Performance of Computer-Aided Detection and Diagnosis of Colorectal Polyps Compares to That of Experienced Endoscopists

Evaluation of Artificial Intelligence: Computer-aided Detection of Colorectal Polyps

Objectives

Colonoscopy is the gold standard for screening cancer and precancerous lesions in the large intestine. Recently, remarkable advances in artificial intelligence (AI) have led to the development of various computer-aided detection (CADe) systems for colonoscopy. This study aimed to evaluate the usefulness of AI for colonoscopy using CAD-EYEⓇ (Fujifilm, Tokyo, Japan) to calculate the adenoma miss rate (AMR).

Methods

This randomized, open-label, single-center, tandem study was conducted at Fukuoka University Chikushi Hospital from February 2022 to November 2022. Patients were randomly assigned to the CADe or non-CADe group. Immediately after the completion of the first endoscopy by an endoscopist, a new endoscopist was assigned to perform the second endoscopy. As a result, different endoscopists performed the examinations in a tandem fashion. A missed lesion was defined as a newly detected colorectal polyp by the second endoscopy. Finally, the AMR was compared between the two groups.

Results

The study population comprised 48 patients in the CADe group and 46 patients in the non-CADe group. The AMR was 17.4% in the CADe group and 30.3% in the non-CADe group. Therefore, the AMR in the CADe group was statistically significantly lower than that in the non-CADe group (P=0.009).

Conclusions

The application of CAD-EYEⓇ to colonoscopy reduced the AMR. Overall, CAD-EYEⓇ might be useful for reducing missed colorectal 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.

Multicentre study to assess the performance of an artificial intelligence instrument to support qualitative diagnosis of colorectal polyps

OBJECTIVE

Computer-aided diagnosis (CAD) using artificial intelligence (AI) is expected to support the characterisation of colorectal lesions, which is clinically relevant for efficient colorectal cancer prevention. We conducted this study to assess the diagnostic performance of commercially available CAD systems.

METHODS

This was a multicentre, prospective performance evaluation study. The endoscopist diagnosed polyps using white light imaging, followed by non-magnified blue light imaging (non-mBLI) and mBLI. AI subsequently assessed the lesions using non-mBLI (non-mAI), followed by mBLI (mAI). Eventually, endoscopists made the final diagnosis by integrating the AI diagnosis (AI+endoscopist). The primary endpoint was the accuracy of the AI diagnosis of neoplastic lesions. The diagnostic performance of each modality (sensitivity, specificity and accuracy) and confidence levels were also assessed.

RESULTS

Overall, 380 lesions from 139 patients were included in the analysis. The accuracy of non-mAI was 83%, 95% CI (79% to 87%), which was inferior to that of mBLI (89%, 95% CI (85% to 92%)) and mAI (89%, 95% CI (85% to 92%)). The accuracy (95% CI) of diagnosis by expert endoscopists using mAI (91%, 95% CI (87% to 94%)) was comparable to that of expert endoscopists using mBLI (91%, 95% CI (87% to 94%)) but better than that of non-expert endoscopists using mAI (83%, 95% CI (75% to 90%)). The level of confidence in making a correct diagnosis was increased when using magnification and AI.

CONCLUSIONS

The diagnostic performance of mAI for differentiating colonic lesions is comparable to that of endoscopists, regardless of their experience. However, it can be affected by the use of magnification as well as the endoscopists' level of experience.

Development and internal validation of an artificial intelligence-assisted bowel sounds auscultation system to predict early enteral nutrition-associated diarrhoea in acute pancreatitis: a prospective observational study

Aims/Background An artificial intelligence-assisted prediction model for enteral nutrition-associated diarrhoea (ENAD) in acute pancreatitis (AP) was developed utilising data obtained from bowel sounds auscultation. This model underwent validation through a single-centre, prospective observational study. The primary objective of the model was to enhance clinical decision-making by providing a more precise assessment of ENAD risk. Methods The study enrolled patients with AP who underwent early enteral nutrition (EN). Real-time collection and analysis of bowel sounds were conducted using an artificial intelligence bowel sounds auscultation system. Univariate analysis, multicollinearity analysis, and logistic regression analysis were employed to identify risk factors associated with ENAD. The random forest algorithm was utilised to establish the prediction model, and partial dependence plots were generated to analyse the impact of risk factors on ENAD risk. Validation of the model was performed using the optimal model Bootstrap resampling method. Predictive performance was assessed using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and an area under the receiver operating characteristic (ROC) curve. Results Among the 133 patients included in the study, the incidence of ENAD was 44.4%. Six risk factors were identified, and the model's accuracy was validated through Bootstrap iterations. The prediction accuracy of the model was 81.10%, with a sensitivity of 84.30% and a specificity of 77.80%. The positive predictive value was 82.60%, and the negative predictive value was 80.10%. The area under the ROC curve was 0.904 (95% confidence interval: 0.817-0.997). Conclusion The artificial intelligence bowel sounds auscultation system enhances the assessment of gastrointestinal function in AP patients undergoing EN and facilitates the construction of an ENAD predictive model. The model demonstrates good predictive efficacy, offering an objective basis for precise intervention timing in ENAD management.

