ECCO Topical Review Optimising Reporting in Surgery, Endoscopy, and Histopathology

The development of artificial intelligence in the histological diagnosis of Inflammatory Bowel Disease (IBD-AI)

BACKGROUND

Inflammatory bowel disease (IBD) includes Crohn's Disease (CD) and Ulcerative Colitis (UC). Correct diagnosis requires the identification of precise morphological features such basal plasmacytosis. However, histopathological interpretation can be challenging, and it is subject to high variability.

AIM

The IBD-Artificial Intelligence (AI) project aims at the development of an AI-based evaluation system to support the diagnosis of IBD, semi-automatically quantifying basal plasmacytosis.

METHODS

A deep learning model was trained to detect and quantify plasma cells on a public dataset of 4981 annotated images. The model was then tested on an external validation cohort of 356 intestinal biopsies of CD, UC and healthy controls. AI diagnostic performance was calculated compared to human gold standard.

RESULTS

The system correctly found that CD and UC samples had a greater prevalence of basal plasma cells with mean number of PCs within ROIs of 38.22 (95 % CI: 31.73, 49.04) for CD, 55.16 (46.57, 65.93) for UC, and 17.25 (CI: 12.17, 27.05) for controls. Overall, OR=4.968 (CI: 1.835, 14.638) was found for IBD compared to normal mucosa (CD: +59 %; UC: +129 %). Additionally, as expected, UC samples were found to have more plasma cells in colon than CD cases.

CONCLUSION

Our model accurately replicated human assessment of basal plasmacytosis, underscoring the value of AI models as a potential aid IBD diagnosis.

Validation of a new optical diagnosis training module to improve dysplasia characterization in inflammatory bowel disease: a multicenter international study

BACKGROUND AND AIMS

Inflammatory bowel disease (IBD) increases risk of dysplasia and colorectal cancer. Advanced endoscopic techniques allow for the detection and characterization of IBD dysplastic lesions, but specialized training is not widely available. We aimed to develop and validate an online training platform to improve the detection and characterization of colonic lesions in IBD: OPtical diagnosis Training to Improve dysplasia Characterization in Inflammatory Bowel Disease (OPTIC-IBD).

METHODS

We designed a web-based learning module that includes surveillance principles, optical diagnostic methods, approach to characterization, and classifications of colonic lesions using still images and videos. We invited gastroenterologists from Canada, Italy, and the United Kingdom with a wide range of experience. Participants reviewed 24 educational videos of IBD colonic lesions, predicted histology, and rated their confidence. The primary endpoint was to improve accuracy in detecting dysplastic lesions after training on the platform. Furthermore, participants were randomized 1:1 to get additional training or not, with a final assessment occurring after 60 days. Diagnostic performance for dysplasia and rater confidence were measured.

RESULTS

A total of 117 participants completed the study and were assessed for the primary endpoint. Diagnostic accuracy improved from 70.8% to 75.0% (P = .002) after training, with the greatest improvements seen in less experienced endoscopists. Improvements in both accuracy and confidence were sustained after 2 months of assessment, although the group randomized to receive additional training did not improve further. Similarly, participants' confidence in characterizing lesions significantly improved between before and after the course (P < .001), and it was sustained after 2 months of assessment.

CONCLUSIONS

The OPTIC-IBD training module demonstrated that an online platform could improve participants' accuracy and confidence in the optical diagnosis of dysplasia in patients with IBD. The training platform can be widely available and improve endoscopic care for people with IBD. (Clinical trial registration number: NCT04924543.).

Proposed clinical operative synoptic report for ileocolic resection for Crohn's disease

BACKGROUND

Crohn's disease patients may require multiple surgeries during their lifetime. Because operative reports are not standardized, information relevant to future management may not be documented. Synoptic reports used in other fields such as histopathology have proven to be effective and allow consistent documentation of results. The aim of this study was to retrospectively review the completeness of the operative reports for ileocolic Crohn's resections (ICR) and to propose a synoptic report.

