Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

Accuracy of optical diagnosis with narrow band imaging in the surveillance of ulcerative colitis: a prospective study comparing Kudo, Kudo-IBD and NICE classifications

PURPOSE

The diagnostic accuracy of Narrow Band Imaging (NBI) in the endoscopic surveillance of ulcerative colitis (UC) has been disappointing in most trials which used the Kudo classification. We aim to compare the performance of NBI in the lesion characterization of UC, when applied according to three different classifications (NICE, Kudo, Kudo-IBD).

METHODS

In a prospective, real-life study, all visible lesions found during consecutive surveillance colonoscopies with NBI (Exera-II CV-180) for UC were classified as suspected or non-suspected for neoplasia according to the NICE, Kudo and Kudo-IBD criteria. The sensitivity (SE), specificity (SP), positive (+LR) and negative (-LR) likelihood ratios of the three classifications were calculated, using histology as the reference standard.

RESULTS

394 lesions (mean size 6 mm, range 2-40 mm) from 84 patients were analysed. Twenty-one neoplastic (5%), 49 hyperplastic (12%), and 324 inflammatory (82%) lesions were found. The diagnostic accuracy of the NICE, Kudo and Kudo-IBD classifications were, respectively: SE 76%-71%-86%; SP 55-69%-79% (p < 0.05 Kudo-IBD vs. both Kudo and NICE); +LR 1.69-2.34-4.15 (p < 0.05 Kudo-IBD vs. both Kudo and NICE); -LR 0.43-0.41-0.18.

CONCLUSION

The diagnostic accuracy of NBI in the differentiation of neoplastic and non-neoplastic lesions in UC is low if used with conventional classifications of the general population, but it is significantly better with the modified Kudo classification specific for UC.

Computer-Aided Diagnosis for Leaving Colorectal Polyps In Situ : A Systematic Review and Meta-analysis

BACKGROUND

Computer-aided diagnosis (CADx) allows prediction of polyp histology during colonoscopy, which may reduce unnecessary removal of nonneoplastic polyps. However, the potential benefits and harms of CADx are still unclear.

PURPOSE

To quantify the benefit and harm of using CADx in colonoscopy for the optical diagnosis of small (≤5-mm) rectosigmoid polyps.

DATA SOURCES

Medline, Embase, and Scopus were searched for articles published before 22 December 2023.

STUDY SELECTION

Histologically verified diagnostic accuracy studies that evaluated the real-time performance of physicians in predicting neoplastic change of small rectosigmoid polyps without or with CADx assistance during colonoscopy.

DATA EXTRACTION

The clinical benefit and harm were estimated on the basis of accuracy values of the endoscopist before and after CADx assistance. The certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. The outcome measure for benefit was the proportion of polyps predicted to be nonneoplastic that would avoid removal with the use of CADx. The outcome measure for harm was the proportion of neoplastic polyps that would be not resected and left in situ due to an incorrect diagnosis with the use of CADx. Histology served as the reference standard for both outcomes.

DATA SYNTHESIS

Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed. The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change. In the studies that compared histology prediction performance before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; risk ratio [RR], 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence) or in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence).

LIMITATION

The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator.

CONCLUSION

Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy.

PRIMARY FUNDING SOURCE

European Commission. (PROSPERO: CRD42023402197).

Computer-aided diagnosis system for optical diagnosis of colorectal polyps under white light imaging

OBJECTIVES

This study presents a novel computer-aided diagnosis (CADx) designed for optically diagnosing colorectal polyps using white light imaging (WLI).We aimed to evaluate the effectiveness of the CADx and its auxiliary role among endoscopists with different levels of expertise.

METHODS

We collected 2,324 neoplastic and 3,735 nonneoplastic polyp WLI images for model training, and 838 colorectal polyp images from 740 patients for model validation. We compared the diagnostic accuracy of the CADx with that of 15 endoscopists under WLI and narrow band imaging (NBI). The auxiliary benefits of CADx for endoscopists of different experience levels and for identifying different types of colorectal polyps was also evaluated.

RESULTS

The CADx demonstrated an optical diagnostic accuracy of 84.49%, showing considerable superiority over all endoscopists, irrespective of whether WLI or NBI was used (P < 0.001). Assistance from the CADx significantly improved the diagnostic accuracy of the endoscopists from 68.84% to 77.49% (P = 0.001), with the most significant impact observed among novice endoscopists. Notably, novices using CADx-assisted WLI outperform junior and expert endoscopists without such assistance.

CONCLUSIONS

The CADx demonstrated a crucial role in substantially enhancing the precision of optical diagnosis for colorectal polyps under WLI and showed the greatest auxiliary benefits for novice endoscopists.

Artificial intelligence for dysplasia detection during surveillance colonoscopy in patients with ulcerative colitis: A cross-sectional, non-inferiority, diagnostic test comparison study

BACKGROUND AND STUDY AIM

High-definition virtual chromoendoscopy, along with targeted biopsies, is recommended for dysplasia surveillance in ulcerative colitis patients at risk for colorectal cancer. Computer-aided detection (CADe) systems aim to improve colonic adenoma detection, however their efficacy in detecting polyps and adenomas in this context remains unclear. This study evaluates the CADe Discovery™ system's effectiveness in detecting colonic dysplasia in ulcerative colitis patients at risk for colorectal cancer.

PATIENTS AND METHODS

A prospective cross-sectional, non-inferiority, diagnostic test comparison study was conducted on ulcerative colitis patients undergoing colorectal cancer surveillance colonoscopy between January 2021 and April 2021. Patients underwent virtual chromoendoscopy (VCE) with iSCAN 1 and 3 with optical enhancement. One endoscopist, blinded to CADe Discovery™ system results, examined colon sections, while a second endoscopist concurrently reviewed CADe images. Suspicious areas detected by both techniques underwent resection. Proportions of dysplastic lesions and patients with dysplasia detected by VCE or CADe were calculated.

