Quality assurance of computer-aided detection and diagnosis in colonoscopy

Artificial intelligence for gastric cancer in endoscopy: From diagnostic reasoning to market

Recognition of gastric conditions during endoscopy exams, including gastric cancer, usually requires specialized training and a long learning curve. Besides that, the interobserver variability is frequently high due to the different morphological characteristics of the lesions and grades of mucosal inflammation. In this sense, artificial intelligence tools based on deep learning models have been developed to support physicians to detect, classify, and predict gastric lesions more efficiently. Even though a growing number of studies exists in the literature, there are multiple challenges to bring a model to practice in this field, such as the need for more robust validation studies and regulatory hurdles. Therefore, the aim of this review is to provide a comprehensive assessment of the current use of artificial intelligence applied to endoscopic imaging to evaluate gastric precancerous and cancerous lesions and the barriers to widespread implementation of this technology in clinical routine.

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.

Establishment and validation of an artificial intelligence-based model for real-time detection and classification of colorectal adenoma

Colorectal cancer (CRC) prevention requires early detection and removal of adenomas. We aimed to develop a computational model for real-time detection and classification of colorectal adenoma. Computationally constrained background based on real-time detection, we propose an improved adaptive lightweight ensemble model for real-time detection and classification of adenomas and other polyps. Firstly, we devised an adaptive lightweight network modification and effective training strategy to diminish the computational requirements for real-time detection. Secondly, by integrating the adaptive lightweight YOLOv4 with the single shot multibox detector network, we established the adaptive small object detection ensemble (ASODE) model, which enhances the precision of detecting target polyps without significantly increasing the model's memory footprint. We conducted simulated training using clinical colonoscopy images and videos to validate the method's performance, extracting features from 1148 polyps and employing a confidence threshold of 0.5 to filter out low-confidence sample predictions. Finally, compared to state-of-the-art models, our ASODE model demonstrated superior performance. In the test set, the sensitivity of images and videos reached 87.96% and 92.31%, respectively. Additionally, the ASODE model achieved an accuracy of 92.70% for adenoma detection with a false positive rate of 8.18%. Training results indicate the effectiveness of our method in classifying small polyps. Our model exhibits remarkable performance in real-time detection of colorectal adenomas, serving as a reliable tool for assisting endoscopists.

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 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.

Performance comparison between two computer-aided detection colonoscopy models by trainees using different false positive thresholds: a cross-sectional study in Thailand

BACKGROUND/AIMS

This study aims to compare polyp detection performance of "Deep-GI," a newly developed artificial intelligence (AI) model, to a previously validated AI model computer-aided polyp detection (CADe) using various false positive (FP) thresholds and determining the best threshold for each model.

METHODS

Colonoscopy videos were collected prospectively and reviewed by three expert endoscopists (gold standard), trainees, CADe (CAD EYE; Fujifilm Corp.), and Deep-GI. Polyp detection sensitivity (PDS), polyp miss rates (PMR), and false-positive alarm rates (FPR) were compared among the three groups using different FP thresholds for the duration of bounding boxes appearing on the screen.

RESULTS

In total, 170 colonoscopy videos were used in this study. Deep-GI showed the highest PDS (99.4% vs. 85.4% vs. 66.7%, p<0.01) and the lowest PMR (0.6% vs. 14.6% vs. 33.3%, p<0.01) when compared to CADe and trainees, respectively. Compared to CADe, Deep-GI demonstrated lower FPR at FP thresholds of ≥0.5 (12.1 vs. 22.4) and ≥1 second (4.4 vs. 6.8) (both p<0.05). However, when the threshold was raised to ≥1.5 seconds, the FPR became comparable (2 vs. 2.4, p=0.3), while the PMR increased from 2% to 10%.

CONCLUSION

Compared to CADe, Deep-GI demonstrated a higher PDS with significantly lower FPR at ≥0.5- and ≥1-second thresholds. At the ≥1.5-second threshold, both systems showed comparable FPR with increased PMR.

Use of a Novel Artificial Intelligence System Leads to the Detection of Significantly Higher Number of Adenomas During Screening and Surveillance Colonoscopy: Results From a Large, Prospective, US Multicenter, Randomized Clinical Trial

INTRODUCTION

Adenoma per colonoscopy (APC) has recently been proposed as a quality measure for colonoscopy. We evaluated the impact of a novel artificial intelligence (AI) system, compared with standard high-definition colonoscopy, for APC measurement.

METHODS

This was a US-based, multicenter, prospective randomized trial examining a novel AI detection system (EW10-EC02) that enables a real-time colorectal polyp detection enabled with the colonoscope (CAD-EYE). Eligible average-risk subjects (45 years or older) undergoing screening or surveillance colonoscopy were randomized to undergo either CAD-EYE-assisted colonoscopy (CAC) or conventional colonoscopy (CC). Modified intention-to-treat analysis was performed for all patients who completed colonoscopy with the primary outcome of APC. Secondary outcomes included positive predictive value (total number of adenomas divided by total polyps removed) and adenoma detection rate.

RESULTS

In modified intention-to-treat analysis, of 1,031 subjects (age: 59.1 ± 9.8 years; 49.9% male), 510 underwent CAC vs 523 underwent CC with no significant differences in age, gender, ethnicity, or colonoscopy indication between the 2 groups. CAC led to a significantly higher APC compared with CC: 0.99 ± 1.6 vs 0.85 ± 1.5, P = 0.02, incidence rate ratio 1.17 (1.03-1.33, P = 0.02) with no significant difference in the withdrawal time: 11.28 ± 4.59 minutes vs 10.8 ± 4.81 minutes; P = 0.11 between the 2 groups. Difference in positive predictive value of a polyp being an adenoma among CAC and CC was less than 10% threshold established: 48.6% vs 54%, 95% CI -9.56% to -1.48%. There were no significant differences in adenoma detection rate (46.9% vs 42.8%), advanced adenoma (6.5% vs 6.3%), sessile serrated lesion detection rate (12.9% vs 10.1%), and polyp detection rate (63.9% vs 59.3%) between the 2 groups. There was a higher polyp per colonoscopy with CAC compared with CC: 1.68 ± 2.1 vs 1.33 ± 1.8 (incidence rate ratio 1.27; 1.15-1.4; P < 0.01).