METHODS

A draft synoptic operative report for ICR for Crohn's disease was presented in the IBD multidisciplinary meeting and a Delphi process used to gain consensus for inclusion in the synoptic report. Retrospective analysis of consecutive ICR from January 2010 to April 2023 was undertaken to determine the presence of the standardized criteria.

RESULTS

A total of 66 ICR were performed in 63 patients during the study period. No operation reports were excluded. The examination of bowel for macroscopic disease was partially documented in 88% cases. The extent of mesenteric resection and any difficulty encountered during dissection were poorly documented. The remaining length of small and large intestines was not documented in most operative reports. The clinical sections that were compulsory entrance in the electronic operative report achieved 100% compliance.

CONCLUSION

This study has demonstrated that key information was often deficient in the operative report. This may have a significant impact on the future management of Crohn's patients and affects the interpretation of research outcomes. A proposed clinical synoptic operative report is easy to use and ensures compliance.

Present and future of endoscopy precision for inflammatory bowel disease

Several advanced imaging techniques are now available for endoscopists managing inflammatory bowel disease (IBD) patients. These tools, including dye-based and virtual chromoendoscopy, probe-based confocal laser endomicroscopy and endocytoscopy, are increasingly innovative applications in clinical practice. They allow for a more in-depth and refined evaluation of the mucosal and vascular bowel surface, getting closer to histology. They have demonstrated a remarkable ability in assessing intestinal inflammation, histologic remission, and predicting relapse and favorable long-term outcomes. In addition, the future application of molecular endoscopy to predict biological drug responses has yielded preliminary but encouraging results. Furthermore, these techniques are crucial in detecting and characterizing IBD-related dysplasia, assisting endoscopic mucosal resection and submucosal dissection towards a surgery-sparing approach. Artificial intelligence (AI) holds great potential in this promising landscape, as it can provide an objective and reproducible assessment of inflammation and dysplasia. Moreover, it can improve the prediction of outcomes and aid in subsequent therapeutic decision-making. This review aims to summarize the promising role of state-of-the-art advanced endoscopic techniques and related AI-enabled models for managing IBD, paving the way for precision medicine.

Patient-reported Outcome Measures in Ileoanal Pouch Surgery: a Systematic Review

OBJECTIVE

To summarise frequency, type, and heterogeneity of patient-reported outcomes measures [PROMs] in papers reporting on outcomes after ileal pouch anal anastomosis [IPAA].

BACKGROUND

Prevalence of ulcerative colitis [UC] has risen in Western countries, and one in three patients requires surgery. IPAA is a frequently performed procedure for UC, and a lack of standardisation is manifest in reporting outcomes for inflammatory bowel disease [IBD] despite the clear need for inclusion of PROMs as primary outcomes in IBD trials.

METHODS

Scopus, Pubmed, and Web of Science databases were searched from January 2010 to January 2023 for studies investigating outcomes in IPAA surgery. The primary outcome was the proportion of studies reporting outcomes for IPAA surgery for UC, which included PROMs.

RESULTS

The search identified a total of 8028 studies which, after de-duplication and exclusion, were reduced to 79 articles assessing outcomes after IPAA surgery. In all 44 [55.7%] reported PROMs, with 23 including validated questionnaires and 21 papers using authors' questions, 22 different PROMs were identified, with bowel function as the most investigated item. The majority of studies [67/79, 85%] were retrospective, only 14/79 [18%] were prospective papers and only two were [2.5%] randomised, controlled trials.

CONCLUSIONS

Only half of the papers reviewed used PROMs. The main reported item is bowel function and urogenital, social, and psychological functions are the most neglected. There is lack of standardisation for use of PROMs in IPAA. Complexity of UC and of outcomes after IPAA demands a change in clinical practice and follow-up, given how crucial PROMs are, compared with their non-routine use.