RESULTS

Fifty-two patients were included, and 48 lesions analyzed. VCE and CADe each detected 9 cases of dysplasia (21.4% and 20.0%, respectively; p=0.629) in 8 patients and 7 patients (15.4% vs. 13.5%, respectively; p=0.713). Sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy for dysplasia detection using VCE or CADe were 90% and 90%, 13% and 5%, 21% and 2%, 83% and 67%, and 29.2% and 22.9%, respectively.

CONCLUSIONS

The CADe Discovery™ system shows similar diagnostic performance to VCE with iSCAN in detecting colonic dysplasia in ulcerative colitis patients at risk for colorectal cancer.

White light computer-aided optical diagnosis of diminutive colorectal polyps in routine clinical practice

Background and study aims Artificial Intelligence (AI) systems could make the optical diagnosis (OD) of diminutive colorectal polyps (DCPs) more reliable and objective. This study was aimed at prospectively evaluating feasibility and diagnostic performance of AI-standalone and AI-assisted OD of DCPs in a real-life setting by using a white light-based system (GI Genius, Medtronic Co, Minneapolis, Minnesota, United States). Patients and methods Consecutive colonoscopy outpatients with at least one DCP were evaluated by 11 endoscopists (5 experts and 6 non-experts in OD). DCPs were classified in real time by AI (AI-standalone OD) and by the endoscopist with the assistance of AI (AI-assisted OD), with histopathology as the reference standard. Results Of the 480 DCPs, AI provided the outcome "adenoma" or "non-adenoma" in 81.4% (95% confidence interval [CI]: 77.5-84.6). Sensitivity, specificity, positive and negative predictive value, and accuracy of AI-standalone OD were 97.0% (95% CI 94.0-98.6), 38.1% (95% CI 28.9-48.1), 80.1% (95% CI 75.2-84.2), 83.3% (95% CI 69.2-92.0), and 80.5% (95% CI 68.7-82.8%), respectively. Compared with AI-standalone, the specificity of AI-assisted OD was significantly higher (58.9%, 95% CI 49.7-67.5) and a trend toward an increase was observed for other diagnostic performance measures. Overall accuracy and negative predictive value of AI-assisted OD for experts and non-experts were 85.8% (95% CI 80.0-90.4) vs. 80.1% (95% CI 73.6-85.6) and 89.1% (95% CI 75.6-95.9) vs. 80.0% (95% CI 63.9-90.4), respectively. Conclusions Standalone AI is able to provide an OD of adenoma/non-adenoma in more than 80% of DCPs, with a high sensitivity but low specificity. The human-machine interaction improved diagnostic performance, especially when experts were involved.

Enhancing endoscopic measurement: validating a quantitative method for polyp size and location estimation in upper gastrointestinal endoscopy

BACKGROUND

Accurate measurement of polyps size is crucial in predicting malignancy, planning relevant intervention strategies and surveillance schedules. Endoscopists' visual estimations can lack precision. This study builds on our prior research, with the aim to evaluate a recently developed quantitative method to measure the polyp size and location accurately during a simulated endoscopy session.

METHODS

The quantitative method merges information about endoscopic positions obtained from an electromagnetic tracking sensor, with corresponding points on the images of the segmented polyp border. This yields real-scale 3D coordinates of the border of the polyp. By utilising the sensor, positions of any anatomical landmarks are attainable, enabling the estimation of a polyp's location relative to them. To verify the method's reliability and accuracy, simulated endoscopies were conducted in pig stomachs, where polyps were artificially created and assessed in a test-retest manner. The polyp measurements were subsequently compared against clipper measurements.

RESULTS

The average size of the fifteen polyps evaluated was approximately 12 ± 4.3 mm, ranging from 5 to 20 mm. The test-retest reliability, measured by the Intraclass Correlation Coefficient (ICC) for polyp size estimation, demonstrated an absolute agreement of 0.991 (95% CI 0.973-0.997, p < 0.05). Bland & Altman analysis revealed a mean estimation difference of - 0.17 mm (- 2.03%) for polyp size and, a mean difference of - 0.4 mm (- 0.21%) for polyp location. Both differences were statistically non-significant (p > 0.05). When comparing the proposed method with calliper measurements, the Bland & Altman plots showed 95% of size estimation differences between - 1.4 and 1.8 mm (- 13 to 17.4%) which was not significant (p > 0.05).

CONCLUSIONS

The proposed method of measurements of polyp size and location was found to be highly accurate, offering great potential for clinical implementation to improve polyp assessment. This level of performance represents a notable improvement over visual estimation technique used in clinical practice.

Implementing narrow banding imaging with dual focus magnification for histological prediction of small rectosigmoid polyps in Vietnamese setting

Background and Aim

Small rectosigmoid colorectal polyps (<10 mm) are prevalent, with a low prevalence of advanced neoplastic lesions. The "diagnose-and-leave" strategy, employing narrow band imaging (NBI), is gaining popularity for its safety and cost-effectiveness by reducing polypectomy complications and minimizing histopathology expenses. This study assessed the diagnostic efficacy of NBI with dual focus (DF) magnification for real-time neoplastic prediction of rectosigmoid polyps and explored the feasibility of implementing this strategy in Vietnam.

Methods

In a prospective single-center study, 307 rectosigmoid polyps from 245 patients were analyzed using three consecutive endoscopic modes: white light endoscopy (WLE), NBI, and NBI-DF. Endoscopists assessed polyps for size, location, macroscopic shape, optical diagnosis, and confidence levels before histopathological evaluation. High confidence was assigned when the polyp exhibited all features of a single histology type. Predictions were compared with final histopathology results.