DISCUSSION

Use of a novel AI detection system showed to a significantly higher number of adenomas per colonoscopy compared with conventional high-definition colonoscopy without any increase in colonoscopy withdrawal time, thus supporting the use of AI-assisted colonoscopy to improve colonoscopy quality ( ClinicalTrials.gov NCT04979962).

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).

Deep learning-based anatomical position recognition for gastroscopic examination

BACKGROUND

The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors.

OBJECTIVE

The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination.

METHODS

A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score.

RESULTS

The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05).

CONCLUSION

The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.

Artificial intelligence for colorectal neoplasia detection during colonoscopy: a systematic review and meta-analysis of randomized clinical trials

BACKGROUND

The use of artificial intelligence (AI) in detecting colorectal neoplasia during colonoscopy holds the potential to enhance adenoma detection rates (ADRs) and reduce adenoma miss rates (AMRs). However, varied outcomes have been observed across studies. Thus, this study aimed to evaluate the potential advantages and disadvantages of employing AI-aided systems during colonoscopy.

METHODS

Using Medical Subject Headings (MeSH) terms and keywords, a comprehensive electronic literature search was performed of the Embase, Medline, and the Cochrane Library databases from the inception of each database until October 04, 2023, in order to identify randomized controlled trials (RCTs) comparing AI-assisted with standard colonoscopy for detecting colorectal neoplasia. Primary outcomes included AMR, ADR, and adenomas detected per colonoscopy (APC). Secondary outcomes comprised the poly missed detection rate (PMR), poly detection rate (PDR), and poly detected per colonoscopy (PPC). We utilized random-effects meta-analyses with Hartung-Knapp adjustment to consolidate results. The prediction interval (PI) and I2 statistics were utilized to quantify between-study heterogeneity. Moreover, meta-regression and subgroup analyses were performed to investigate the potential sources of heterogeneity. This systematic review and meta-analysis is registered with PROSPERO (CRD42023428658).

FINDINGS

This study encompassed 33 trials involving 27,404 patients. Those undergoing AI-aided colonoscopy experienced a significant decrease in PMR (RR, 0.475; 95% CI, 0.294-0.768; I2 = 87.49%) and AMR (RR, 0.495; 95% CI, 0.390-0.627; I2 = 48.76%). Additionally, a significant increase in PDR (RR, 1.238; 95% CI, 1.158-1.323; I2 = 81.67%) and ADR (RR, 1.242; 95% CI, 1.159-1.332; I2 = 78.87%), along with a significant increase in the rates of PPC (IRR, 1.388; 95% CI, 1.270-1.517; I2 = 91.99%) and APC (IRR, 1.390; 95% CI, 1.277-1.513; I2 = 86.24%), was observed. This resulted in 0.271 more PPCs (95% CI, 0.144-0.259; I2 = 65.61%) and 0.202 more APCs (95% CI, 0.144-0.259; I2 = 68.15%).

INTERPRETATION

AI-aided colonoscopy significantly enhanced the detection of colorectal neoplasia detection, likely by reducing the miss rate. However, future studies should focus on evaluating the cost-effectiveness and long-term benefits of AI-aided colonoscopy in reducing cancer incidence.

FUNDING

This work was supported by the Heilongjiang Provincial Natural Science Foundation of China (LH2023H096), the Postdoctoral research project in Heilongjiang Province (LBH-Z22210), the National Natural Science Foundation of China's General Program (82072640) and the Outstanding Youth Project of Heilongjiang Natural Science Foundation (YQ2021H023).

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.

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.

Computer-aided diagnosis of early-stage colorectal cancer using nonmagnified endoscopic white-light images (with videos)

BACKGROUND AND AIMS

Differentiation of colorectal cancers (CRCs) with deep submucosal invasion (T1b) from CRCs with superficial invasion (T1a) or no invasion (Tis) is not straightforward. This study aimed to develop a computer-aided diagnosis (CADx) system to establish the diagnosis of early-stage cancers using nonmagnified endoscopic white-light images alone.

METHODS

From 5108 images, 1513 lesions (Tis, 1074; T1a, 145; T1b, 294) were collected from 1470 patients at 10 academic hospitals and assigned to training and testing datasets (3:1). The ResNet-50 network was used as the backbone to extract features from images. Oversampling and focal loss were used to compensate class imbalance of the invasive stage. Diagnostic performance was assessed using the testing dataset including 403 CRCs with 1392 images. Two experts and 2 trainees read the identical testing dataset.

RESULTS

At a 90% cutoff for the per-lesion score, CADx showed the highest specificity of 94.4% (95% confidence interval [CI], 91.3-96.6), with 59.8% (95% CI, 48.3-70.4) sensitivity and 87.3% (95% CI, 83.7-90.4) accuracy. The area under the characteristic curve was 85.1% (95% CI, 79.9-90.4) for CADx, 88.2% (95% CI, 83.7-92.8) for expert 1, 85.9% (95% CI, 80.9-90.9) for expert 2, 77.0% (95% CI, 71.5-82.4) for trainee 1 (vs CADx; P = .0076), and 66.2% (95% CI, 60.6-71.9) for trainee 2 (P < .0001). The function was also confirmed on 9 short videos.

CONCLUSIONS

A CADx system developed with endoscopic white-light images showed excellent per-lesion specificity and accuracy for T1b lesion diagnosis, equivalent to experts and superior to trainees. (Clinical trial registration number: UMIN000037053.).

Effectiveness and application of artificial intelligence for endoscopic screening of colorectal cancer: the future is now

INTRODUCTION

Artificial intelligence (AI) in gastrointestinal endoscopy includes systems designed to interpret medical images and increase sensitivity during examination. This may be a promising solution to human biases and may provide support during diagnostic endoscopy.

AREAS COVERED

This review aims to summarize and evaluate data supporting AI technologies in lower endoscopy, addressing their effectiveness, limitations, and future perspectives.

EXPERT OPINION

Computer-aided detection (CADe) systems have been studied with promising results, allowing for an increase in adenoma detection rate (ADR), adenoma per colonoscopy (APC), and a reduction in adenoma miss rate (AMR). This may lead to an increase in the sensitivity of endoscopic examinations and a reduction in the risk of interval-colorectal cancer. In addition, computer-aided characterization (CADx) has also been implemented, aiming to distinguish adenomatous and non-adenomatous lesions through real-time assessment using advanced endoscopic imaging techniques. Moreover, computer-aided quality (CADq) systems have been developed with the aim of standardizing quality measures in colonoscopy (e.g. withdrawal time and adequacy of bowel cleansing) both to improve the quality of examinations and set a reference standard for randomized controlled trials.