Dysplasia detection rates under a surveillance program in a tertiary referral center for inflammatory bowel diseases: Real-world data

BACKGROUND AND AIMS

Surveillance colonoscopies are crucial for high-risk patients with inflammatory bowel diseases (IBD) to detect colorectal carcinoma (CRC). However, there is no established quality metric for dysplasia detection rate (DDR) in IBD surveillance. This study assessed the DDR in a dedicated surveillance program at a tertiary referral center for IBD.

METHODS

Consecutive patients with quiescent colitis were enrolled in a cross-sectional study evaluating DDR. High-definition colonoscopy with dye chromoendoscopy (DCE) was performed by a specialized operator. Advanced dysplasia (AD) was defined as low-grade dysplasia ≥ 10 mm, high-grade dysplasia, or colorectal cancer. Risk factors for dysplasia detection were analyzed.

RESULTS

In total, 119 patients underwent 151 procedures, identifying 206 lesions, of which 40 dysplastic with seven AD . Per-lesion and per-procedure DDR were 19.4 % and 20.5 %, respectively. The per-procedure AD detection rate (ADDR) was 4.6 %. A Kudo pit pattern of II-V had a sensitivity of 92.5 % for dysplasia detection but a false positive rate of 64.8 % (p < 0.001). Age at diagnosis and at index colonoscopy and past or indefinite dysplasia were associated with per-procedure dysplasia detection.

CONCLUSIONS

In a real-world setting, a dedicated surveillance program achieved a high DDR. We suggest that optimal DDR in high-risk IBD patients be defined and implemented as a standardized quality measure for surveillance programs.

A step-by-step guide to ileoanal J-pouch MRI interpretation

BACKGROUND

Multidisciplinary management of patients with an ileoanal pouch requires dedicated imaging to identify structural problems of the pouch associated with dysfunction. The purpose of this study is to provide a framework for interpretation of magnetic resonance imaging (MRI) scan of the ileoanal pouch to enable surgeons and radiologists to work cohesively, optimise diagnosis and ultimately improve patient care.

METHODS

We propose a protocol for structured MRI assessment of the ileal pouch, aiming to provide surgeons a systematic report of the anatomy, its variations and pouch complications. This guide consists of studying the characteristics of the bowel, mesentery and anal canal.

RESULTS

The presented checklist is designed to systematically interpret and identify abnormalities of the ileoanal pouch on MRI. It focuses on the characteristics of the bowel (encompassing pre-pouch ileum, pouch and rectal cuff), mesentery and anal canal. The different elements of the checklist are presented in the associated supplementary video.

CONCLUSIONS

A combination of clinical assessment, endoscopic evaluations and imaging is fundamental to achieving accurate diagnosis of ileoanal pouch surgery complications and pouch dysfunction.

Evaluation of Gastrointestinal System Complaints and Comorbidities in Pediatric Familial Mediterranean Fever Patients

OBJECTIVE

Familial Mediterranean fever (FMF) is the most prevalent hereditary autoinflammatory disease among children. Abdominal pain and various gastrointestinal system (GIS) manifestations may arise directly from FMF or concomitantly with FMF. This study aimed to evaluate GIS complaints and findings other than classic peritonitis attacks in patients with FMF and to interpret concomitant GIS and hepatic disorders in these patients.

METHODS

The medical and genetic findings of patients with FMF who attended our clinic between December 2011 and December 2021 were reviewed. Gastrointestinal system symptoms, liver function tests, abdominal images, and endoscopic and histopathological data were extracted from medical records.

RESULTS

A total of 576 pediatric patients (female, 52.3%) diagnosed with FMF were included. Among them, almost one-fifth displayed GIS complaints, such as abdominal pain, defecation problems, and dyspepsia, distinct from typical FMF attacks. High serum aminotransferase levels were detected in 18.4% of the patients, with viral infections being the most common cause of moderate/severe hypertransaminasemia. In addition, during follow-up, 26.9% of them were referred to the pediatric gastroenterology department. At least 1 gastroenterological and hepatobiliary disorder was detected in 17.5% of the patients because of organic and functional GIS disorders or hepatobiliary disorders, such as gastroesophageal reflux disease, esophagitis, functional dyspepsia, and inflammatory bowel diseases.

