Impact of the clinical use of artificial intelligence-assisted neoplasia detection for colonoscopy: a large-scale prospective, propensity score-matched study (with video)

A comparative study benchmarking colon polyp with computer-aided detection (CADe) software

Background and aims

Computer-aided detection software (CADe) has shown promising results in real-time polyp detection, but a limited head-to-head comparison of the available CADe systems has been performed. Moreover, such systems have not been compared to endoscopists using standardized videos. This study aims to compare the performance of three CADe systems in detecting polyps, employing a novel standardized methodology.

Methods

Videos from 300 colonoscopies conducted at Oslo University Hospital were analyzed. Short video clips (20-45 s) presenting normal mucosa or polyps were randomly selected. These videos were then streamed through each CADe system from Medtronic, Olympus, and Augere Medical. Each system featured diverse configurations, resulting in a total of six software settings. Sensitivity and false positivity (FP) were assessed by comparing the CADe systems to both the mean of the systems and pairwise between them. Furthermore, the systems' performance was compared to the performance of five endoscopists.

Results

CADe systems' sensitivity ranged between 84.9% and 98.7%, with statistically significant differences observed between the systems, both in comparison to the mean and to each other. FP rates ranged between 1.2% and 5.6%, also differing statistically significantly between the systems. The CADe systems achieving the highest sensitivity also exhibited the highest FP. Statistically significant differences in the alert delay were observed between different CADe systems and endoscopists.

Conclusions

This study highlights significant differences between commercially available CADe software regarding sensitivity and FP, but a superior performance compared to endoscopists. The software with the highest sensitivity also exhibited the highest FP, highlighting the need for further refinement.

New Concept of Colonoscopy Assisted by a Microwave-Based Accessory Device: First Clinical Experience

Background/Objectives: Colonoscopies have some limitations that result in a miss rate detection of polyps. Microwave imaging has been demonstrated to detect colorectal polyps based on their dielectric properties in synthetic phantoms, ex vivo tissues and in vivo animal models. This study aims to evaluate, for the first time, the feasibility, safety and performance of microwave-based colonoscopy for diagnosis of polyps in real-time explorations in humans. Methods: This was a single-center, prospective, observational study. Patients referred for diagnostic colonoscopy were explored with a device with microwave antennas which was attached to the tip of a standard colonoscope. The primary outcomes were rate of cecal intubation, adverse events, mural injuries and performance metrics for the detection of polyps. Secondary outcomes were the following: patients' subjective feedback, procedural time and perception of difficulty according to the endoscopist. Results: Fifteen patients were enrolled. Cecal intubation rate was 100%, with a mean time of 12.7 ± 4.9 min (range 4-22). Use of the device did not affect the endoscopic image, and polypectomy was successfully performed in all cases. In on scale from zero (not difficult) to four (very difficult), the maneuverability during the insertion was considered ≤2 in the 86.7% (13/15) of colonoscopies. Only 16 incidents were reported in 14 patients: 11 (67%) superficial hematomas, 2 minor rectal bleedings, 1 anal fissure, 1 rhinorrhea and 1 headache. Most of the patients (94%) reported no discomfort or minimal discomfort before discharge (Gloucester score 1 and 2, respectively). In the six patients with 23 polyps used for the performance analysis, the sensitivity and specificity were 86.9% and 72.0%, respectively. Conclusions: microwave-based colonoscopy is safe and feasible and has the potential to detect polyps in real colonoscopies.

Efficiency of Real-time Computer-aided Polyp Detection during Surveillance Colonoscopy: A Pilot Study

Objectives

Studies have suggested that computer-aided polyp detection using artificial intelligence improves adenoma identification during colonoscopy. However, its real-world effectiveness remains unclear. Therefore, this study evaluated the usefulness of computer-aided detection during regular surveillance colonoscopy.

Methods

Consecutive patients who underwent surveillance colonoscopy with computer-aided detection between January and March 2023 and had undergone colonoscopy at least twice during the past 3 years were recruited. The clinicopathological findings of lesions identified using computer-aided detection were evaluated. The detection ability was sub-analyzed based on the expertise of the endoscopist and the presence of diminutive adenomas (size ≤5 mm).