Non-polypoid Colorectal Lesions Detection and False Positive Detection by Artificial Intelligence under Blue Laser Imaging and Linked Color Imaging

Objectives

Artificial intelligence (AI) with white light imaging (WLI) is not enough for detecting non-polypoid colorectal polyps and it still has high false positive rate (FPR). We developed AIs using blue laser imaging (BLI) and linked color imaging (LCI) to detect them with specific learning sets (LS).

Methods

The contents of LS were as follows, LS (WLI): 1991 WLI images of lesion of 2-10 mm, LS (IEE): 5920 WLI, BLI, and LCI images of non-polypoid and small lesions of 2-20 mm. LS (IEE) was extracted from videos and included both in-focus and out-of-focus images. We designed three AIs as follows: AI (WLI) finetuned by LS (WLI), AI (IEE) finetuned by LS (WLI)+LS (IEE), and AI (HQ) finetuned by LS (WLI)+LS (IEE) only with images in focus. Polyp detection using a test set of WLI, BLI, and LCI videos of 100 non-polypoid or non-reddish lesions of 2-20 mm and FPR using movies of 15 total colonoscopy were analyzed, compared to 2 experts and 2 trainees.

Results

The sensitivity for LCI in AI (IEE) (83%) was compared to that for WLI in AI (IEE) (76%: p=0.02), WLI in AI (WLI) (57%: p<0.01), BLI in AI (IEE) (78%: p=0.14), and LCI in trainees (74%: p<0.01). The sensitivity for LCI in AI (IEE) (83%) was significantly higher than that in AI (HQ) (78%: p<0.01). The FPR for LCI (6.5%) in AI (IEE) were significantly lower than that in AI (HQ) (17.3%: p<0.01).

Conclusions

AI finetuned by appropriate LS detected non-reddish and non-polypoid polyps under LCI.

Linked-color imaging with or without artificial intelligence for adenoma detection: a randomized trial

BACKGROUND

Adenoma detection rate (ADR) is an important indicator of colonoscopy quality and colorectal cancer incidence. Both linked-color imaging (LCI) with artificial intelligence (LCA) and LCI alone increase adenoma detection during colonoscopy, although it remains unclear whether one modality is superior. This study compared ADR between LCA and LCI alone, including according to endoscopists' experience (experts and trainees) and polyp size.

METHODS

Patients undergoing colonoscopy for positive fecal immunochemical tests, follow-up of colon polyps, and abdominal symptoms at a single institution were randomly assigned to the LCA or LCI group. ADR, adenoma per colonoscopy (APC), cecal intubation time, withdrawal time, number of adenomas per location, and adenoma size were compared.

RESULTS

The LCA (n=400) and LCI (n=400) groups showed comparable cecal intubation and withdrawal times. The LCA group showed a significantly higher ADR (58.8% vs. 43.5%; P<0.001) and mean (95%CI) APC (1.31 [1.15 to 1.47] vs. 0.94 [0.80 to 1.07]; P<0.001), particularly in the ascending colon (0.30 [0.24 to 0.36] vs. 0.20 [0.15 to 0.25]; P=0.02). Total number of nonpolypoid-type adenomas was also significantly higher in the LCA group (0.15 [0.09 to 0.20] vs. 0.08 [0.05 to 0.10]; P=0.02). Small polyps (≤5, 6-9mm) were detected significantly more frequently in the LCA group (0.75 [0.64 to 0.86] vs. 0.48 [0.40 to 0.57], P<0.001 and 0.34 [0.26 to 0.41] vs. 0.24 [0.18 to 0.29], P=0.04, respectively). In both groups, ADR was not significantly different between experts and trainees.

CONCLUSIONS

LCA was significantly superior to LCI alone in terms of ADR.

Detailed Superiority of the CAD EYE Artificial Intelligence System over Endoscopists for Lesion Detection and Characterization Using Unique Movie Sets

Objectives

Detailed superiority of CAD EYE (Fujifilm, Tokyo, Japan), an artificial intelligence for polyp detection/diagnosis, compared to endoscopists is not well examined. We examined endoscopist's ability using movie sets of colorectal lesions which were detected and diagnosed by CAD EYE accurately.