CONCLUSION

Various GIS and hepatic disorders can be encountered in children with FMF. The spectrum of these complaints and pathologies can range from frequently observed health problems to more severe diseases.

Results of the Eighth Scientific Workshop of ECCO: Pathophysiology and Risk Factors of Postoperative Crohn's Disease Recurrence after an Ileocolonic Resection

Postoperative recurrence [POR] after an ileocolonic resection with ileocolonic anastomosis is frequently encountered in patients with Crohn's disease. The 8th Scientific Workshop of ECCO reviewed the available evidence on the pathophysiology and risk factors for POR. In this paper, we discuss published data on the role of the microbiome, the mesentery, the immune system and the genetic background. In addition to investigating the causative mechanisms of POR, identification of risk factors is essential to tailor preventive strategies. Potential clinical, surgical and histological risk factors are presented along with their limitations. Emphasis is placed on unanswered research questions, guiding prevention of POR based on individual patient profiles.

Sensitivity and specificity of diagnostic modalities in pouchitis: a systematic review and meta-analysis

Restorative proctocolectomy (RPC) is the most common surgical procedure to restore gastrointestinal continuity after surgical resection of the colon and rectum. Pouchitis is a common complication with several different modalities that can be used to aid diagnosis. This systematic review and meta-analysis aimed at exploring the sensitivity and specificity these diagnostic modalities. The medical literature was searched using MEDLINE, EMBASE and EMBASE classic and PubMed from 1978 to June 2022. We calculated descriptive statistics using sensitivity, specificity, and false-positive rate of the primary studies and also their positive and negative likelihood ratios, and their diagnostic odds ratios. The screen found 5477 records with 13 studies being included. Faecal lactoferrin was found to have the highest pooled sensitivity and specificity of 98% and 88% respectively with imaging modalities coming in second and faecal calprotectin third with pooled sensitivities and specificities of 87% and 79% and 74% and 81% respectively. Faecal biomarkers particularly lactoferrin and imaging modalities may have an important role to play in diagnosing pouchitis. Importantly due to delays in availability of pouchoscopy, our data supports early ordering of these tests to help delineate from other causes. Further studies are required with larger cohort sizes to further validate these tests.

Update on Endoscopic Dysplasia Surveillance in Inflammatory Bowel Disease

As medical management of inflammatory bowel disease makes great advances, most patients with inflammatory bowel disease will have long life expectancies without need for total colectomy. With prolonged disease duration, however, there is increased risk of dysplasia leading to colorectal cancer. Multiple consensus and guideline documents have been published over the last decade with recommendations to optimize early detection and management of dysplastic lesions. Endoscopic technology has improved tremendously, even over the past few years. Previously invisible dysplasia has become visible in most cases with advanced imaging technologies that now allow for much clearer and more detailed mucosal inspection. New tools to facilitate endoscopic resection of visible lesions have also enabled patients to avoid colectomy, with resulting need to continue colon surveillance. There are limited or conflicting data leading to inconsistent recommendations regarding the need for random biopsies, the preferred endoscopic imaging technique, and surveillance intervals after resection of dysplasia. Similarly, there remains significant variability in the application of guidelines into daily practice and availability of and training with advanced imaging technologies. Here, we present a narrative review of which patients are at highest risk for dysplasia, the current guidelines on surveillance colonoscopy, factors affecting optimal mucosal visualization, enhanced imaging techniques, standardized reporting terminologies for surveillance colonoscopy, endoscopic management of dysplasia, indications for colectomy, and briefly on future potential technologies to assist in dysplasia detection.