A Review of Colonoscopy in Intestinal Diseases

Since the development of the fiberoptic colonoscope in the late 1960s, colonoscopy has been a useful tool to diagnose and treat various intestinal diseases. This article reviews the clinical use of colonoscopy for various intestinal diseases based on present and future perspectives. Intestinal diseases include infectious diseases, inflammatory bowel disease (IBD), neoplasms, functional bowel disorders, and others. In cases of infectious diseases, colonoscopy is helpful in making the differential diagnosis, revealing endoscopic gross findings, and obtaining the specimens for pathology. Additionally, colonoscopy provides clues for distinguishing between infectious disease and IBD, and aids in the post-treatment monitoring of IBD. Colonoscopy is essential for the diagnosis of neoplasms that are diagnosed through only pathological confirmation. At present, malignant tumors are commonly being treated using endoscopy because of the advancement of endoscopic resection procedures. Moreover, the characteristics of tumors can be described in more detail by image-enhanced endoscopy and magnifying endoscopy. Colonoscopy can be helpful for the endoscopic decompression of colonic volvulus in large bowel obstruction, balloon dilatation as a treatment for benign stricture, and colon stenting as a treatment for malignant obstruction. In the diagnosis of functional bowel disorder, colonoscopy is used to investigate other organic causes of the symptom.

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.

Development and validation of an artificial intelligence-based system for predicting colorectal cancer invasion depth using multi-modal data

OBJECTIVES

Accurate endoscopic optical prediction of the depth of cancer invasion is critical for guiding an optimal treatment approach of large sessile colorectal polyps but was hindered by insufficient endoscopists expertise and inter-observer variability. We aimed to construct a clinically applicable artificial intelligence (AI) system for the identification of presence of cancer invasion in large sessile colorectal polyps.

METHODS

A deep learning-based colorectal cancer invasion calculation (CCIC) system was constructed. Multi-modal data including clinical information, white light (WL) and image-enhanced endoscopy (IEE) were included for training. The system was trained using 339 lesions and tested on 198 lesions across three hospitals. Man-machine contest, reader study and video validation were further conducted to evaluate the performance of CCIC.

RESULTS

The overall accuracy of CCIC system using image and video validation was 90.4% and 89.7%, respectively. In comparison with 14 endoscopists, the accuracy of CCIC was comparable with expert endoscopists but superior to all the participating senior and junior endoscopists in both image and video validation set. With CCIC augmentation, the average accuracy of junior endoscopists improved significantly from 75.4% to 85.3% (P = 0.002).

CONCLUSIONS

This deep learning-based CCIC system may play an important role in predicting the depth of cancer invasion in colorectal polyps, thus determining treatment strategies for these large sessile colorectal polyps.

The scientific progress and prospects of artificial intelligence in digestive endoscopy: A comprehensive bibliometric analysis

Artificial intelligence (AI) has been used for diagnosis and outcome prediction in clinical practice. Furthermore, AI in digestive endoscopy has attracted much attention and shown promising and stimulating results. This study aimed to determine the development trends and research hotspots of AI in digestive endoscopy by visualizing articles. Publications on AI in digestive endoscopy research were retrieved from the Web of Science Core Collection on April 25, 2022. VOSviewer and CiteSpace were used to assess and plot the research outputs. This analytical research was based on original articles and reviews. A total of 524 records of AI research in digestive endoscopy, published between 2005 and 2022, were retrieved. The number of articles has increased 27-fold from 2017 to 2021. Fifty-one countries and 994 institutions contributed to all publications. Asian countries had the highest number of publications. China, the USA, and Japan were consistently the leading driving forces and mainly contributed (26%, 21%, and 14.31%, respectively). With a solid academic reputation in this area, Japan has the highest number of citations per article. Tada Tomohiro published the most articles and received the most citations.. Gastrointestinal endoscopy published the largest number of publications, and 4 of the top 10 cited papers were published in this journal. "The Classification," "ulcerative colitis," "capsule endoscopy," "polyp detection," and "early gastric cancer" were the leading research hotspots. Our study provides systematic elaboration for researchers to better understand the development of AI in gastrointestinal endoscopy.

Effects of ai-assisted colonoscopy on adenoma miss rate/adenoma detection rate: A protocol for systematic review and meta-analysis

BACKGROUND

Colonoscopy can detect colorectal adenomas and reduce the incidence of colorectal cancer, but there are still many missing diagnoses. Artificial intelligence-assisted colonoscopy (AIAC) can effectively reduce the rate of missed diagnosis and improve the detection rate of adenoma, but its clinical application is still unclear. This systematic review and meta-analysis assessed the adenoma missed detection rate (AMR) and the adenoma detection rate (ADR) by artificial colonoscopy.

METHODS

Conduct a comprehensive literature search using the PubMed, Medline database, Embase, and the Cochrane Library. This meta-analysis followed the direction of the preferred reporting items for systematic reviews and meta-analyses, the preferred reporting item for systematic review and meta-analysis. The random effect model was used for meta-analysis.

RESULTS

A total of 12 articles were eventually included in the study. Computer aided detection (CADe) significantly decreased AMR compared with the control group (137/1039, 13.2% vs 304/1054, 28.8%; OR,0.39; 95% CI, 0.26-0.59; P < .05). Similarly, there was statistically significant difference in ADR between the CADe group and control group, respectively (1835/5041, 36.4% vs 1309/4553, 28.7%; OR, 1.54; 95% CI, 1.39-1.71; P < .05). The advanced adenomas missed rate and detection rate in CADe group was not statistically significant when compared with the control group.

CONCLUSIONS

AIAC can effectively reduce AMR and improve ADR, especially small adenomas. Therefore, this method is worthy of clinical application. However, due to the limitations of the number and quality of the included studies, more in-depth studies are needed in the field of AIAC in the future.

Trial protocol for COLO-DETECT: A randomized controlled trial of lesion detection comparing colonoscopy assisted by the GI Genius™ artificial intelligence endoscopy module with standard colonoscopy

AIM

Colorectal cancer is the second commonest cause of cancer death worldwide. Colonoscopy plays a key role in the control of colorectal cancer and, in that regard, maximizing detection (and removal) of pre-cancerous adenomas at colonoscopy is imperative. GI Genius™ (Medtronic Ltd) is a computer-aided detection system that integrates with existing endoscopy systems and improves adenoma detection during colonoscopy. COLO-DETECT aims to assess the clinical and cost effectiveness of GI Genius™ in UK routine colonoscopy practice.