Methods

Consecutive lesions of ≤10 mm were examined live by CAD EYE from March-June 2022 in our institution. Short unique movie sets of each lesion with and without CAD EYE were recorded simultaneously using two recorders for detection under white light imaging (WLI) and linked color imaging (LCI) and diagnosis under blue laser/light imaging (BLI). Excluding inappropriate movies, 100 lesions detected and diagnosed with CAD EYE accurately were evaluated. Movies without CAD EYE were evaluated first by three trainees and three experts. Subsequently, movies with CAD EYE were examined. The rates of accurate detection and diagnosis were evaluated for both movie sets.

Results

Among 100 lesions (mean size: 4.7±2.6 mm; 67 neoplastic/33 hyperplastic), mean accurate detection rates of movies without or with CAD EYE were 78.7%/96.7% under WLI (p<0.01) and 91.3%/97.3% under LCI (p<0.01) for trainees and 85.3%/99.0% under WLI (p<0.01) and 92.6%/99.3% under LCI (p<0.01) for experts. Mean accurate diagnosis rates of movies without or with CAD EYE for BLI were 85.3%/100% for trainees (p<0.01) and 92.3%/100% for experts (p<0.01), respectively. The significant risk factors of not-detected lesions for trainees were right-sided, hyperplastic, not-reddish, in the corner, halation, and inadequate bowel preparation.

Conclusions

Unique movie sets with and without CAD EYE could suggest it's efficacy for lesion detection/diagnosis.

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).

Impact of an artificial intelligence-aided endoscopic diagnosis system on improving endoscopy quality for trainees in colonoscopy: Prospective, randomized, multicenter study

OBJECTIVE

This study was performed to evaluate whether the use of CAD EYE (Fujifilm, Tokyo, Japan) for colonoscopy improves colonoscopy quality in gastroenterology trainees.

METHODS

The patients in this multicenter randomized controlled trial were divided into Group A (observation using CAD EYE) and Group B (standard observation). Six trainees performed colonoscopies using a back-to-back method in pairs with gastroenterology experts. The primary end-point was the trainees' adenoma detection rate (ADR), and the secondary end-points were the trainees' adenoma miss rate (AMR) and Assessment of Competency in Endoscopy (ACE) tool scores. Each trainee's learning curve was evaluated using a cumulative sum (CUSUM) control chart.

RESULTS

We analyzed data for 231 patients (Group A, n = 113; Group B, n = 118). The ADR was not significantly different between the two groups. Group A had a significantly lower AMR (25.6% vs. 38.6%, P = 0.033) and number of missed adenomas per patient (0.5 vs. 0.9, P = 0.004) than Group B. Group A also had significantly higher ACE tool scores for pathology identification (2.26 vs. 2.07, P = 0.030) and interpretation and identification of pathology location (2.18 vs. 2.00, P = 0.038). For the CUSUM learning curve, Group A showed a trend toward a lower number of cases of missed multiple adenomas by the six trainees.

CONCLUSION

CAD EYE did not improve ADR but decreased the AMR and improved the ability to accurately locate and identify colorectal adenomas. CAD EYE can be assumed to be beneficial for improving colonoscopy quality in gastroenterology trainees.

TRIAL REGISTRATION

University Hospital Medical Information Network Clinical Trials Registry (UMIN000044031).

The Potential Use of Artificial Intelligence in Irritable Bowel Syndrome Management

Irritable bowel syndrome (IBS) has a global prevalence of around 4.1% and is associated with a low quality of life and increased healthcare costs. Current guidelines recommend that IBS is diagnosed using the symptom-based Rome IV criteria. Despite this, when patients seek medical attention, they are usually over-investigated. This issue might be resolved by novel technologies in medicine, such as the use of Artificial Intelligence (AI). In this context, this paper aims to review AI applications in IBS. AI in colonoscopy proved to be useful in organic lesion detection and diagnosis and in objectively assessing the quality of the procedure. Only a recently published study talked about the potential of AI-colonoscopy in IBS. AI was also used to study biofilm characteristics in the large bowel and establish a potential relationship with IBS. Moreover, an AI algorithm was developed in order to correlate specific bowel sounds with IBS. In addition to that, AI-based smartphone applications have been developed to facilitate the monitoring of IBS symptoms. From a therapeutic standpoint, an AI system was created to recommend specific diets based on an individual's microbiota. In conclusion, future IBS diagnosis and treatment may benefit from AI.

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.

Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video

Artificial-intelligence-based computer-aided diagnosis (CAD) systems have developed remarkably in recent years. These systems can help increase the adenoma detection rate (ADR), an important quality indicator in colonoscopies. While there have been many still-image-based studies on the usefulness of CAD, few have reported on its usefulness using actual clinical videos. However, no studies have compared the CAD group and control groups using the exact same case videos. This study aimed to determine whether CAD or endoscopists were superior in identifying colorectal neoplastic lesions in videos. In this study, we examined 34 lesions from 21 cases. CAD performed better than four of the six endoscopists (three experts and three beginners), including all the beginners. The time to lesion detection with beginners and experts was 2.147 ± 1.118 s and 1.394 ± 0.805 s, respectively, with significant differences between beginners and experts (p < 0.001) and between beginners and CAD (both p < 0.001). The time to lesion detection was significantly shorter for experts and CAD than for beginners. No significant difference was found between experts and CAD (p = 1.000). CAD could be useful as a diagnostic support tool for beginners to bridge the experience gap with experts.

Performance of artificial intelligence in the characterization of colorectal lesions

Background

Image-enhanced endoscopy (IEE) has been used in the differentiation between neoplastic and non-neoplastic colorectal lesions through microvasculature analysis. This study aimed to evaluate the computer-aided diagnosis (CADx) mode of the CAD EYE system for the optical diagnosis of colorectal lesions and compare it with the performance of an expert, in addition to evaluating the computer-aided detection (CADe) mode in terms of polyp detection rate (PDR) and adenoma detection rate (ADR).

Methods

A prospective study was conducted to evaluate the performance of CAD EYE using blue light imaging (BLI), dichotomizing lesions into hyperplastic and neoplastic, and of an expert based on the Japan Narrow-Band Imaging Expert Team (JNET) classification for the characterization of lesions. After white light imaging (WLI) diagnosis, magnification was used on all lesions, which were removed and examined histologically. Diagnostic criteria were evaluated, and PDR and ADR were calculated.

Results

A total of 110 lesions (80 (72.7%) dysplastic lesions and 30 (27.3%) nondysplastic lesions) were evaluated in 52 patients, with a mean lesion size of 4.3 mm. Artificial intelligence (AI) analysis showed 81.8% accuracy, 76.3% sensitivity, 96.7% specificity, 98.5% positive predictive value (PPV), and 60.4% negative predictive value (NPV). The kappa value was 0.61, and the area under the receiver operating characteristic curve (AUC) was 0.87. Expert analysis showed 93.6% accuracy, 92.5% sensitivity, 96.7% specificity, 98.7% PPV, and 82.9% NPV. The kappa value was 0.85, and the AUC was 0.95. Overall, PDR was 67.6% and ADR was 45.9%.

Conclusions

The CADx mode showed good accuracy in characterizing colorectal lesions, but the expert assessment was superior in almost all diagnostic criteria. PDR and ADR were high.

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.

Mucosal imaging in colon polyps: New advances and what the future may hold

An expanding range of advanced mucosal imaging technologies have been developed with the goal of improving the detection and characterization of lesions in the gastrointestinal tract. Many technologies have targeted colorectal neoplasia given the potential for intervention prior to the development of invasive cancer in the setting of widespread surveillance programs. Improvement in adenoma detection reduces miss rates and prevents interval cancer development. Advanced imaging technologies aim to enhance detection without significantly increasing procedural time. Accurate polyp characterisation guides resection techniques for larger polyps, as well as providing the platform for the "resect and discard" and "do not resect" strategies for small and diminutive polyps. This review aims to collate and summarise the evidence regarding these technologies to guide colonoscopic practice in both interventional and non-interventional endoscopists.

Current Status and Future Perspectives of Artificial Intelligence in Colonoscopy

The early endoscopic identification, resection, and treatment of precancerous adenoma and early-stage cancer has been shown to reduce not only the prevalence of colorectal cancer but also its mortality rate. Recent advances in endoscopic devices and imaging technology have dramatically improved our ability to detect colorectal lesions and predict their pathological diagnosis. In addition to this, rapid advances in artificial intelligence (AI) technology mean that AI-related research and development is now progressing in the diagnostic imaging field, particularly colonoscopy, and AIs (i.e., devices that mimic cognitive abilities, such as learning and problem-solving) already approved as medical devices are now being introduced into everyday clinical practice. Today, there is an increasing expectation that sophisticated AIs will be able to provide high-level diagnostic performance irrespective of the level of skill of the endoscopist. In this paper, we review colonoscopy-related AI research and the AIs that have already been approved and discuss the future prospects of this technology.

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.