey was developed and disseminated to gastroenterologists and endoscopists across the UK. Results: One hundred four participants completed the survey. Quality improvement in endoscopy (97%) and better endoscopic diagnosis (92%) were perceived as the most beneficial applications of AI to clinical practice. The most significant challenges were accountability for incorrect diagnoses (85%) and potential bias of algorithms (82%). A lack of guidelines (92%) was identified as the greatest barrier to adopting AI in routine clinical practice. Participants identified real-time endoscopic image diagnosis (95%) as a research priority for AI, while the most perceived significant barriers to AI research were funding (82%) and the availability of annotated data (76%). Participants consider the priorities for the BSG AI Task Force to be identifying research priorities (96%), guidelines for adopting AI devices in clinical practice (93%) and supporting the delivery of multicentre clinical trials (91%). Conclusion: This survey has identified views from the UK gastroenterology and endoscopy community regarding AI in clinical practice and research, and identified priorities for the newly formed BSG AI Task Force.

Polyp detection on video colonoscopy using a hybrid 2D/3D CNN.

Colonoscopy is the gold standard for early diagnosis and pre-emptive treatment of colorectal cancer by detecting and removing colonic polyps. Deep learning approaches to polyp detection have shown potential for enhancing polyp detection rates. However, the majority of these systems are developed and evaluated on static images from colonoscopies, whilst in clinical practice the treatment is performed on a real-time video feed. Non-curated video data remains a challenge, as it contains low-quality frames when compared to still, selected images often obtained from diagnostic records. Nevertheless, it also embeds temporal information that can be exploited to increase predictions stability. A hybrid 2D/3D convolutional neural network architecture for polyp segmentation is presented in this paper. The network is used to improve polyp detection by encompassing spatial and temporal correlation of the predictions while preserving real-time detections. Extensive experiments show that the hybrid method outperforms a 2D baseline. The proposed architecture is validated on videos from 46 patients and on the publicly available SUN polyp database. A higher performance and increased generalisability indicate that real-world clinical implementations of automated polyp detection can benefit from the hybrid algorithm and the inclusion of temporal information.

Unlocking the benefits of the Baveno VI guidance when screening for varices: an audit of clinical practice across London.

Background: The Baveno VI consensus identifies patients with compensated advanced chronic liver disease (cACLD) who can safely avoid screening endoscopy. However, concordance in clinical practice with this guidance is unknown. We audited clinical practice and the provision of transient elastography (TE) aiming to identify potential cost savings and benefits. Methods: Retrospective data collection from 12 sites across London over 6 months by reviewing oesophagogastroduodenoscopy (OGD) reports, platelet count and TE results as well as information on site-specific provision of TE. Results: Three-hundred and fifty-one screening procedures were identified; 177 (50.43%) had a TE test performed within the preceding 12 months; 142 (80.23%) patients with a recent TE test did not meet criteria for screening OGD. TE provision varied widely between sites. Conclusion: Improving concordance with the Baveno criteria through improved provision of TE would have benefits for patients, healthcare systems and the environment and would help to address the challenges of moving on from the COVID-19 pandemic.

A new artificial intelligence system successfully detects and localises early neoplasia in Barrett's esophagus by using convolutional neural networks.

BACKGROUND AND AIMS: Seattle protocol biopsies for Barrett's Esophagus (BE) surveillance are labour intensive with low compliance. Dysplasia detection rates vary, leading to missed lesions. This can potentially be offset with computer aided detection. We have developed convolutional neural networks (CNNs) to identify areas of dysplasia and where to target biopsy. METHODS: 119 Videos were collected in high-definition white light and optical chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and non-dysplastic BE (NDBE). We trained an indirectly supervised CNN to classify images as dysplastic/non-dysplastic using whole video annotations to minimise selection bias and maximise accuracy. The CNN was trained using 148,936 video frames (31 dysplastic patients, 31 NDBE, two normal esophagus), validated on 25,161 images from 11 patient videos and tested on 264 iscan-1 images from 28 dysplastic and 16 NDBE patients which included expert delineations. To localise targeted biopsies/delineations, a second directly supervised CNN was generated based on expert delineations of 94 dysplastic images from 30 patients. This was tested on 86 i-scan one images from 28 dysplastic patients. FINDINGS: The indirectly supervised CNN achieved a per image sensitivity in the test set of 91%, specificity 79%, area under receiver operator curve of 93% to detect dysplasia. Per-lesion sensitivity was 100%. Mean assessment speed was 48 frames per second (fps). 97% of targeted biopsy predictions matched expert and histological assessment at 56 fps. The artificial intelligence system performed better than six endoscopists. INTERPRETATION: Our CNNs classify and localise dysplastic Barrett's Esophagus potentially supporting endoscopists during surveillance.

Optical diagnosis of colorectal polyps using convolutional neural networks.

Colonoscopy remains the gold standard investigation for colorectal cancer screening as it offers the opportunity to both detect and resect pre-malignant and neoplastic polyps. Although technologies for image-enhanced endoscopy are widely available, optical diagnosis has not been incorporated into routine clinical practice, mainly due to significant inter-operator variability. In recent years, there has been a growing number of studies demonstrating the potential of convolutional neural networks (CNN) to enhance optical diagnosis of polyps. Data suggest that the use of CNNs might mitigate the inter-operator variability amongst endoscopists, potentially enabling a "resect and discard" or "leave in" strategy to be adopted in real-time. This would have significant financial benefits for healthcare systems, avoid unnecessary polypectomies of non-neoplastic polyps and improve the efficiency of colonoscopy. Here, we review advances in CNN for the optical diagnosis of colorectal polyps, current limitations and future directions.