Results

Of the total, 237 (77.2%) were diminutive (≤5 mm) polyps, and 18 (5.8%) were advanced neoplastic lesions. WLE + NBI and WLE + NBI + NBI-DF exhibited significantly higher accuracy compared to WLE (88.6% and 90.2% vs 74.2%, P < 0.01). For diminutive polyps, the DF mode significantly increased the rate of high-confidence optical diagnoses (89.1% vs 94.9%, P < 0.001). WLE + NBI + NBI-DF demonstrated high sensitivity (90.1%), specificity (95.5%), and negative predictive value (93.4%) in high-confidence predictions, enabling the implementation of the "diagnose-and-leave" strategy. This approach would have reduced 58.2% of unnecessary polypectomies without missing any advanced neoplastic lesions.

Conclusion

NBI and DF modes provide accurate neoplastic predictions for rectosigmoid polyps. For diminutive polyps, DF magnification improves the confidence level of the optical diagnosis, allowing the safe implementation of the "diagnose-and-leave" strategy.

Colorectal polypectomy and endoscopic mucosal resection: European Society of Gastrointestinal Endoscopy (ESGE) Guideline - Update 2024

1:  ESGE recommends cold snare polypectomy (CSP), to include a clear margin of normal tissue (1-2 mm) surrounding the polyp, for the removal of diminutive polyps (≤ 5 mm).Strong recommendation, high quality of evidence. 2:  ESGE recommends against the use of cold biopsy forceps excision because of its high rate of incomplete resection.Strong recommendation, moderate quality of evidence. 3:  ESGE recommends CSP, to include a clear margin of normal tissue (1-2 mm) surrounding the polyp, for the removal of small polyps (6-9 mm).Strong recommendation, high quality of evidence. 4:  ESGE recommends hot snare polypectomy for the removal of nonpedunculated adenomatous polyps of 10-19 mm in size.Strong recommendation, high quality of evidence. 5:  ESGE recommends conventional (diathermy-based) endoscopic mucosal resection (EMR) for large (≥ 20 mm) nonpedunculated adenomatous polyps (LNPCPs).Strong recommendation, high quality of evidence. 6:  ESGE suggests that underwater EMR can be considered an alternative to conventional hot EMR for the treatment of adenomatous LNPCPs.Weak recommendation, moderate quality of evidence. 7:  Endoscopic submucosal dissection (ESD) may also be suggested as an alternative for removal of LNPCPs of ≥ 20 mm in selected cases and in high-volume centers.Weak recommendation, low quality evidence. 8:  ESGE recommends that, after piecemeal EMR of LNPCPs by hot snare, the resection margins should be treated by thermal ablation using snare-tip soft coagulation to prevent adenoma recurrence.Strong recommendation, high quality of evidence. 9:  ESGE recommends (piecemeal) cold snare polypectomy or cold EMR for SSLs of all sizes without suspected dysplasia.Strong recommendation, moderate quality of evidence. 10:  ESGE recommends prophylactic endoscopic clip closure of the mucosal defect after EMR of LNPCPs in the right colon to reduce to reduce the risk of delayed bleeding.Strong recommendation, high quality of evidence. 11:  ESGE recommends that en bloc resection techniques, such as en bloc EMR, ESD, endoscopic intermuscular dissection, endoscopic full-thickness resection, or surgery should be the techniques of choice in cases with suspected superficial invasive carcinoma, which otherwise cannot be removed en bloc by standard polypectomy or EMR.Strong recommendation, moderate quality of evidence.

A Semi-Supervised Learning Framework for Classifying Colorectal Neoplasia Based on the NICE Classification

Labelling medical images is an arduous and costly task that necessitates clinical expertise and large numbers of qualified images. Insufficient samples can lead to underfitting during training and poor performance of supervised learning models. In this study, we aim to develop a SimCLR-based semi-supervised learning framework to classify colorectal neoplasia based on the NICE classification. First, the proposed framework was trained under self-supervised learning using a large unlabelled dataset; subsequently, it was fine-tuned on a limited labelled dataset based on the NICE classification. The model was evaluated on an independent dataset and compared with models based on supervised transfer learning and endoscopists using accuracy, Matthew's correlation coefficient (MCC), and Cohen's kappa. Finally, Grad-CAM and t-SNE were applied to visualize the models' interpretations. A ResNet-backboned SimCLR model (accuracy of 0.908, MCC of 0.862, and Cohen's kappa of 0.896) outperformed supervised transfer learning-based models (means: 0.803, 0.698, and 0.742) and junior endoscopists (0.816, 0.724, and 0.863), while performing only slightly worse than senior endoscopists (0.916, 0.875, and 0.944). Moreover, t-SNE showed a better clustering of ternary samples through self-supervised learning in SimCLR than through supervised transfer learning. Compared with traditional supervised learning, semi-supervised learning enables deep learning models to achieve improved performance with limited labelled endoscopic images.

Colorectal cancer screening: A review of current knowledge and progress in research

Colorectal cancer (CRC) is one of the most prevalent malignancies worldwide, being the third most commonly diagnosed malignancy and the second leading cause of cancer-related deaths globally. Despite the progress in screening, early diagnosis, and treatment, approximately 20%-25% of CRC patients still present with metastatic disease at the time of their initial diagnosis. Furthermore, the burden of disease is still expected to increase, especially in individuals younger than 50 years old, among whom early-onset CRC incidence has been increasing. Screening and early detection are pivotal to improve CRC-related outcomes. It is well established that CRC screening not only reduces incidence, but also decreases deaths from CRC. Diverse screening strategies have proven effective in decreasing both CRC incidence and mortality, though variations in efficacy have been reported across the literature. However, uncertainties persist regarding the optimal screening method, age intervals and periodicity. Moreover, adherence to CRC screening remains globally low. In recent years, emerging technologies, notably artificial intelligence, and non-invasive biomarkers, have been developed to overcome these barriers. However, controversy exists over the actual impact of some of the new discoveries on CRC-related outcomes and how to effectively integrate them into daily practice. In this review, we aim to cover the current evidence surrounding CRC screening. We will further critically assess novel approaches under investigation, in an effort to differentiate promising innovations from mere novelties.