Results

A total of 78 patients were included. Computer-aided detection identified 46 adenomas in 28 patients; however, no carcinomas were identified. The mean withdrawal time was 824 ± 353 s, and the mean tumor diameter was 3.3 mm (range, 2-8 mm). The most common gross type was 0-Is (70%), followed by 0-Isp (17%) and 0-IIa (13%). The most common tumor locations were the ascending colon and sigmoid colon (28%), followed by the transverse colon (26%), cecum (7%), descending colon (7%), and rectum (4%). Overall, 34.1% and 38.2% of patients with untreated diminutive adenomas and those with no adenomas, respectively, had newly detected adenomas. Endoscopist expertise did not affect the results.

Conclusions

Computer-aided detection may help identify adenomas during surveillance colonoscopy for patients with untreated diminutive adenomas and those with a history of endoscopic resection.

Combination of white-light imaging-based and narrow-band imaging-based artificial intelligence models during colonoscopy in patients with ulcerative colitis

BACKGROUND AND AIMS

The long-term treat-to-target (T2T) approach in ulcerative colitis (UC) aims for endoscopic remission, but variability among endoscopists and a lack of precision in relapse prediction both limit its clinical usefulness. A recently reported white-light imaging (WLI) artificial intelligence (AI) model helps standardize diagnosis, although challenges remain. Therefore, we attempted to combine a narrow-band imaging (NBI) AI model with the WLI AI model to determine whether these challenges can be overcome.

METHODS

This post hoc analysis of a prospective study evaluated the efficacy of combining AI-assisted WLI and NBI models in predicting clinical relapse in patients with UC over a 12-month follow-up period. A total of 102 patients with UC in clinical remission were included, and the combined AI models were used during colonoscopy to assess relapse risk.

RESULTS

The study found that within the same AI-based Mayo endoscopic subscore category, patients with vascular activity were more likely to experience clinical relapse than those with vascular healing. Compared with the WLI model alone, the specificity of the combined method significantly increased from 42.2% (95% confidence interval [CI]: 32.1%-52.9%) to 61.5% (95% CI: 50.7%-71.2%) (P = .013) with its sensitivity being maintained.

CONCLUSIONS

The sequential use of WLI and NBI AI models can provide better stratification of relapse risk compared with using either model alone, offering a more accurate and personalized approach to treatment intensification. This dual-model AI approach aligns with the T2T approach in UC management.

Effectiveness of a novel artificial intelligence-assisted colonoscopy system for adenoma detection: a prospective, propensity score-matched, non-randomized controlled study in Korea

BACKGROUND/AIMS

The real-world effectiveness of computer-aided detection (CADe) systems during colonoscopies remains uncertain. We assessed the effectiveness of the novel CADe system, ENdoscopy as AI-powered Device (ENAD), in enhancing the adenoma detection rate (ADR) and other quality indicators in real-world clinical practice.

METHODS

We enrolled patients who underwent elective colonoscopies between May 2022 and October 2022 at a tertiary healthcare center. Standard colonoscopy (SC) was compared to ENAD-assisted colonoscopy. Eight experienced endoscopists performed the procedures in randomly assigned CADe- and non-CADe-assisted rooms. The primary outcome was a comparison of ADR between the ENAD and SC groups.

RESULTS

A total of 1,758 sex- and age-matched patients were included and evenly distributed into two groups. The ENAD group had a significantly higher ADR (45.1% vs. 38.8%, p=0.010), higher sessile serrated lesion detection rate (SSLDR) (5.7% vs. 2.5%, p=0.001), higher mean number of adenomas per colonoscopy (APC) (0.78±1.17 vs. 0.61±0.99; incidence risk ratio, 1.27; 95% confidence interval, 1.13-1.42), and longer withdrawal time (9.0±3.4 vs. 8.3±3.1, p<0.001) than the SC group. However, the mean withdrawal times were not significantly different between the two groups in cases where no polyps were detected (6.9±1.7 vs. 6.7±1.7, p=0.058).

CONCLUSIONS

ENAD-assisted colonoscopy significantly improved the ADR, APC, and SSLDR in real-world clinical practice, particularly for smaller and nonpolypoid adenomas.