METHODS AND ANALYSIS

Participants will be recruited from patients attending for colonoscopy at National Health Service sites in England, for clinical symptoms, surveillance or within the national Bowel Cancer Screening Programme. Randomization will involve a 1:1 allocation ratio (GI Genius™-assisted colonoscopy:standard colonoscopy) and will be stratified by age category (<60 years, 60-<74 years, ≥74 years), sex, hospital site and indication for colonoscopy. Demographic data, procedural data, histology and post-procedure patient experience and quality of life will be recorded. COLO-DETECT is designed and powered to detect clinically meaningful differences in mean adenomas per procedure and adenoma detection rate between GI Genius™-assisted colonoscopy and standard colonoscopy groups. The study will close when 1828 participants have had a complete colonoscopy. An economic evaluation will be conducted from the perspective of the National Health Service. A patient and public representative is contributing to all stages of the trial. Registered at ClinicalTrials.gov (NCT04723758) and ISRCTN (10451355). WHAT WILL THIS TRIAL ADD TO THE LITERATURE?: COLO-DETECT will be the first multi-centre randomized controlled trial evaluating GI Genius™ in real world colonoscopy practice and will, uniquely, evaluate both clinical and cost effectiveness.

A review: The detection of cancer cells in histopathology based on machine vision

Machine vision is being employed in defect detection, size measurement, pattern recognition, image fusion, target tracking and 3D reconstruction. Traditional cancer detection methods are dominated by manual detection, which wastes time and manpower, and heavily relies on the pathologists' skill and work experience. Therefore, these manual detection approaches are not convenient for the inheritance of domain knowledge, and are not suitable for the rapid development of medical care in the future. The emergence of machine vision can iteratively update and learn the domain knowledge of cancer cell pathology detection to achieve automated, high-precision, and consistent detection. Consequently, this paper reviews the use of machine vision to detect cancer cells in histopathology images, as well as the benefits and drawbacks of various detection approaches. First, we review the application of image preprocessing and image segmentation in histopathology for the detection of cancer cells, and compare the benefits and drawbacks of different algorithms. Secondly, for the characteristics of histopathological cancer cell images, the research progress of shape, color and texture features and other methods is mainly reviewed. Furthermore, for the classification methods of histopathological cancer cell images, the benefits and drawbacks of traditional machine vision approaches and deep learning methods are compared and analyzed. Finally, the above research is discussed and forecasted, with the expected future development tendency serving as a guide for future research.

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

OBJECTIVES

There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field.

METHODS

An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp-positive frames and 634,988 polyp-negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK).

RESULTS

In the first two video datasets, the algorithm achieved per-polyp sensitivities of 100% and 98.9%. Per-frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG-independent and trainee endoscopists, achieving per-polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average.

CONCLUSIONS

The AI based algorithm achieved high per-polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.

Anomaly Detection of Calcifications in Mammography Based on 11,000 Negative Cases

In mammography, calcifications are one of the most common signs of breast cancer. Detection of such lesions is an active area of research for computer-aided diagnosis and machine learning algorithms. Due to limited numbers of positive cases, many supervised detection models suffer from overfitting and fail to generalize. We present a one-class, semi-supervised framework using a deep convolutional autoencoder trained with over 50,000 images from 11,000 negative-only cases. Since the model learned from only normal breast parenchymal features, calcifications produced large signals when comparing the residuals between input and reconstruction output images. As a key advancement, a structural dissimilarity index was used to suppress non-structural noises. Our selected model achieved pixel-based AUROC of 0.959 and AUPRC of 0.676 during validation, where calcification masks were defined in a semi-automated process. Although not trained directly on any cancers, detection performance of calcification lesions on 1,883 testing images (645 malignant and 1238 negative) achieved 75% sensitivity at 2.5 false positives per image. Performance plateaued early when trained with only a fraction of the cases, and greater model complexity or a larger dataset did not improve performance. This study demonstrates the potential of this anomaly detection approach to detect mammographic calcifications in a semi-supervised manner with efficient use of a small number of labeled images, and may facilitate new clinical applications such as computer-aided triage and quality improvement.

Comparing the number and relevance of false activations between 2 artificial intelligence computer-aided detection systems: the NOISE study

BACKGROUND AND AIMS

Artificial intelligence has been shown to be effective in polyp detection, and multiple computer-aided detection (CADe) systems have been developed. False-positive (FP) activation emerged as a possible way to benchmark CADe performance in clinical practice. The aim of this study was to validate a previously developed classification of FPs comparing the performances of different brands of approved CADe systems.

METHODS

We compared 2 different consecutive video libraries (40 video per arm) collected at Humanitas Research Hospital with 2 different CADe system brands (CADe A and CADe B). For each video, the number of CADe false activations, cause, and time spent by the endoscopist to examine the area erroneously highlighted were reported. The FP activations were classified according to the previously developed classification of FPs (the NOISE classification) according to their cause and relevance.

RESULTS

In CADe A 1021 FP activations were registered across the 40 videos (25.5 ± 12.2 FPs per colonoscopy), whereas in CADe B 1028 were identified (25.7 ± 13.2 FPs per colonoscopy; P = .53). Among them, 22.9 ± 9.9 (89.8% in CADe A) and 22.1 ± 10.0 (86.0% in CADe B) were because of artifacts from the bowel wall. Conversely, 2.6 ± 1.9 (10.2% in CADe A) and 3.5 ± 2.1 (14% in CADe B) were caused by bowel content (P = .45). Within CADe A each false activation required .2 ± .9 seconds, with 1.6 ± 1.0 FPs (6.3%) requiring additional time for endoscopic assessment. Comparable results were reported within CADe B with .2 ± .8 seconds spent per false activation and 1.8 ± 1.2 FPs per colonoscopy requiring additional inspection.

CONCLUSIONS

The use of a standardized nomenclature provided comparable results with either of the 2 recently approved CADe systems. (Clinical trial registration number: NCT04399590.).