Artificial intelligence for characterization of diminutive colorectal polyps: A feasibility study comparing two computer-aided diagnosis systems

BACKGROUND

Artificial intelligence (AI) has potential in the optical diagnosis of colorectal polyps.

AIM

To evaluate the feasibility of the real-time use of the computer-aided diagnosis system (CADx) AI for ColoRectal Polyps (AI4CRP) for the optical diagnosis of diminutive colorectal polyps and to compare the performance with CAD EYE^TM (Fujifilm, Tokyo, Japan). CADx influence on the optical diagnosis of an expert endoscopist was also investigated.

METHODS

AI4CRP was developed in-house and CAD EYE was proprietary software provided by Fujifilm. Both CADx-systems exploit convolutional neural networks. Colorectal polyps were characterized as benign or premalignant and histopathology was used as gold standard. AI4CRP provided an objective assessment of its characterization by presenting a calibrated confidence characterization value (range 0.0-1.0). A predefined cut-off value of 0.6 was set with values < 0.6 indicating benign and values ≥ 0.6 indicating premalignant colorectal polyps. Low confidence characterizations were defined as values 40% around the cut-off value of 0.6 (< 0.36 and > 0.76). Self-critical AI4CRP’s diagnostic performances excluded low confidence characterizations.

RESULTS

AI4CRP use was feasible and performed on 30 patients with 51 colorectal polyps. Self-critical AI4CRP, excluding 14 low confidence characterizations [27.5% (14/51)], had a diagnostic accuracy of 89.2%, sensitivity of 89.7%, and specificity of 87.5%, which was higher compared to AI4CRP. CAD EYE had a 83.7% diagnostic accuracy, 74.2% sensitivity, and 100.0% specificity. Diagnostic performances of the endoscopist alone (before AI) increased non-significantly after reviewing the CADx characterizations of both AI4CRP and CAD EYE (AI-assisted endoscopist). Diagnostic performances of the AI-assisted endoscopist were higher compared to both CADx-systems, except for specificity for which CAD EYE performed best.

CONCLUSION

Real-time use of AI4CRP was feasible. Objective confidence values provided by a CADx is novel and self-critical AI4CRP showed higher diagnostic performances compared to AI4CRP.

Artificial Intelligence-assisted colonoscopy and colorectal cancer screening: Where are we going?

Colorectal cancer is a significant global health concern, necessitating effective screening strategies to reduce its incidence and mortality rates. Colonoscopy plays a crucial role in the detection and removal of colorectal neoplastic precursors. However, there are limitations and variations in the performance of endoscopists, leading to missed lesions and suboptimal outcomes. The emergence of artificial intelligence (AI) in endoscopy offers promising opportunities to improve the quality and efficacy of screening colonoscopies. In particular, AI applications, including computer-aided detection (CADe) and computer-aided characterization (CADx), have demonstrated the potential to enhance adenoma detection and optical diagnosis accuracy. Additionally, AI-assisted quality control systems aim to standardize the endoscopic examination process. This narrative review provides an overview of AI principles and discusses the current knowledge on AI-assisted endoscopy in the context of screening colonoscopies. It highlights the significant role of AI in improving lesion detection, characterization, and quality assurance during colonoscopy. However, further well-designed studies are needed to validate the clinical impact and cost-effectiveness of AI-assisted colonoscopy before its widespread implementation.

Impact of computer-aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study

OBJECTIVES

Computer-aided characterization (CADx) may be used to implement optical biopsy strategies into colonoscopy practice; however, its impact on endoscopic diagnosis remains unknown. We aimed to evaluate the additional diagnostic value of CADx when used by endoscopists for assessing colorectal polyps.

METHODS

This was a single-center, multicase, multireader, image-reading study using randomly extracted images of pathologically confirmed polyps resected between July 2021 and January 2022. Approved CADx that could predict two-tier classification (neoplastic or nonneoplastic) by analyzing narrow-band images of the polyps was used to obtain a CADx diagnosis. Participating endoscopists determined if the polyps were neoplastic or not and noted their confidence level using a computer-based, image-reading test. The test was conducted twice with a 4-week interval: the first test was conducted without CADx prediction and the second test with CADx prediction. Diagnostic performances for neoplasms were calculated using the pathological diagnosis as reference and performances with and without CADx prediction were compared.

RESULTS

Five hundred polyps were randomly extracted from 385 patients and diagnosed by 14 endoscopists (including seven experts). The sensitivity for neoplasia was significantly improved by referring to CADx (89.4% vs. 95.6%). CADx also had incremental effects on the negative predictive value (69.3% vs. 84.3%), overall accuracy (87.2% vs. 91.8%), and high-confidence diagnosis rate (77.4% vs. 85.8%). However, there was no significant difference in specificity (80.1% vs. 78.9%).

CONCLUSIONS

Computer-aided characterization has added diagnostic value for differentiating colorectal neoplasms and may improve the high-confidence diagnosis rate.