Considerations for Colorectal Neoplasia Detection in Inflammatory Bowel Disease Clinical Trials

BACKGROUND

High-quality colonoscopic surveillance can lead to earlier and increased detection of colorectal neoplasia in patients with inflammatory bowel disease (IBD). In IBD clinical trials, endoscopy is used to assess mucosal disease activity before and after treatment but also provides an opportunity to surveil for colorectal neoplasia during follow-up.

SUMMARY

Best practices for colorectal cancer identification in IBD clinical trials require engagement and collaboration between the clinical trial sponsor, site endoscopist and/or principal investigator, and central read team. Each team member has unique responsibilities for maximizing dysplasia detection in IBD trials.

KEY MESSAGES

Sponsors should work in accordance with scientific guidelines to standardize imaging procedures, design the protocol to ensure the trial population is safeguarded, and oversee trial conduct. The site endoscopist should remain updated on best practices to tailor sponsor protocol-required procedures to patient needs, examine the mucosa for disease activity and potential dysplasia during all procedures, and provide optimal procedure videos for central read analysis. Central readers may detect dysplasia or colorectal cancer and a framework to report these findings to trial sponsors is essential. Synergistic relationships between all team members in IBD clinical trials provide an important opportunity for extended endoscopic evaluation and colorectal neoplasia identification.

Telemedicine in inflammatory bowel diseases: A new brick in the medicine of the future?

Inflammatory bowel disease (IBD) is a chronic digestive disease that requires continuous monitoring by healthcare professionals to determine the appropriate therapy and monitor short-term and long-term complications. The progressive development of information technology has enabled healthcare personnel to deliver care services to patients remotely. Therefore, various applications of telemedicine in IBD management have evolved, including telemonitoring, teleconsulting, teleducation, telenursing, telenutrition, and telepathology. While evidence has been provided for some telemedicine applications, targeted studies are still required. This review summarises the major studies that have evaluated telemedicine and its application in the management of IBD.

Effect of a deep learning-based automatic upper GI endoscopic reporting system: a randomized crossover study (with video)

BACKGROUND AND AIMS

EGD is essential for GI disorders, and reports are pivotal to facilitating postprocedure diagnosis and treatment. Manual report generation lacks sufficient quality and is labor intensive. We reported and validated an artificial intelligence-based endoscopy automatic reporting system (AI-EARS).

METHODS

The AI-EARS was designed for automatic report generation, including real-time image capturing, diagnosis, and textual description. It was developed using multicenter datasets from 8 hospitals in China, including 252,111 images for training, 62,706 images, and 950 videos for testing. Twelve endoscopists and 44 endoscopy procedures were consecutively enrolled to evaluate the effect of the AI-EARS in a multireader, multicase, crossover study. The precision and completeness of the reports were compared between endoscopists using the AI-EARS and conventional reporting systems.

RESULTS

In video validation, the AI-EARS achieved completeness of 98.59% and 99.69% for esophageal and gastric abnormality records, respectively, accuracies of 87.99% and 88.85% for esophageal and gastric lesion location records, and 73.14% and 85.24% for diagnosis. Compared with the conventional reporting systems, the AI-EARS achieved greater completeness (79.03% vs 51.86%, P < .001) and accuracy (64.47% vs 42.81%, P < .001) of the textual description and completeness of the photo-documents of landmarks (92.23% vs 73.69%, P < .001). The mean reporting time for an individual lesion was significantly reduced (80.13 ± 16.12 seconds vs 46.47 ± 11.68 seconds, P < .001) after the AI-EARS assistance.

CONCLUSIONS

The AI-EARS showed its efficacy in improving the accuracy and completeness of EGD reports. It might facilitate the generation of complete endoscopy reports and postendoscopy patient management. (Clinical trial registration number: NCT05479253.).