Clinical evaluation of a real-time artificial intelligence-based polyp detection system: a US multi-center pilot study

Artificial intelligence (AI) has increasingly been employed in multiple fields, and there has been significant interest in its use within gastrointestinal endoscopy. Computer-aided detection (CAD) can potentially improve polyp detection rates and decrease miss rates in colonoscopy. However, few clinical studies have evaluated real-time CAD during colonoscopy. In this study, we analyze the efficacy of a novel real-time CAD system during colonoscopy. This was a single-arm prospective study of patients undergoing colonoscopy with a real-time CAD system. This AI-based system had previously been trained using manually labeled colonoscopy videos to help detect neoplastic polyps (adenomas and serrated polyps). In this pilot study, 300 patients at two centers underwent elective colonoscopy with the CAD system. These results were compared to 300 historical controls consisting of consecutive colonoscopies performed by the participating endoscopists within 12 months prior to onset of the study without the aid of CAD. The primary outcome was the mean number of adenomas per colonoscopy. Use of real-time CAD trended towards increased adenoma detection (1.35 vs 1.07, p = 0.099) per colonoscopy though this did not achieve statistical significance. Compared to historical controls, use of CAD demonstrated a trend towards increased identification of serrated polyps (0.15 vs 0.07) and all neoplastic (adenomatous and serrated) polyps (1.50 vs 1.14) per procedure. There were significantly more non-neoplastic polyps detected with CAD (1.08 vs 0.57, p < 0.0001). There was no difference in ≥ 10 mm polyps identified between the two groups. A real-time CAD system can increase detection of adenomas and serrated polyps during colonoscopy in comparison to historical controls without CAD, though this was not statistically significant. As this pilot study is underpowered, given the findings we recommend pursuing a larger randomized controlled trial to further evaluate the benefits of CAD.

Artificial intelligence in colonoscopy: A review on the current status

Artificial intelligence has become an increasingly hot topic in the last several years, and it has also gained its way into the medical field. In recent years, the application of artificial intelligence in the gastroenterology field has been of increasing interest, particularly in the colonoscopy setting. Novel technologies such as deep neural networks have enabled real‐time computer‐aided polyp detection and diagnosis during colonoscopy. This might lead to increased performance of endoscopists as well as potentially reducing the costs of unnecessary polypectomies of hyperplastic polyps. Newly published prospective trials studying computer‐aided detection showed that the assistance of artificial intelligence significantly increased the detection of polyps and non‐advanced adenomas approximately by 10%, while three tandem randomized control trials proved that the adenoma miss rate was significantly reduced (e.g., 13.8% vs. 36.7% in one Japanese multicenter trial). Promising results have also been shown in prospective single‐arm trials on computer‐aided polyp diagnosis, but the evidence is insufficient to reach a conclusion.

Application of logistic regression and convolutional neural network in prediction and diagnosis of high-risk populations of lung cancer

OBJECTIVES

The early detection, early diagnosis, and early treatment of lung cancer are the best strategies to improve the 5-year survival rate. Logistic regression analysis can be a helpful tool in the early detection of high-risk groups of lung cancer. Convolutional neural network (CNN) could distinguish benign from malignant pulmonary nodules, which is critical for early precise diagnosis and treatment. Here, we developed a risk assessment model of lung cancer and a high-precision classification diagnostic model using these technologies so as to provide a basis for early screening of lung cancer and for intelligent differential diagnosis.

METHODS

A total of 355 lung cancer patients, 444 patients with benign lung disease and 472 healthy people from The First Affiliated Hospital of Zhengzhou University were included in this study. Moreover, the dataset of 607 lung computed tomography images was collected from the above patients. The logistic regression method was employed to screen the high-risk groups of lung cancer, and the CNN model was designed to classify pulmonary nodules into benign or malignant nodules.

RESULTS

The area under the curve of the lung cancer risk assessment model in the training set and the testing set were 0.823 and 0.710, respectively. After finely optimizing the settings of the CNN, the area under the curve could reach 0.984.

CONCLUSIONS

This performance demonstrated that the lung cancer risk assessment model could be used to screen for high-risk individuals with lung cancer and the CNN framework was suitable for the differential diagnosis of pulmonary nodules.

Effect of artificial intelligence-aided colonoscopy for adenoma and polyp detection: a meta-analysis of randomized clinical trials

BACKGROUND

This meta-analysis aimed to determine whether artificial intelligence (AI) improves colonoscopy outcome metrics i.e. adenoma detection rate (ADR) and polyp detection rate (PDR).

METHODS

Two authors independently searched Web of Science, PubMed, Science Direct, and Cochrane Library to find all published research before July 2021 that has compared AI-aided colonoscopy with routine colonoscopy (RC) for detection of adenoma and polyp.

RESULTS

This meta-analysis included 10 RCTs with 6629 individuals in AI-aided (n = 3300) and routine (n = 3329) groups. The results showed that both ADR (RR, 1.43; P < 0.001) and PDR (RR, 1.44; P < 0.001) using AI-aided endoscopy were significantly greater when compared with RC. The adenomas detected per colonoscopy (APC) (WMD, 0.25; P = 0.009), polyps detected per colonoscopy (PPC) (WMD, 0.52; P < 0.001), and sessile serrated lesions detected per colonoscopy (SSLPC) (RR, 1.53; P < 0.001) were significantly higher in the AI-aided group compared with the RC group. Subgroup analysis based on size, location, and shape of adenomas and polyps demonstrated that, except for in the cecum and pedunculated adenomas or polyps, the AI-aided groups of the other subgroups are more advantageous. Withdrawal time was longer in the AI-aided group when biopsies were included, while withdrawal time excluding biopsy time showed no significant difference.

CONCLUSIONS

AI-aided polyp detection system significantly increases lesion detection rate. In addition, lesion detection by AI is hardly affected by factors such as size, location, and shape.

Large polyps: Pearls for the referring and receiving endoscopist

Polyps are precursors to colorectal cancer, the third most common cancer in the United States. Large polyps, i.e.,, those with a size ≥ 20 mm, are more likely to harbor cancer. Colonic polyps can be removed through various techniques, with the goal to completely resect and prevent colorectal cancer; however, the management of large polyps can be relatively complex and challenging. Such polyps are generally more difficult to remove en bloc with conventional methods, and depending on level of expertise, may consequently be resected piecemeal, leading to an increased rate of incomplete removal and thus polyp recurrence. To effectively manage large polyps, endoscopists should be able to: (1) Evaluate the polyp for characteristics which predict high difficulty of resection or incomplete removal; (2) Determine the optimal resection technique (e.g., snare polypectomy, endoscopic mucosal resection, endoscopic submucosal dissection, etc.); and (3) Recognize when to refer to colleagues with greater expertise. This review covers important considerations in this regard for referring and receiving endoscopists and methods to best manage large colonic polyps.