From Staining Techniques to Artificial Intelligence: A Review of Colorectal Polyps Characterization

This review article provides a comprehensive overview of the evolving techniques in image-enhanced endoscopy (IEE) for the characterization of colorectal polyps, and the potential of artificial intelligence (AI) in revolutionizing the diagnostic accuracy of endoscopy. We discuss the historical use of dye-spray and virtual chromoendoscopy for the characterization of colorectal polyps, which are now being replaced with more advanced technologies. Specifically, we focus on the application of AI to create a "virtual biopsy" for the detection and characterization of colorectal polyps, with potential for replacing histopathological diagnosis. The incorporation of AI has the potential to provide an evolutionary learning system that aids in the diagnosis and management of patients with the best possible outcomes. A detailed analysis of the literature supporting AI-assisted diagnostic techniques for the detection and characterization of colorectal polyps, with a particular emphasis on AI's characterization mechanism, is provided. The benefits of AI over traditional IEE techniques, including the reduction in human error in diagnosis, and its potential to provide an accurate diagnosis with similar accuracy to the gold standard are presented. However, the need for large-scale testing of AI in clinical practice and the importance of integrating patient data into the diagnostic process are acknowledged. In conclusion, the constant evolution of IEE technology and the potential for AI to revolutionize the field of endoscopy in the future are presented.

Computer-aided polyp characterization in colonoscopy: sufficient performance or not?

Computer-assisted polyp characterization (computer-aided diagnosis, CADx) facilitates optical diagnosis during colonoscopy. Several studies have demonstrated high sensitivity and specificity of CADx tools in identifying neoplastic changes in colorectal polyps. To implement CADx tools in colonoscopy, there is a need to confirm whether these tools satisfy the threshold levels that are required to introduce optical diagnosis strategies such as "diagnose-and-leave," "resect-and-discard" or "DISCARD-lite." In this article, we review the available data from prospective trials regarding the effect of multiple CADx tools and discuss whether they meet these thresholds.

Endoscopic characterization of neoplastic and non-neoplastic lesions in inflammatory bowel disease: systematic review in the era of advanced endoscopic imaging

Background

Current guidelines strongly recommend the use of validated classifications to support optical diagnosis of lesions with advanced endoscopic imaging in the lower gastrointestinal tract. However, the optimal strategy in inflammatory bowel disease (IBD) is still a matter of debate.

Objectives

To analyze the accuracy of endoscopic classifications or single predictors for in vivo lesion characterization during endoscopic surveillance of IBD with advanced endoscopic imaging.

Design

Systematic review.

Data sources and methods

Medline and PubMed were used to extract all studies which focused on lesion characterization of neoplastic and non-neoplastic lesions in IBD. The diagnostic accuracy of endoscopic classifications and single endoscopic predictors for lesion characterization were analyzed according to type of patients, lesions, and technology used. When available, the rates of true and false positives or negatives for neoplasia were pooled and the sensitivity (SE), specificity (SP), positive predictive value, and negative predictive value (NPV) were calculated.

Results

We included 35 studies (2789 patients; 5925 lesions - 1149 neoplastic). Advanced endoscopic imaging included dye-based chromoendoscopy, virtual chromoendoscopy (VCE), magnification and high-definition endoscopy, confocal laser endomicroscopy (CLE), endocytoscopy, and autofluorescence imaging. The Kudo classification of pit patterns was most frequently used, with pooled SE 83%, SP 83%, and NPV 95%. The endoscopic criteria with the highest accuracy, with minimum SE ⩾ 90%, SP ⩾ 80%, and NPV ⩾ 90% were: the Kudo-IBD classification used with VCE (Fuji Intelligent Color Enhancement and i-SCAN); combined irregular surface and vascular patterns used with narrow band imaging; the Mainz classification used with CLE. Multiple clinical and technical factors were found to influence the accuracy of optical diagnosis in IBD.

Conclusion

No single endoscopic factor has yet shown sufficient accuracy for lesion characterization in IBD surveillance. Conventional classifications developed in the non-IBD setting have lower accuracy in IBD. The use of new classifications adapted for IBD (Kudo-IBD), and new technologies based on in vivo microscopic analysis show promise.

Application of artificial intelligence in colorectal cancer screening by colonoscopy: Future prospects (Review)

Colorectal cancer (CRC) has become a severe global health concern, with the third‑high incidence and second‑high mortality rate of all cancers. The burden of CRC is expected to surge to 60% by 2030. Fortunately, effective early evidence‑based screening could significantly reduce the incidence and mortality of CRC. Colonoscopy is the core screening method for CRC with high popularity and accuracy. Yet, the accuracy of colonoscopy in CRC screening is related to the experience and state of operating physicians. It is challenging to maintain the high CRC diagnostic rate of colonoscopy. Artificial intelligence (AI)‑assisted colonoscopy will compensate for the above shortcomings and improve the accuracy, efficiency, and quality of colonoscopy screening. The unique advantages of AI, such as the continuous advancement of high‑performance computing capabilities and innovative deep‑learning architectures, which hugely impact the control of colorectal cancer morbidity and mortality expectancy, highlight its role in colonoscopy screening.

Impact of 3-second rule for high confidence assignment on the performance of endoscopists for the real-time optical diagnosis of colorectal polyps

BACKGROUND

Confusion between high and low confidence decisions in optical diagnosis hinders the implementation of real-time optical diagnosis in clinical practice. We evaluated the effect of a 3-second rule (decision time limited to 3 seconds for a high confidence assignment) in expert and nonexpert endoscopists.

METHODS

This single-center prospective study included eight board-certified gastroenterologists. A 2-month baseline phase used standard real-time optical diagnosis for colorectal polyps < 10 mm and was followed by a 6-month intervention phase using optical diagnosis with the 3-second rule. Performance, including high confidence accuracy, and Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) and Simple Optical Diagnosis Accuracy (SODA) thresholds, was measured.