[Inflammatory bowel diseases: Scoring and pathological reports optimization]

The two main forms of inflammatory bowel disease (IBD) are ulcerative colitis (UC) and Crohn's disease (CD). Both diseases have inflammatory flare-ups that alternate with periods of remission. The pathologist may examine biopsies of the digestive tract from IBD patients in different contexts: at the time of the initial diagnosis, in the event of a disease flare-up in order to differentiate a flare of the disease from another cause, particularly an infectious one, and during the long term follow-up of the disease in order to detect the occurrence of dysplastic lesions. Pathologists are increasingly involved in the evaluation of inflammatory activity during the follow-up of IBD patients. The therapeutic management of IBD has evolved significantly and the emergence of new treatments allows a global approach targeting endoscopic mucosal healing. However, mucosal healing is not always correlated with histological healing. Numerous studies have shown the value of histological evaluation during follow-up. A higher score for histological activity in ulcerative colitis predicts a higher likelihood of neoplasia. Histological activity is a better predictor than endoscopic inflammation of the risk. In UC, histological remission may be a long-term therapeutic goal but its role in CD remains unclear. Different scores have been developed to quantify the inflammatory activity of IBD patients and the response to treatment. The aim of this review is to present the main activity scores used in the follow-up of IBD, their interest, their evaluation and their limitations.

Image-Enhanced Endoscopy in the Surveillance of Colitis-Associated Neoplasia

Advances in endoscopic technology have allowed for improved detection and management of dysplasia. These developments have also raised the question of the optimal methods for surveillance. Promising data showed that virtual chromoendoscopy (VCE) is comparable to dye-based chromoendoscopy (DCE). However, the usefulness of DCE and VCE in the surveillance of longstanding inflammatory bowel disease colitis when compared with high-definition white-light endoscopy has been recently questioned. Confocal laser endomicroscopy is a highly innovative endoscopic procedure but is still far from the routine adoption for surveillance. Thus, a personalized approach should guide the most appropriate surveillance strategy.

Histological Indices and Risk of Recurrence in Crohn's Disease: A Retrospective Study of a Cohort of Patients in Endoscopic Remission

BACKGROUND

Although histological healing is raising interest in ulcerative colitis to predict recurrence, its meaning in Crohn's disease (CD) remains unknown. We aimed to study the performances of different histological indices to predict recurrence of CD patients with mucosal healing.

METHODS

Crohn's disease patients with mucosal healing diagnosed between 2010 and 2018 were included if there was available clinical and endoscopical data. Nancy Histological index (NHI), Geboes score (GS), Robarts Histopathology index (RHI), Global Histological Disease Activity Score (GHAS), and Inflammatory Bowel Disease-Distribution Chronicity Activity score (IBD-DCA) were independently assessed by 3 pathologists.

RESULTS

Eighty-eight patients were included, of which 28 relapsed (32%) within 30.5 months. All 4 histological indices were associated with recurrence, with significant relapse risk (NHI, odds ratio [OR], 1.67; GHAS, OR, 2.33; RHI, OR, 1.19; GS, OR, 2.09; and IBD-DCA, OR, 2.14). Microscopic activity was significantly associated with relapse only with the IBD-DCA score. Predicting performances of all these scores were poor. Calibration curves indicate that the GHAS and IBD-DCA are the closest to the ideal predicted probability curve and thus could better predict recurrence than the other scores. Interobserver agreement varied from poor for GHAS (k = .39) to good for RHI (k = .68).

CONCLUSIONS

Histological scores are valuable indicators to predict recurrence. Histological assessment of activity seems insufficient to predict CD course with most of the score evaluated, highlighting the need for new indices or adaptation of actual scores to CD specificities.