PEACE: Perception and Expectations toward Artificial Intelligence in Capsule Endoscopy

Artificial intelligence (AI) has shown promising results in digestive endoscopy, especially in capsule endoscopy (CE). However, some physicians still have some difficulties and fear the advent of this technology. We aimed to evaluate the perceptions and current sentiments toward the use of AI in CE. An online survey questionnaire was sent to an audience of gastroenterologists. In addition, several European national leaders of the International CApsule endoscopy REsearch (I CARE) Group were asked to disseminate an online survey among their national communities of CE readers (CER). The survey included 32 questions regarding general information, perceptions of AI, and its use in daily life, medicine, endoscopy, and CE. Among 380 European gastroenterologists who answered this survey, 333 (88%) were CERs. The mean average time length of experience in CE reading was 9.9 years (0.5–22). A majority of CERs agreed that AI would positively impact CE, shorten CE reading time, and help standardize reporting in CE and characterize lesions seen in CE. Nevertheless, in the foreseeable future, a majority of CERs disagreed with the complete replacement all CE reading by AI. Most CERs believed in the high potential of AI for becoming a valuable tool for automated diagnosis and for shortening the reading time. Currently, the perception is that AI will not replace CE reading.

Enhancing polyp detection: technological advances in colonoscopy imaging

The detection and removal of polyps at colonoscopy is core to the current colorectal cancer (CRC) prevention strategy. However, colonoscopy is flawed with a well described miss rate and variability in detection rates associated with incomplete protection from CRC. Consequently, there is significant interest in techniques and technologies which increase polyp detection with the aim to remedy colonoscopy's ills. Technologic advances in colonoscope imaging are numerous and include; increased definition of imaging, widening field of view, virtual technologies to supplant conventional chromocolonoscopy (CC) and now computer assisted detection. However, despite nearly two decades of technologic advances, data on gains in detection from individual technologies have been modest at best and heterogenous and conflicted as a rule. This state of detection technology science is exacerbated by use of relatively blunt metrics of improvement without consensus, the myopic search for gains over single generations of technology improvement and an unhealthy focus on adenomatous lesions. Yet there remains cause for optimism as detection gains from new technology, while small, may still improve CRC prevention. The technologies are also readily available in current generation colonoscopes and have roles beyond simply detection such as lesion characterization, further improving their worth. Coupled with the imminent expansion of computer assisted detection the detection future from colonoscope imaging advances looks bright. This review aims to cover the major imaging advances and evidence for improvement in polyp detection.

Image-Enhanced Capsule Endoscopy Improves the Identification of Small Intestinal Lesions

Image-enhanced endoscopy is useful for diagnosing and identifying lesions in the gastrointestinal tract. Recently, image-enhanced endoscopy has become a breakthrough technology that has attracted significant attention. This image enhancing technology is available for capsule endoscopy, which is an effective tool for small intestinal lesions and has been applied in flexible spectral color enhancement technology and in contrast capsule like narrow-band imaging. In this field, most researchers focus on improving the visibility and detection of small intestinal lesions. This review summarizes previous studies on image-enhanced capsule endoscopy and aims to evaluate the efficacy of this technology.

EndoConf: real-time video consultation during endoscopy; telemedicine in endoscopy at its best

Background and study aims  The aim of this study was to introduce EndoConf, a reliable and easy-to-use tool capable of optimizing clinical care in endoscopy by reducing the number of repeat endoscopy procedures, providing continuous on-the-job clinical education, and allowing a smooth transition to the next level of artificial intelligence-supported systems. Patients and methods  We prospectively developed and improved a real-time conference system (EndoConf). EndoConf enables endoscopists to contact on-demand and in real time experienced endoscopists across other sites. After the initial introduction period, we registered all EndoConf-assisted procedures from our unit (Surgical Department of Odense University Hospital) over a 3-month period (Autumn of 2019). Results  Of 84 EndoConf-supported procedures, 58 were eligible for further analysis. Eventually, 38 calls were made, of which only four were technically of low quality (10.5 %) while three were not answered (7.9 %). Of the 35 (92.1 %) completed EndoConf calls; 24 were referred for endoscopic mucosal resection, six were referred for transanal microsurgery preceded by transrectal ultrasonography and three were referred for multidisciplinary conference, whereas in two cases, the lesion was resected during EndoConf. Conclusions  We found the EndoConf system to provide support that could reduce the number of unnecessary repeat endoscopic procedures while at the same time ensuring avoidance of any hazardous attempt at polypectomy.

Detection Accuracy and Latency of Colorectal Lesions with Computer-Aided Detection System Based on Low-Bias Evaluation

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for 69 colorectal lesions at the Jikei University Hospital between June 2017 and February 2018. First, we evaluated the diagnostic performances using still images randomly and automatically extracted from video recordings of the entire endoscopic procedure at intervals of 5 s, without eliminating poor quality images. Second, the latency of lesion detection by the CADe system from the initial appearance of lesions was investigated by reviewing the videos. A total of 6531 images, including 662 images with a lesion, were studied in the image-based analysis. The AUC, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.983, 94.6%, 95.2%, 68.8%, 99.4%, and 95.1%, respectively. The median time for detecting colorectal lesions measured in the lesion-based analysis was 0.67 s. In conclusion, we proved that the originally developed CADe system based on YOLO v3 could accurately and instantaneously detect colorectal lesions using the test dataset obtained from videos, mitigating operator selection biases.

Clinical practice standards for colonoscopy

Colonoscopy is considered as the most effective tool for preventing, screening, and diagnosing colorectal lesions. Effectiveness of colonoscopy was identified as a major priority, and it strictly depends on quality measures. Therefore, international guidelines were formulated on quality indicators for colonoscopy, aiming to reduce the rate of interval cancers related to missed lesions during colonoscopy. Quality indicators are divided into 3 time periods: preprocedure, intraprocedure, and postprocedure.  The main pre-procedural indicators are the assessment of the appropriateness of indication of colonoscopy and the prescription of adequate bowel preparation during a consultation prior to colonoscopy. Per-procedural criteria include all technical aspects of the procedure, which are "endoscopist-dependent" factors, particularly cecal intubation, detection of adenomas and withdrawal time. The main post-procedure indicators are the rate of complications, patient experience and optimal surveillance intervals following removal of colorectal polyps. The implementation of key performance measures in endoscopy practice is increasingly important as it can help improving our care of patients and optimize outcomes. In this review, the "Club d'endoscopie digestive" (CED) presented a summary of the main colonoscopy quality indicators, and suggested recommendations that took into account the particularities of our local conditions.