RESULTS

Real-time optical diagnosis was performed on 1793 patients with 3694 polyps. There was significant improvement in high confidence accuracy between baseline and intervention phases in the nonexpert group (79.2 % vs. 86.3 %; P = 0.01) but not in the expert group (85.3 % vs. 87.5 %; P = 0.53). Using the 3-second rule improved the overall performance of PIVI and SODA in both groups.

CONCLUSIONS

The 3-second rule was effective in improving real-time optical diagnosis performance, especially in nonexperts.

Accuracy of polyp characterization by artificial intelligence and endoscopists: a prospective, non-randomized study in a tertiary endoscopy center

Background and study aims Artificial intelligence (AI) in gastrointestinal endoscopy is developing very fast. Computer-aided detection of polyps and computer-aided diagnosis (CADx) for polyp characterization are available now. This study was performed to evaluate the diagnostic performance of a new commercially available CADx system in clinical practice. Patients and methods This prospective, non-randomized study was performed at a tertiary academic endoscopy center from March to August 2022. We included patients receiving a colonoscopy. Polypectomy had to be performed in all polyps. Every patient was examined concurrently by an endoscopist and AI using two opposing screens. The AI system, overseen by a second observer, was not visible to the endoscopist. The primary outcome was accuracy of the AI classifying the polyps into "neoplastic" and "non-neoplastic." The secondary outcome was accuracy of the classification by the endoscopists. Sessile serrated lesions were classified as neoplastic. Results We included 156 patients (mean age 65; 57 women) with 262 polyps ≤10 mm. Eighty-four were hyperplastic polyps (32.1%), 158 adenomas (60.3%), seven sessile serrated lesions (2.7%) and 13 other entities (normal/inflammatory colonmucosa, lymphoidic polyp) (4.9%) on histological diagnosis. Sensitivity, specificity and accuracy of AI were 89.70% (95% confidence interval [CI]: 84.02%-93.88%), 75.26% (95% CI: 65.46%-83.46%) and 84.35% (95% CI:79.38%-88.53%), respectively. Sensitivity, specificity and accuracy for less experienced endoscopists (2-5 years of endoscopy) were 95.56% (95% CI: 84.85%-99.46%), 61.54% (95% CI: 40.57%-79.77%) and 83.10% (95% CI: 72.34%-90.95%) and for experienced endoscopists 90.83% (95% CI: 84.19%-95.33%), 71.83% (95% CI: 59.90%-81.87%) and 83.77% (95% CI: 77.76%-88.70%), respectively. Conclusion Accuracy for polyp characterization by a new commercially available AI system is high, but does not fulfill the criteria for a "resect-and-discard" strategy.

Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists

BACKGROUND : We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. METHODS : We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. RESULTS : During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). CONCLUSIONS : We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.

Combination of Mucosa-Exposure Device and Computer-Aided Detection for Adenoma Detection During Colonoscopy: A Randomized Trial

BACKGROUND & AIMS

Both computer-aided detection (CADe)-assisted and Endocuff-assisted colonoscopy have been found to increase adenoma detection. We investigated the performance of the combination of the 2 tools compared with CADe-assisted colonoscopy alone to detect colorectal neoplasias during colonoscopy in a multicenter randomized trial.

METHODS

Men and women undergoing colonoscopy for colorectal cancer screening, polyp surveillance, or clincial indications at 6 centers in Italy and Switzerland were enrolled. Patients were assigned (1:1) to colonoscopy with the combinations of CADe (GI-Genius; Medtronic) and a mucosal exposure device (Endocuff Vision [ECV]; Olympus) or to CADe-assisted colonoscopy alone (control group). All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was adenoma detection rate (percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, advanced adenomas and serrated lesions detection rate, the rate of unnecessary polypectomies (polyp resection without histologically proven adenomas), and withdrawal time.

RESULTS

From July 1, 2021 to May 31, 2022, there were 1316 subjects randomized and eligible for analysis; 660 to the ECV group, 656 to the control group). The adenoma detection rate was significantly higher in the ECV group (49.6%) than in the control group (44.0%) (relative risk, 1.12; 95% CI, 1.00-1.26; P = .04). Adenomas detected per colonoscopy were significantly higher in the ECV group (mean ± SD, 0.94 ± 0.54) than in the control group (0.74 ± 0.21) (incidence rate ratio, 1.26; 95% CI, 1.04-1.54; P = .02). The 2 groups did not differ in term of detection of advanced adenomas and serrated lesions. There was no significant difference between groups in mean ± SD withdrawal time (9.01 ± 2.48 seconds for the ECV group vs 8.96 ± 2.24 seconds for controls; P = .69) or proportion of subjects undergoing unnecessary polypectomies (relative risk, 0.89; 95% CI, 0.69-1.14; P = .38).

CONCLUSIONS

The combination of CADe and ECV during colonoscopy increases adenoma detection rate and adenomas detected per colonoscopy without increasing withdrawal time compared with CADe alone.

CLINICALTRIALS

gov, Number: NCT04676308.

Automatic textual description of colorectal polyp features: explainable artificial intelligence

Computer-aided diagnosis systems (CADx) can improve colorectal polyp (CRP) optical diagnosis. For integration into clinical practice, better understanding of artificial intelligence (AI) by endoscopists is needed. We aimed to develop an explainable AI CADx capable of automatically generating textual descriptions of CRPs. For training and testing of this CADx, textual descriptions of CRP size and features according to the Blue Light Imaging (BLI) Adenoma Serrated International Classification (BASIC) were used, describing CRP surface, pit pattern, and vessels. CADx was tested using BLI images of 55 CRPs. Reference descriptions with agreement by at least five out of six expert endoscopists were used as gold standard. CADx performance was analyzed by calculating agreement between the CADx generated descriptions and reference descriptions. CADx development for automatic textual description of CRP features succeeded. Gwet's AC1 values comparing the reference and generated descriptions per CRP feature were: size 0.496, surface-mucus 0.930, surface-regularity 0.926, surface-depression 0.940, pits-features 0.921, pits-type 0.957, pits-distribution 0.167, and vessels 0.778. CADx performance differed per CRP feature and was particularly high for surface descriptors while size and pits-distribution description need improvement. Explainable AI can help comprehend reasoning behind CADx diagnoses and therefore facilitate integration into clinical practice and increase trust in AI.