The application of the combination between artificial intelligence and endoscopy in gastrointestinal tumors

Gastrointestinal (GI) tumors have always been a major type of malignant tumor and a leading cause of tumor‐related deaths worldwide. The main principles of modern medicine for GI tumors are early prevention, early diagnosis, and early treatment, with early diagnosis being the most effective measure. Endoscopy, due to its ability to visualize lesions, has been one of the primary modalities for screening, diagnosing, and treating GI tumors. However, a qualified endoscopist often requires long training and extensive experience, which to some extent limits the wider use of endoscopy. With advances in data science, artificial intelligence (AI) has brought a new development direction for the endoscopy of GI tumors. AI can quickly process large quantities of data and images and improve diagnostic accuracy with some training, greatly reducing the workload of endoscopists and assisting them in early diagnosis. Therefore, this review focuses on the combined application of endoscopy and AI in GI tumors in recent years, describing the latest research progress on the main types of tumors and their performance in clinical trials, the application of multimodal AI in endoscopy, the development of endoscopy, and the potential applications of AI within it, with the aim of providing a reference for subsequent research.

Assessing the potential of artificial intelligence to enhance colonoscopy adenoma detection in clinical practice: a prospective observational trial

BACKGROUND/AIMS

This study aimed to evaluate the effectiveness of the GI Genius (Medtronic) module in clinical practice, focusing on the adenoma detection rate (ADR) during colonoscopy. Computer-aided polyp detection (CADe) systems using artificial intelligence have been shown to improve adenoma detection in controlled trials. However, the effectiveness of these systems in clinical practice has recently been questioned.

METHODS

This single-center prospective observational study was conducted at the University Hospital of Southern Denmark and included all individuals referred for colonoscopy between November 2020 and January 2021. The primary outcome was ADR, comparing patients examined with CADe to those examined without it. The selection of patients to be examined with the CADe module was completely random.

RESULTS

A total of 502 patients were analyzed (318 in the control group and 184 in the CADe group). The overall ADR was 32.1% with a slight increase in the CADe group (34.7% vs. 30.5%). Multivariable analysis showed a very modest and statistically insignificant increase in ADR (risk ratio, 1.12; 95% confidence interval, 0.88-1.43).

CONCLUSIONS

The use of CADe in clinical practice did not increase ADR with statistical significance when compared to colonoscopy without CADe. These findings suggest that the impact of CADe systems in everyday clinical practice are modest.

Artificial Intelligence in Colorectal Cancer: From Patient Screening over Tailoring Treatment Decisions to Identification of Novel Biomarkers

BACKGROUND

Artificial intelligence (AI) is increasingly entering and transforming not only medical research but also clinical practice. In the last 10 years, new AI methods have enabled computers to perform visual tasks, reaching high performance and thereby potentially supporting and even outperforming human experts. This is in particular relevant for colorectal cancer (CRC), which is the 3rd most common cancer type in general, as along the CRC patient journey many complex visual tasks need to be performed: from endoscopy over imaging to histopathology; the screening, diagnosis, and treatment of CRC involve visual image analysis tasks.

SUMMARY

In all these clinical areas, AI models have shown promising results by supporting physicians, improving accuracy, and providing new biological insights and biomarkers. By predicting prognostic and predictive biomarkers from routine images/slides, AI models could lead to an improved patient stratification for precision oncology approaches in the near future. Moreover, it is conceivable that AI models, in particular together with innovative techniques such as single-cell or spatial profiling, could help identify novel clinically as well as biologically meaningful biomarkers that could pave the way to new therapeutic approaches.

KEY MESSAGES

Here, we give a comprehensive overview of AI in colorectal cancer, describing and discussing these developments as well as the next steps which need to be taken to incorporate AI methods more broadly into the clinical care of CRC.

Lack of Effectiveness of Computer Aided Detection for Colorectal Neoplasia: A Systematic Review and Meta-Analysis of Nonrandomized Studies

BACKGROUND AND AIMS

Benefits of computer-aided detection (CADe) in detecting colorectal neoplasia were shown in many randomized trials in which endoscopists' behavior was strictly controlled. However, the effect of CADe on endoscopists' performance in less-controlled setting is unclear. This systematic review and meta-analyses were aimed at clarifying benefits and harms of using CADe in real-world colonoscopy.

METHODS

We searched MEDLINE, EMBASE, Cochrane, and Google Scholar from inception to August 20, 2023. We included nonrandomized studies that compared the effectiveness between CADe-assisted and standard colonoscopy. Two investigators independently extracted study data and quality. Pairwise meta-analysis was performed utilizing risk ratio for dichotomous variables and mean difference (MD) for continuous variables with a 95% confidence interval (CI).