Benchmarking definitions of false-positive alerts during computer-aided polyp detection in colonoscopy

BACKGROUND

The occurrence of false-positive alerts is an important outcome measure in computer-aided colon polyp detection (CADe) studies. However, there is no consensus definition of a false positive in clinical trials evaluating CADe in colonoscopy. We aimed to study the diagnostic performance of CADe based on different threshold definitions for false-positive alerts.

METHODS

A previously validated CADe system was applied to screening/surveillance colonoscopy videos. Different thresholds for false-positive alerts were defined based on the time an alert box was continuously traced by the system. Primary outcomes were false-positive results and specificity using different threshold definitions of false positive.

RESULTS

62 colonoscopies were analyzed. CADe specificity and accuracy were 93.2 % and 97.8 %, respectively, for a threshold definition of ≥ 0.5 seconds, 98.6 % and 99.5 % for a threshold definition of ≥ 1 second, and 99.8 % and 99.9 % for a threshold definition of ≥ 2 seconds.

CONCLUSION

Our analysis demonstrated how different threshold definitions of false positive can impact the reported diagnostic performance of CADe for colon polyp detection.

Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method

BACKGROUND : Artificial intelligence (AI) research in colonoscopy is progressing rapidly but widespread clinical implementation is not yet a reality. We aimed to identify the top implementation research priorities. METHODS : An established modified Delphi approach for research priority setting was used. Fifteen international experts, including endoscopists and translational computer scientists/engineers, from nine countries participated in an online survey over 9 months. Questions related to AI implementation in colonoscopy were generated as a long-list in the first round, and then scored in two subsequent rounds to identify the top 10 research questions. RESULTS : The top 10 ranked questions were categorized into five themes. Theme 1: clinical trial design/end points (4 questions), related to optimum trial designs for polyp detection and characterization, determining the optimal end points for evaluation of AI, and demonstrating impact on interval cancer rates. Theme 2: technological developments (3 questions), including improving detection of more challenging and advanced lesions, reduction of false-positive rates, and minimizing latency. Theme 3: clinical adoption/integration (1 question), concerning the effective combination of detection and characterization into one workflow. Theme 4: data access/annotation (1 question), concerning more efficient or automated data annotation methods to reduce the burden on human experts. Theme 5: regulatory approval (1 question), related to making regulatory approval processes more efficient. CONCLUSIONS : This is the first reported international research priority setting exercise for AI in colonoscopy. The study findings should be used as a framework to guide future research with key stakeholders to accelerate the clinical implementation of AI in endoscopy.

Artificial intelligence and colonoscopy − enhancements and improvements

Artificial intelligence is a technology that processes and analyzes information with reproducibility and accuracy. Its application in medicine, especially in the field of gastroenterology, has great potential to facilitate in diagnosis of various disease states. Currently, the role of artificial intelligence as it pertains to colonoscopy revolves around enhanced polyp detection and characterization. The aim of this article is to review the current and potential future applications of artificial intelligence for enhanced quality of detection for colorectal neoplasia.

Early gastrointestinal cancer: The application of artificial intelligence

Early gastrointestinal (GI) cancer has been the core of clinical endoscopic work. Its early detection and treatment are tightly associated with patients’ prognoses. As a novel technology, artificial intelligence has been improved and applied in the field of endoscopy. Studies on detection, diagnosis, risk, and prognosis evaluation of diseases in the GI tract have been in development, including precancerous lesions, adenoma, early GI cancers, and advanced GI cancers. In this review, research on esophagus, stomach, and colon was concluded, and associated with the process from precancerous lesions to early GI cancer, such as from Barrett’s esophagus to early esophageal cancer, from dysplasia to early gastric cancer, and from adenoma to early colonic cancer. A status quo of research on early GI cancers and artificial intelligence was provided.

Establishment and validation of a computer-assisted colonic polyp localization system based on deep learning

BACKGROUND

Artificial intelligence in colonoscopy is an emerging field, and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas. Several deep learning-based computer-assisted detection (CADe) techniques were established from small single-center datasets, and unrepresentative learning materials might confine their application and generalization in wide practice. Although CADes have been reported to identify polyps in colonoscopic images and videos in real time, their diagnostic performance deserves to be further validated in clinical practice.

AIM

To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.

METHODS

With high-quality screening and labeling from 55 qualified colonoscopists, a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe. In addition, the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps. Finally, we conducted a self-controlled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.

RESULTS

The CADe was able to identify polyps in the test dataset with 95.0% sensitivity and 99.1% specificity. For colonoscopy videos, all 86 polyps were detected with 92.2% sensitivity and 93.6% specificity in frame-by-frame analysis. In the prospective validation, the sensitivity of CAD in identifying polyps was 98.4% (185/188). Folds, reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies. Colonoscopists can detect more polyps (0.90 vs 0.82, P < 0.001) and adenomas (0.32 vs 0.30, P = 0.045) with the aid of CADe, particularly polyps < 5 mm and flat polyps (0.65 vs 0.57, P < 0.001; 0.74 vs 0.67, P = 0.001, respectively). However, high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time (P = 0.32; P = 0.16, respectively).

CONCLUSION

CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas, and further confirmation is warranted.

Reducing adenoma miss rate of colonoscopy assisted by artificial intelligence: a multicenter randomized controlled trial

BACKGROUND

We have developed the computer-aided detection (CADe) system using an original deep learning algorithm based on a convolutional neural network for assisting endoscopists in detecting colorectal lesions during colonoscopy. The aim of this study was to clarify whether adenoma miss rate (AMR) could be reduced with CADe assistance during screening and surveillance colonoscopy.

METHODS

This study was a multicenter randomized controlled trial. Patients aged 40 to 80 years who were referred for colorectal screening or surveillance at four sites in Japan were randomly assigned at a 1:1 ratio to either the "standard colonoscopy (SC)-first group" or the "CADe-first group" to undergo a back-to-back tandem procedure. Tandem colonoscopies were performed on the same day for each participant by the same endoscopist in a preassigned order. All polyps detected in each pass were histopathologically diagnosed after biopsy or resection.