Artificial Intelligence-Aided Endoscopy and Colorectal Cancer Screening

Colorectal cancer (CRC) is the third most common cancer worldwide, with the highest incidence reported in high-income countries. However, because of the slow progression of neoplastic precursors, along with the opportunity for their endoscopic detection and resection, a well-designed endoscopic screening program is expected to strongly decrease colorectal cancer incidence and mortality. In this regard, quality of colonoscopy has been clearly related with the risk of post-colonoscopy colorectal cancer. Recently, the development of artificial intelligence (AI) applications in the medical field has been growing in interest. Through machine learning processes, and, more recently, deep learning, if a very high numbers of learning samples are available, AI systems may automatically extract specific features from endoscopic images/videos without human intervention, helping the endoscopists in different aspects of their daily practice. The aim of this review is to summarize the current knowledge on AI-aided endoscopy, and to outline its potential role in colorectal cancer prevention.

Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement

The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost-effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer-aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health-care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe-related cancer prevention; Statement 1.4: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer-aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health-care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high-quality cost-effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health-care systems.

Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study

BACKGROUND

Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤ 5 mm) rectosigmoid polyps (DRSPs).

METHODS

Consecutive colonoscopy outpatients with ≥ 1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥ 90 % negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations [PIVI-1] threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥ 90 %; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines.

RESULTS

Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %-93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %-98.9 %) and 92.6 % (95 %CI 90.0 %-95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %-87.3 %) than for experts (91.9 %, 95 %CI 88.5 %-94.5 %); however, nonexperts quickly approached the performance levels of experts over time.

CONCLUSION

AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopists' high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.

NBI International Colorectal Endoscopic-derived high-confidence optical diagnosis of small polyps compared with histology: understanding errors to improve diagnostic accuracy

BACKGROUND AND AIMS

Developments in image-enhancing endoscopy and polyp classification systems have led to a number of gastroenterology societies endorsing an optical diagnosis (OD) approach for small polyps at colonoscopy. In this study we performed a root-cause analysis of ODs to determine the most likely causes of OD error.

METHODS

As part of a prospective feasibility study, DISCARD3 (Detect InSpect ChAracterise Resect and Discard 3), evaluating implementation and quality assurance of a "resect and discard" strategy for consecutive small polyps <10 mm, a root-cause analysis of 184 cases of high-confidence OD error was performed. In all cases, histopathology underwent a second blinded review and, where discrepancy persisted, further review with deeper levels.

RESULTS

After a root-cause analysis, 133 of 184 true OD errors were identified and classified into 4 types: A (OD, adenoma; histology, serrated), 45/133 (33.8%); B (OD, serrated; histology, adenoma), 55/133 (41.4%); C (OD, adenoma; histology, normal), 19/133 (14.3%); and D (OD, serrated; histology, normal), 14/133 (10.5%). The remaining 51 of 184 errors were because of a pathology error requiring deeper levels (43/184), pathology observer or laboratory error (7/184), or other error (1/184).

CONCLUSIONS

OD errors can be related to endoscopist-related factors such as poor photodocumentation, failures of current classification systems, and incomplete histology. We identified a subset of serrated polyps frequently misdiagnosed as adenomas ("pseudoadenomas") using the NBI International Colorectal Endoscopic (NICE) classification. An enhanced algorithm for OD is proposed based on the NICE classification including morphologic and adjunct polyp features.

Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. MAIN RECOMMENDATIONS:: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in ≥90% of the procedures. (3) For acceptance of AI in the detection of Barrett's high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett's neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma detection rate should be comparable to that of experienced endoscopists. (8) For acceptance of AI optical diagnosis (computer-aided diagnosis [CADx]) of diminutive polyps (≤5 mm), AI-assisted characterization should match performance standards for implementing resect-and-discard and diagnose-and-leave strategies. (9) For acceptance of AI in the management of polyps ≥ 6 mm, AI-assisted characterization should be comparable to that of experienced endoscopists in selecting lesions amenable to endoscopic resection.

"Endoscopic" adenoma detection rate as a quality indicator of colonoscopy: First report from the J-SCOUT study

OBJECTIVES

To examine whether reasonable detection rate of endoscopically diagnosed lesions as adenoma ("endoscopic" adenoma detection rate [ADR]) could be calculated with a database generated from colonoscopy reports and whether it could be used as a surrogate colonoscopy quality indicator of "pathological" ADR.

METHODS

A lesion-by-lesion database of colonoscopies performed between 2010 and 2020 at eight Japanese endoscopy centers and corresponding pathology database were integrated. Differences in numbers of detected polyps, "endoscopic" and "pathological" adenomas, and what these differences could be attributed to were examined. Polyp detection rate (PDR), "endoscopic" and "pathological" ADRs, and correlation coefficients between "pathological" ADR and PDR or "endoscopic" ADR by each endoscopist were calculated.

RESULTS

Overall, 129,065 colonoscopy reports were analyzed. Among a total of 146,854 polyps, more "endoscopic" adenomas (n = 117,359) were observed than "pathological" adenomas (n = 70,076), primarily because adenomas were not resected on site, rather than because of a misdiagnosis. In all patients analyzed, PDR, "endoscopic" and "pathological" ADRs were 56.4% (95% confidence interval [CI] 56.2-56.7), 48.0% (95% CI 47.7-48.3), and 32.7% (95% CI 32.5-33.0), respectively. "Endoscopic" and "pathological" ADRs from each endoscopist showed a high correlation in hospitals where adenomas were usually resected at the time of examination.