RESULTS

Eight studies were included, comprising 9782 patients (4569 with CADe and 5213 without CADe). Regarding benefits, there was a difference in neither adenoma detection rate (44% vs 38%; risk ratio, 1.11; 95% CI, 0.97 to 1.28) nor mean adenomas per colonoscopy (0.93 vs 0.79; MD, 0.14; 95% CI, -0.04 to 0.32) between CADe-assisted and standard colonoscopy, respectively. Regarding harms, there was no difference in the mean non-neoplastic lesions per colonoscopy (8 studies included for analysis; 0.52 vs 0.47; MD, 0.14; 95% CI, -0.07 to 0.34) and withdrawal time (6 studies included for analysis; 14.3 vs 13.4 minutes; MD, 0.8 minutes; 95% CI, -0.18 to 1.90). There was a substantial heterogeneity, and all outcomes were graded with a very low certainty of evidence.

CONCLUSION

CADe in colonoscopies neither improves the detection of colorectal neoplasia nor increases burden of colonoscopy in real-world, nonrandomized studies, questioning the generalizability of the results of randomized trials.

Evaluating false-positive detection in a computer-aided detection system for colonoscopy

BACKGROUND AND AIM

Computer-aided detection (CADe) systems can efficiently detect polyps during colonoscopy. However, false-positive (FP) activation is a major limitation of CADe. We aimed to compare the rate and causes of FP using CADe before and after an update designed to reduce FP.

METHODS

We analyzed CADe-assisted colonoscopy videos recorded between July 2022 and October 2022. The number and causes of FPs and excessive time spent by the endoscopist on FP (ET) were compared pre- and post-update using 1:1 propensity score matching.

RESULTS

During the study period, 191 colonoscopy videos (94 and 97 in the pre- and post-update groups, respectively) were recorded. Propensity score matching resulted in 146 videos (73 in each group). The mean number of FPs and median ET per colonoscopy were significantly lower in the post-update group than those in the pre-update group (4.2 ± 3.7 vs 18.1 ± 11.1; P < 0.001 and 0 vs 16 s; P < 0.001, respectively). Mucosal tags, bubbles, and folds had the strongest association with decreased FP post-update (pre-update vs post-update: 4.3 ± 3.6 vs 0.4 ± 0.8, 0.32 ± 0.70 vs 0.04 ± 0.20, and 8.6 ± 6.7 vs 1.6 ± 1.7, respectively). There was no significant decrease in the true positive rate (post-update vs pre-update: 95.0% vs 99.2%; P = 0.09) or the adenoma detection rate (post-update vs pre-update: 52.1% vs 49.3%; P = 0.87).

CONCLUSIONS

The updated CADe can reduce FP without impairing polyp detection. A reduction in FP may help relieve the burden on endoscopists.

Artificial Intelligence-Assisted Colonoscopy in Real-World Clinical Practice: A Systematic Review and Meta-Analysis

INTRODUCTION

Artificial intelligence (AI) could minimize the operator-dependent variation in colonoscopy quality. Computer-aided detection (CADe) has improved adenoma detection rate (ADR) and adenomas per colonoscopy (APC) in randomized controlled trials. There is a need to assess the impact of CADe in real-world settings.

METHODS

We searched MEDLINE, EMBASE, and Web of Science for nonrandomized real-world studies of CADe in colonoscopy. Random-effects meta-analyses were performed to examine the effect of CADe on ADR and APC. The study is registered under PROSPERO (CRD42023424037). There was no funding for this study.

RESULTS

Twelve of 1,314 studies met inclusion criteria. Overall, ADR was statistically significantly higher with vs without CADe (36.3% vs 35.8%, risk ratio [RR] 1.13, 95% confidence interval [CI] 1.01-1.28). This difference remained significant in subgroup analyses evaluating 6 prospective (37.3% vs 35.2%, RR 1.15, 95% CI 1.01-1.32) but not 6 retrospective (35.7% vs 36.2%, RR 1.12, 95% CI 0.92-1.36) studies. Among 6 studies with APC data, APC rate ratio with vs without CADe was 1.12 (95% CI 0.95-1.33). In 4 studies with GI Genius (Medtronic), there was no difference in ADR with vs without CADe (RR 0.96, 95% CI 0.85-1.07).

DISCUSSION

ADR, but not APC, was slightly higher with vs without CADe among all available real-world studies. This difference was attributed to the results of prospective but not retrospective studies. The discrepancies between these findings and those of randomized controlled trials call for future research on the true impact of current AI technology on colonoscopy quality and the subtleties of human-AI interactions.