RESULTS

A total of 358 patients were enrolled and 179 patients were assigned to the SC-first group or CADe-first group. The AMR of the CADe-first group was significantly lower than that of the SC-first group (13.8% vs. 36.7%, P < 0.0001). Similar results were observed for the polyp miss rate (14.2% vs. 40.6%, P < 0.0001) and sessile serrated lesion miss rate (13.0% vs. 38.5%, P = 0.03). The adenoma detection rate of CADe-assisted colonoscopy was 64.5%, which was significantly higher than that of standard colonoscopy (53.6%; P = 0.036).

CONCLUSION

Our study results first showed a reduction in the AMR when assisting with CADe based on deep learning in a multicenter randomized controlled trial.

Use of a convolutional neural network for classifying microvessels of superficial esophageal squamous cell carcinomas

BACKGROUND AND AIM

The morphological diagnosis of microvessels on the surface of superficial esophageal squamous cell carcinomas using magnifying endoscopy with narrow-band imaging is widely used in clinical practice. Nevertheless, inconsistency, even among experts, remains a problem. We constructed a convolutional neural network-based computer-aided diagnosis system to classify the microvessels of superficial esophageal squamous cell carcinomas and evaluated its diagnostic performance.

METHODS

In this retrospective study, a cropped magnifying endoscopy with narrow-band images from superficial esophageal squamous cell carcinoma lesions was used as the dataset. All images were assessed by three experts, and classified into three classes, Type B1, B2, and B3, based on the Japan Esophagus Society classification. The dataset was divided into training and validation datasets. A convolutional neural network model (ResNeXt-101) was trained and tuned with the training dataset. To evaluate diagnostic accuracy, the validation dataset was assessed by the computer-aided diagnosis system and eight endoscopists.

RESULTS

In total, 1777 and 747 cropped images (total, 393 lesions) were included in the training and validation datasets, respectively. The diagnosis system took 20.3 s to evaluate the 747 images in the validation dataset. The microvessel classification accuracy of the computer-aided diagnosis system was 84.2%, which was higher than the average of the eight endoscopists (77.8%, P < 0.001). The area under the receiver operating characteristic curves for diagnosing Type B1, B2, and B3 vessels were 0.969, 0.948, and 0.973, respectively.

CONCLUSIONS

The computer-aided diagnosis system showed remarkable performance in the classification of microvessels on superficial esophageal squamous cell carcinomas.

Computer-Aided Detection False Positives in Colonoscopy

Randomized control trials and meta-analyses comparing colonoscopies with and without computer-aided detection (CADe) assistance showed significant increases in adenoma detection rates (ADRs) with CADe. A major limitation of CADe is its false positives (FPs), ranked 3rd in importance among 59 research questions in a modified Delphi consensus review. The definition of FPs varies. One commonly used definition defines an FP as an activation of the CADe system, irrespective of the number of frames or duration of time, not due to any polypoid or nonpolypoid lesions. Although only 0.07 to 0.2 FPs were observed per colonoscopy, video analysis studies using FPs as the primary outcome showed much higher numbers of 26 to 27 per colonoscopy. Most FPs were of short duration (91% < 0.5 s). A higher number of FPs was also associated with suboptimal bowel preparation. The appearance of FPs can lead to user fatigue. The polypectomy of FPs results in increased procedure time and added use of resources. Re-training the CADe algorithms is one way to reduce FPs but is not practical in the clinical setting during colonoscopy. Water exchange (WE) is an emerging method that the colonoscopist can use to provide salvage cleaning during insertion. We discuss the potential of WE for reducing FPs as well as the augmentation of ADRs through CADe.

Serrated polyps of the colon and rectum: a concise review

"Serrated polyps" is the term used for epithelial lesions of the colon and rectum that have a "sawtooth" pattern on the polyp's surface and crypt epithelium. The so-called serrated pathway describes the progression of sessile serrated adenomas and traditional serrated adenomas to colorectal cancer. Said pathway is well recognized as an alternative mechanism of carcinogenesis and accounts for 15-30% of the cases of colorectal cancer. It also explains a large number of the cases of interval colorectal cancer. Thus, due to their usually aggressive and uncertain behavior, serrated polyps are of the utmost importance in colorectal cancer screening. Our aim was to review the history, current nomenclature, pathophysiology, morphology, treatment, and surveillance of serrated polyps.

Real-time use of a computer-aided system for polyp detection during colonoscopy, an ambispective study

OBJECTIVE

This study aimed to evaluate ambispectively the effectiveness of a real-time computer-aided detection (CADe) system on the number of polyp (PPC) or adenoma per colonoscopy (APC), and polyp (PDR) or adenoma detection rate (ADR).

METHODS

Eight-five videos marked using the CADe system, together with the unmarked videos, were reviewed by two senior endoscopists. Polyps detected in the marked and unmarked videos were recounted in parallel. Additionally, 128 consecutive patients were enrolled for a prospective evaluation using a standard colonoscopy or the CADe monitor alternately every 2 weeks. The PC, APC, PDR and ADR were compared between the two groups.

RESULTS

The total number of polyps reported in the unmarked and marked videos were 73 and 88, respectively (mean PPC 0.86 vs 1.04, P = 0.001). The proportion of polyps detected per colonoscopy increased by 20.5%. Of the 128 prospectively enrolled patients, 186 polyps were detected. The mean PPC was higher in the CADe colonoscopy than in the standard colonoscopy (1.66 vs 1.13, P = 0.039). The PDR using the CADe colonoscopy was significantly higher than that of the standard colonoscopy (78.1% vs 56.3%, P = 0.008).

CONCLUSION

Real-time CADe system significantly increases the PDR and PPC under the situation of a high rate of polyp detection.

Colonoscopy and artificial intelligence: Bridging the gap or a gap needing to be bridged?

Research in artificial intelligence (AI) in gastroenterology has increased over the last decade. Colonoscopy represents the most widely published field with regards to its use in gastroenterology. Most studies to date center on polyp detection and characterization, as well as real-time evaluation of adequacy of mucosal exposure for inspection. This review article discusses how advances in AI has bridged certain gaps in colonoscopy. In addition, the gaps formed with the development of AI that currently prevent its routine use in colonoscopy will be explored.