Colorectal Cancer Surveillance in Patients with Inflammatory Bowel Diseases: Chromoendoscopy or Non-Chromoendoscopy, That Is the Question

Subjects affected by ulcerative colitis and Crohn’s disease with colonic localization have an increased risk of colorectal cancer (CRC). Surveillance colonoscopy is recommended by international guidelines as it can detect early-stage CRC. Based on previous evidence, in 2015 the Surveillance for Colorectal Endoscopic Neoplasia Detection and Management in Inflammatory Bowel Disease Patients International Consensus indicated dye chromoendoscopy (DCE) as the most effective technique for detecting dysplasia. However, advances in endoscopic technology such as high-definition colonoscopes and dye-less virtual chromoendoscopy (VCE) may change future practice. In this review, we summarize the available evidence on CRC surveillance in IBD, focusing on the emerging role of high-definition white light endoscopy (HD-WLE) and VCE over the standard DCE, and the current role of random biopsies.

Sampling and Reporting of Inflammatory Bowel Disease

Pathologists have an important and expanding role in the diagnosis and management of inflammatory bowel disease. This role includes the initial diagnosis of the disease, assessment of the response to treatment and the identification of short-term complications such as cytomegalovirus infection and long-term complications such as dysplasia. Furthermore, the assessment of resection specimens for complication of disease is important to determining the risk of subsequent disease or inflammation within an ileal pouch. Adequate sampling of the disease at endoscopy and from the surgical resection specimen is vital to determining the ultimate information that can be provided by the pathologist. This sampling is determined by the clinical scenario. Similarly, a standardized approach to reporting and synthesizing the histologic findings will improve patient management. This is best exemplified by the increasing interest in histologic activity indices, such as the Nancy index in ulcerative colitis, and in the standardized reporting for inflammatory bowel disease dysplasia recommended by the SCENIC international consensus.

Update on the mesentery: structure, function, and role in disease

Over the past 5 years, systematic investigation of the mesenteric organ has expanded and shown that the mesentery is the organ in and on which all abdominal digestive organs develop and remain connected to. In turn, this observation has clarified the anatomical foundation of the abdomen and the fundamental order at that level. Findings related to the shape and development of the mesentery have illuminated its function, advancing our understanding of the pathobiology, diagnosis, and treatment of several abdominal and systemic diseases. Inclusion of the mesentery in surgical resections alters the course of benign and malignant diseases. Mesenteric-based scoring systems can enhance the radiological interpretation of abdominal disease. Emerging findings reconcile observations across scientific and clinical fields and have been assimilated into reference curricula and practice guidelines. This Review summarises the developmental, anatomical, and clinical advances made since the mesentery was redesignated as an organ in 2016.

Surveillance and management of colorectal dysplasia and cancer in inflammatory bowel disease: Current practice and future perspectives

Patients with inflammatory bowel disease (IBD) are at increased risk of developing colorectal cancer (CRC). Current guidelines recommend frequent surveillance colonoscopies for patients with at least left-sided ulcerative colitis, or Crohn's disease involving more than 30% of the colon. Surveillance allows for early detection and treatment of colorectal dysplasia and cancer. The first colonoscopy should be performed 8 to 10 years after onset of disease symptoms. European and British guidelines employ a risk-stratification algorithm that assigns patients to surveillance intervals of one, three or five years, whereas American guidelines recommend to perform surveillance every 1 to 3 years based on the (combined) presence of risk factors. Patients with concomitant primary sclerosing cholangitis are at an additionally increased risk, and should undergo annual surveillance starting immediately after the diagnosis. The current practice of surveillance is based on limited evidence, is resource intensive and cannot preclude the occurrence of interval carcinomas. Fortunately, advances in endoscopic techniques for mucosal visualisation, along with better control of inflammation, have resulted in a declining incidence of CRC in patients with IBD. Furthermore, advanced endoscopic resection techniques can be expected to result in a shift from surgical to endoscopic management of dysplastic lesions. In this review, we provide an up-to-date overview of colitis-associated CRC pathophysiology, epidemiology, surveillance practices, and management of dysplasia.