Performance evaluation of a computer-aided polyp detection system with artificial intelligence for colonoscopy

OBJECTIVES

A computer-aided detection (CAD) system was developed to support the detection of colorectal lesions by deep learning using video images of lesions and normal mucosa recorded during colonoscopy. The study's purpose was to evaluate the stand-alone performance of this device under blinded conditions.

METHODS

This multicenter prospective observational study was conducted at four Japanese institutions. We used 326 videos of colonoscopies recorded with patient consent at institutions in which the Ethics Committees approved the study. The sensitivity of successful detection of the CAD system was calculated using the target lesions, which were detected by adjudicators from two facilities for each lesion appearance frame; inconsistencies were settled by consensus. Successful detection was defined as display of the detection flag on the lesion for more than 0.5 s within 3 s of appearance.

RESULTS

Of the 556 target lesions from 185 cases, detection success sensitivity was 97.5% (95% confidence interval [CI] 95.8-98.5%). The "successful detection sensitivity per colonoscopy" was 93% (95% CI 88.3-95.8%). For the frame-based sensitivity, specificity, positive predictive value, and negative predictive value were 86.6% (95% CI 84.8-88.4%), 84.7% (95% CI 83.8-85.6%), 34.9% (95% CI 32.3-37.4%), and 98.2% (95% CI 97.8-98.5%), respectively.

TRIAL REGISTRATION

University Hospital Medical Information Network (UMIN000044622).

Application of artificial intelligence in endoscopic gastrointestinal tumors

With an increasing number of patients with gastrointestinal cancer, effective and accurate early diagnostic clinical tools are required provide better health care for patients with gastrointestinal cancer. Recent studies have shown that artificial intelligence (AI) plays an important role in the diagnosis and treatment of patients with gastrointestinal tumors, which not only improves the efficiency of early tumor screening, but also significantly improves the survival rate of patients after treatment. With the aid of efficient learning and judgment abilities of AI, endoscopists can improve the accuracy of diagnosis and treatment through endoscopy and avoid incorrect descriptions or judgments of gastrointestinal lesions. The present article provides an overview of the application status of various artificial intelligence in gastric and colorectal cancers in recent years, and the direction of future research and clinical practice is clarified from a clinical perspective to provide a comprehensive theoretical basis for AI as a promising diagnostic and therapeutic tool for gastrointestinal cancer.

The Role of Artificial Intelligence in Colorectal Cancer Screening: Lesion Detection and Lesion Characterization

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

The imitation game: a review of the use of artificial intelligence in colonoscopy, and endoscopists' perceptions thereof

The development of deep learning systems in artificial intelligence (AI) has enabled advances in endoscopy, and AI-aided colonoscopy has recently been ushered into clinical practice as a clinical decision-support tool. This has enabled real-time AI-aided detection of polyps with a higher sensitivity than the average endoscopist, and evidence to support its use has been promising thus far. This review article provides a summary of currently published data relating to AI-aided colonoscopy, discusses current clinical applications, and introduces ongoing research directions. We also explore endoscopists' perceptions and attitudes toward the use of this technology, and discuss factors influencing its uptake in clinical practice.

Knowledge, perceptions and behaviours of endoscopists towards the use of artificial intelligence-aided colonoscopy

BACKGROUND

Recent developments in artificial intelligence (AI) systems have enabled advancements in endoscopy. Deep learning systems, using convolutional neural networks, have allowed for real-time AI-aided detection of polyps with higher sensitivity than the average endoscopist. However, not all endoscopists welcome the advent of AI systems.

METHODS

We conducted a survey on the knowledge of AI, perceptions of AI in medicine, and behaviours regarding use of AI-aided colonoscopy, in a single centre 2 months after the implementation of Medtronic's GI Genius in colonoscopy. We obtained a response rate of 66.7% (16/24) amongst consultant-grade endoscopists. Fisher's exact test was used to calculate the significance of correlations.

RESULTS

Knowledge of AI varied widely amongst endoscopists. Most endoscopists were optimistic about AI's capabilities in performing objective administrative and clinical tasks, but reserved about AI providing personalised, empathetic care. 68.8% (n = 11) of endoscopists agreed or strongly agreed that GI Genius should be used as an adjunct in colonoscopy. In analysing the 31.3% (n = 5) of endoscopists who disagreed or were ambivalent about its use, there was no significant correlation with their knowledge or perceptions of AI, but a significant number did not enjoy using the programme (p-value = 0.0128) and did not think it improved the quality of colonoscopy (p-value = 0.033).