CONCLUSIONS

By appropriately describing endoscopically diagnosed lesions as "adenomas" in endoscopy reports, "endoscopic" ADR might be used as a surrogate colonoscopy quality indicator of "pathological" ADR (UMIN000040690).

Performance of a novel computer-aided diagnosis system in the characterization of colorectal polyps, and its role in meeting Preservation and Incorporation of Valuable Endoscopic Innovations standards set by the American Society of Gastrointestinal Endoscopy

Background and aims

There has been an increasing role of artificial intelligence (AI) in the characterization of colorectal polyps. Recently, a novel AI algorithm for the characterization of polyps was developed by NEC Corporation (Japan). The aim of our study is to perform an external validation of this algorithm.

Methods

The study was a video-based evaluation of the computer-aided diagnosis (CADx) system. Patients undergoing colonoscopy were recruited to record videos of colonic polyps. The frozen polyp images extracted from these videos were used for real-time histological prediction by the endoscopists and by the CADx system, and the results were compared.

Results

A total of 115 polyp images were extracted from 66 patients. Sensitivity, negative predictive value and accuracy for diminutive polyps on white light imaging (WLI) and image-enhanced endoscopy (IEE) when assessed by CADx was 90.9% [95% confidence interval (CI) 77.3-100] and 95.8% [95% CI 87.5-100], 80% [95% CI 44.4-97.5] and 90.9% [95% CI 58.7-99.8], 84.8% [95% CI 72.7-97] and 84.6% [95%CI 71.8-94.9], respectively, compared to 48.1% [95%CI 37.7-59.1] and 72% [95% CI 62.5-81], 37.5% [95% CI 28.8-46.8] and 55% [95% CI 44.7-65.0], 53.7% [95% CI 44.2-63.2] and 66.7% [95% CI 59.7-73.3] when assessed by endoscopists. Concordance between histology and CADx-based post-polypectomy surveillance intervals was 93.02% on WLI and 96% on IEE.

Conclusion

AI-based optical diagnosis is promising and has the potential to be better than the performance of general endoscopists. We believe that AI can help make real-time optical diagnoses of polyps meeting the Preservation and Incorporation of Valuable endoscopic Innovations standards set by the American Society of Gastrointestinal Endoscopy.

Artificial intelligence in gastrointestinal endoscopy - Evolution to a new era

Artificial intelligence (AI) systems based on machine learning have evolved in the last few years with an increasing applicability in gastrointestinal endoscopy. Thanks to AI, an image (input) can be transformed into a clinical decision (output). Although AI systems have been initially studied to improve detection (CADe) and characterization of colorectal lesions (CADx), other indications are being currently investigated as detection of blind spots, scope guidance, or delineation/measurement of lesions. The objective of these review is to summarize the current evidence on applicability of AI systems in gastrointestinal endoscopy, highlight strengths and limitations of the technology and review regulatory and ethical aspects for its general implementation in gastrointestinal endoscopy.

In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy

Background and study aims  Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep learning-based optical diagnosis system, ATENEA, in a real clinical setting using only high-definition white light endoscopy (WLE) and to compare its performance with endoscopists. Methods  ATENEA was prospectively tested in real life on consecutive polyps detected in colorectal cancer screening colonoscopies at Hospital Clínic. No images were discarded, and only WLE was used. The in vivo ATENEA's prediction (adenoma vs non-adenoma) was compared with the prediction of four staff endoscopists without specific training in optical diagnosis for the study purposes. Endoscopists were blind to the ATENEA output. Histology was the gold standard. Results  Ninety polyps (median size: 5 mm, range: 2-25) from 31 patients were included of which 69 (76.7 %) were adenomas. ATENEA correctly predicted the histology in 63 of 69 (91.3 %, 95 % CI: 82 %-97 %) adenomas and 12 of 21 (57.1 %, 95 % CI: 34 %-78 %) non-adenomas while endoscopists made correct predictions in 52 of 69 (75.4 %, 95 % CI: 60 %-85 %) and 20 of 21 (95.2 %, 95 % CI: 76 %-100 %), respectively. The global accuracy was 83.3 % (95 % CI: 74%-90 %) and 80 % (95 % CI: 70 %-88 %) for ATENEA and endoscopists, respectively. Conclusion  ATENEA can accurately be used for in vivo characterization of colorectal polyps, enabling the endoscopist to make direct decisions. ATENEA showed a global accuracy similar to that of endoscopists despite an unsatisfactory performance for non-adenomatous lesions.

Artificial Intelligence in Digestive Endoscopy—Where Are We and Where Are We Going?

Artificial intelligence, a computer-based concept that tries to mimic human thinking, is slowly becoming part of the endoscopy lab. It has developed considerably since the first attempt at developing an automated medical diagnostic tool, today being adopted in almost all medical fields, digestive endoscopy included. The detection rate of preneoplastic lesions (i.e., polyps) during colonoscopy may be increased with artificial intelligence assistance. It has also proven useful in detecting signs of ulcerative colitis activity. In upper digestive endoscopy, deep learning models may prove to be useful in the diagnosis and management of upper digestive tract diseases, such as gastroesophageal reflux disease, Barrett’s esophagus, and gastric cancer. As is the case with all new medical devices, there are challenges in the implementation in daily medical practice. The regulatory, economic, organizational culture, and language barriers between humans and machines are a few of them. Even so, many devices have been approved for use by their respective regulators. Future studies are currently striving to develop deep learning models that can replicate a growing amount of human brain activity. In conclusion, artificial intelligence may become an indispensable tool in digestive endoscopy.