AGA Clinical Practice Update on Endoscopic Surveillance and Management of Colorectal Dysplasia in Inflammatory Bowel Diseases: Expert Review

Improvements in disease management, as well as endoscopic technology and quality, have dramatically changed the way in which we conceptualize and manage inflammatory bowel disease-related dysplasia over the past 20 years. Based on evolving literature, we propose a conceptual model and best practice advice statements for the prevention, detection, and management of colorectal dysplasia in people with inflammatory bowel disease. This expert review was commissioned and approved by the American Gastroenterological Association Institute Clinical Practice Updates Committee and the American Gastroenterological Association Governing Board to provide timely guidance on a topic of high clinical importance to the American Gastroenterological Association membership. It underwent internal peer review by the Clinical Practice Updates Committee and external peer review through standard procedures of Gastroenterology.

Artificial intelligence in gastrointestinal endoscopy for inflammatory bowel disease: a systematic review and new horizons

INTRODUCTION

Since the advent of artificial intelligence (AI) in clinical studies, luminal gastrointestinal endoscopy has made great progress, especially in the detection and characterization of neoplastic and preneoplastic lesions. Several studies have recently shown the potential of AI-driven endoscopy for the investigation of inflammatory bowel disease (IBD). This systematic review provides an overview of the current position and future potential of AI in IBD endoscopy.

METHODS

A systematic search was carried out in PubMed and Scopus up to 2 December 2020 using the following search terms: artificial intelligence, machine learning, computer-aided, inflammatory bowel disease, ulcerative colitis (UC), Crohn's disease (CD). All studies on human digestive endoscopy were included. A qualitative analysis and a narrative description were performed for each selected record according to the Joanna Briggs Institute methodologies and the PRISMA statement.

RESULTS

Of 398 identified records, 18 were ultimately included. Two-thirds of these (12/18) were published in 2020 and most were cross-sectional studies (15/18). No relevant bias at the study level was reported, although the risk of publication bias across studies cannot be ruled out at this early stage. Eleven records dealt with UC, five with CD and two with both. Most of the AI systems involved convolutional neural network, random forest and deep neural network architecture. Most studies focused on capsule endoscopy readings in CD (n = 5) and on the AI-assisted assessment of mucosal activity in UC (n = 10) for automated endoscopic scoring or real-time prediction of histological disease.

DISCUSSION

AI-assisted endoscopy in IBD is a rapidly evolving research field with promising technical results and additional benefits when tested in an experimental clinical scenario. External validation studies being conducted in large and prospective cohorts in real-life clinical scenarios will help confirm the added value of AI in assessing UC mucosal activity and in CD capsule reading.

PLAIN LANGUAGE SUMMARY

Artificial intelligence for inflammatory bowel disease endoscopy Artificial intelligence (AI) is a promising technology in many areas of medicine. In recent years, AI-assisted endoscopy has been introduced into several research fields, including inflammatory bowel disease (IBD) endoscopy, with promising applications that have the potential to revolutionize clinical practice and gastrointestinal endoscopy.We have performed the first systematic review of AI and its application in the field of IBD and endoscopy.A formal process of paper selection and analysis resulted in the assessment of 18 records. Most of these (12/18) were published in 2020 and were cross-sectional studies (15/18). No relevant biases were reported. All studies showed positive results concerning the novel technology evaluated, so the risk of publication bias cannot be ruled out at this early stage.Eleven records dealt with UC, five with CD and two with both. Most studies focused on capsule endoscopy reading in CD patients (n = 5) and on AI-assisted assessment of mucosal activity in UC patients (n = 10) for automated endoscopic scoring and real-time prediction of histological disease.We found that AI-assisted endoscopy in IBD is a rapidly growing research field. All studies indicated promising technical results. When tested in an experimental clinical scenario, AI-assisted endoscopy showed it could potentially improve the management of patients with IBD.Confirmatory evidence from real-life clinical scenarios should be obtained to verify the added value of AI-assisted IBD endoscopy in assessing UC mucosal activity and in CD capsule reading.