CONCLUSIONS

Acceptance of AI-aided colonoscopy systems is more related to the endoscopist's experience with using the programme, rather than general knowledge or perceptions towards AI. Uptake of such systems will rely greatly on how the device is delivered to the end user.

Recent advances in devices and technologies that might prove revolutionary for colonoscopy procedures

INTRODUCTION

Colorectal cancer (CRC) is the third most common malignancy and second leading cause of cancer-related mortality in the world. Adenoma detection rate (ADR), a quality indicator for colonoscopy, has gained prominence as it is inversely related to CRC incidence and mortality. As such, recent efforts have focused on developing novel colonoscopy devices and technologies to improve ADR.

AREAS COVERED

The main objective of this paper is to provide an overview of advancements in the fields of colonoscopy mechanical attachments, artificial intelligence-assisted colonoscopy, and colonoscopy optical enhancements with respect to ADR. We accomplished this by performing a comprehensive search of multiple electronic databases from inception to September 2023. This review is intended to be an introduction to colonoscopy devices and technologies.

EXPERT OPINION

Numerous mechanical attachments and optical enhancements have been developed that have the potential to improve ADR and AI has gone from being an inaccessible concept to a feasible means for improving ADR. While these advances are exciting and portend a change in what will be considered standard colonoscopy, they continue to require refinement. Future studies should focus on combining modalities to further improve ADR and exploring the use of these technologies in other facets of colonoscopy.

A Real-Time Polyp-Detection System with Clinical Application in Colonoscopy Using Deep Convolutional Neural Networks

Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24% on the open-source CVC-VideoClinicDB benchmark.

Artificial intelligence in gastroenterology: A narrative review

Artificial intelligence (AI) is a complex concept, broadly defined in medicine as the development of computer systems to perform tasks that require human intelligence. It has the capacity to revolutionize medicine by increasing efficiency, expediting data and image analysis and identifying patterns, trends and associations in large datasets. Within gastroenterology, recent research efforts have focused on using AI in esophagogastroduodenoscopy, wireless capsule endoscopy (WCE) and colonoscopy to assist in diagnosis, disease monitoring, lesion detection and therapeutic intervention. The main objective of this narrative review is to provide a comprehensive overview of the research being performed within gastroenterology on AI in esophagogastroduodenoscopy, WCE and colonoscopy.

Impact of artificial intelligence on colorectal polyp detection for early-career endoscopists: an international comparative study

BACKGROUND

Artificial intelligence (AI) for polyp detection is being introduced to colonoscopy, but there is uncertainty how this affects endoscopists' ability to detect polyps and neoplasms. We performed a video-based study to address whether AI improved the endoscopists' performance to detect polyps.

METHODS

We established a dataset of 200 colonoscopy videos (length 5 s; 100 without polyps and 100 with one polyp). About 33 early-career endoscopists (50-400 colonoscopies performed) from 10 European countries classified each video as either 'polyp present' or 'polyp not present'. The video assessment was performed twice with a four-week interval. The first assessment was performed without any AI tool, whereas the second was performed with an AI tool for polyp detection. The primary endpoint was early-career endoscopists' sensitivity to detect polyps. Gold standard for presence and histology of polyps were confirmed by two expert endoscopists and pathologists, respectively. McNemar's test was used for statistical significance.

RESULTS

There were 86 neoplastic and 14 non-neoplastic polyps (mean size 5.6 mm) in the 100 videos with polyps. Early-career endoscopists' sensitivity to detect polyps increased from 86.3% (95% confidence interval [CI]: 85.1-87.5%) to 91.7% (95%CI: 90.7-92.6%) with the AI aid (p < .0001). Their sensitivity to detect neoplastic polyps increased from 85.4% (95% CI: 84.0-86.7%) to 92.1% (95%CI: 91.1-93.1%) with the AI aid (p < .0001).

CONCLUSION

The polyp detection AI tool helped early-career endoscopists to increase their sensitivity to identify all polyps and neoplastic polyps during colonoscopy.

Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications

Colonoscopy is the reference standard procedure for the prevention and diagnosis of colorectal cancer, which is a leading cause of cancer-related deaths in Singapore. Artificial intelligence systems are automated, objective and reproducible. Artificial intelligence-assisted colonoscopy has recently been introduced into clinical practice as a clinical decision support tool. This review article provides a summary of the current published data and discusses ongoing research and current clinical applications of artificial intelligence-assisted colonoscopy.