A novel AI device for real-time optical characterization of colorectal polyps

Assessing clinical efficacy of polyp detection models using open-access datasets

Background

Ensuring accurate polyp detection during colonoscopy is essential for preventing colorectal cancer (CRC). Recent advances in deep learning-based computer-aided detection (CADe) systems have shown promise in enhancing endoscopists' performances. Effective CADe systems must achieve high polyp detection rates from the initial seconds of polyp appearance while maintaining low false positive (FP) detection rates throughout the procedure.

Method

We integrated four open-access datasets into a unified platform containing over 340,000 images from various centers, including 380 annotated polyps, with distinct data splits for comprehensive model development and benchmarking. The REAL-Colon dataset, comprising 60 full-procedure colonoscopy videos from six centers, is used as the fifth dataset of the platform to simulate clinical conditions for model evaluation on unseen center data. Performance assessment includes traditional object detection metrics and new metrics that better meet clinical needs. Specifically, by defining detection events as sequences of consecutive detections, we compute per-polyp recall at early detection stages and average per-patient FPs, enabling the generation of Free-Response Receiver Operating Characteristic (FROC) curves.

Results

Using YOLOv7, we trained and tested several models across the proposed data splits, showcasing the robustness of our open-access platform for CADe system development and benchmarking. The introduction of new metrics allows for the optimization of CADe operational parameters based on clinically relevant criteria, such as per-patient FPs and early polyp detection. Our findings also reveal that omitting full-procedure videos leads to non-realistic assessments and that detecting small polyp bounding boxes poses the greatest challenge.

Conclusion

This study demonstrates how newly available open-access data supports ongoing research progress in environments that closely mimic clinical settings. The introduced metrics and FROC curves illustrate CADe clinical efficacy and can aid in tuning CADe hyperparameters.

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

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

Appropriate trust in artificial intelligence for the optical diagnosis of colorectal polyps: The role of human/artificial intelligence interaction

BACKGROUND AND AIMS

Computer-aided diagnosis (CADx) for the optical diagnosis of colorectal polyps is thoroughly investigated. However, studies on human-artificial intelligence interaction are lacking. Our aim was to investigate endoscopists' trust in CADx by evaluating whether communicating a calibrated algorithm confidence score improved trust.

METHODS

Endoscopists optically diagnosed 60 colorectal polyps. Initially, endoscopists diagnosed the polyps without CADx assistance (initial diagnosis). Immediately afterward, the same polyp was again shown with a CADx prediction: either only a prediction (benign or premalignant) or a prediction accompanied by a calibrated confidence score (0-100). A confidence score of 0 indicated a benign prediction, 100 a (pre)malignant prediction. In half of the polyps, CADx was mandatory, and for the other half, CADx was optional. After reviewing the CADx prediction, endoscopists made a final diagnosis. Histopathology was used as the gold standard. Endoscopists' trust in CADx was measured as CADx prediction utilization: the willingness to follow CADx predictions when the endoscopists initially disagreed with the CADx prediction.

RESULTS

Twenty-three endoscopists participated. Presenting CADx predictions increased the endoscopists' diagnostic accuracy (69.3% initial vs 76.6% final diagnosis, P < .001). The CADx prediction was used in 36.5% (n = 183 of 501) disagreements. Adding a confidence score led to lower CADx prediction utilization, except when the confidence score surpassed 60. Mandatory CADx decreased CADx prediction utilization compared to optional CADx. Appropriate trust-using correct or disregarding incorrect CADx predictions-was 48.7% (n = 244 of 501).

CONCLUSIONS

Appropriate trust was common, and CADx prediction utilization was highest for the optional CADx without confidence scores. These results express the importance of a better understanding of human-artificial intelligence interaction.

REAL-Colon: A dataset for developing real-world AI applications in colonoscopy

Detection and diagnosis of colon polyps are key to preventing colorectal cancer. Recent evidence suggests that AI-based computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems can enhance endoscopists' performance and boost colonoscopy effectiveness. However, most available public datasets primarily consist of still images or video clips, often at a down-sampled resolution, and do not accurately represent real-world colonoscopy procedures. We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset: a compilation of 2.7 M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers. The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists. Comprehensive patient clinical data, colonoscopy acquisition information, and polyp histopathological information are also included in each video. With its unprecedented size, quality, and heterogeneity, the REAL-Colon dataset is a unique resource for researchers and developers aiming to advance AI research in colonoscopy. Its openness and transparency facilitate rigorous and reproducible research, fostering the development and benchmarking of more accurate and reliable colonoscopy-related algorithms and models.

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

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

Computer-aided diagnosis improves characterization of Barrett's neoplasia by general endoscopists (with video)

BACKGROUND AND AIMS

Characterization of visible abnormalities in patients with Barrett's esophagus (BE) can be challenging, especially for inexperienced endoscopists. This results in suboptimal diagnostic accuracy and poor interobserver agreement. Computer-aided diagnosis (CADx) systems may assist endoscopists. We aimed to develop, validate, and benchmark a CADx system for BE neoplasia.

METHODS

The CADx system received pretraining with ImageNet and then consecutive domain-specific pretraining with GastroNet, which includes 5 million endoscopic images. It was subsequently trained and internally validated using 1758 narrow-band imaging (NBI) images of early BE neoplasia (352 patients) and 1838 NBI images of nondysplastic BE (173 patients) from 8 international centers. CADx was tested prospectively on corresponding image and video test sets with 30 cases (20 patients) of BE neoplasia and 60 cases (31 patients) of nondysplastic BE. The test set was benchmarked by 44 general endoscopists in 2 phases (phase 1, no CADx assistance; phase 2, with CADx assistance). Ten international BE experts provided additional benchmark performance.

RESULTS

Stand-alone sensitivity and specificity of the CADx system were 100% and 98% for images and 93% and 96% for videos, respectively. CADx outperformed general endoscopists without CADx assistance in terms of sensitivity (P = .04). Sensitivity and specificity of general endoscopists increased from 84% to 96% and 90% to 98% with CAD assistance (P < .001). CADx assistance increased endoscopists' confidence in characterization (P < .001). CADx performance was similar to that of the BE experts.

CONCLUSIONS

CADx assistance significantly increased characterization performance of BE neoplasia by general endoscopists to the level of expert endoscopists. The use of this CADx system may thereby improve daily Barrett surveillance.

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.

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

OBJECTIVES

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

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.

Polyp characterization using deep learning and a publicly accessible polyp video database

OBJECTIVES

Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow-band imaging (NBI) and NBI-near focus (NBI-NF) and created a publicly accessible polyp video database.

METHODS

We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test-sets. Test-set I consists of 14,320 frames (157 polyps, 111 diminutive). Test-set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists.

RESULTS

Sensitivity for adenoma characterization was 91.6% in test-set I and 89.7% in test-set II. Specificity was 91.9% and 88.5%. Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI-NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)-1 and PIVI-2 thresholds for each test-set. In the benchmarking of test-set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2-23.6], P = 0.01) with no significant difference with experts.

CONCLUSIONS

A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI-NF. A publicly accessible NBI polyp video database was created and benchmarked.

The digital transformation of surgery

Rapid advances in digital technology and artificial intelligence in recent years have already begun to transform many industries, and are beginning to make headway into healthcare. There is tremendous potential for new digital technologies to improve the care of surgical patients. In this piece, we highlight work being done to advance surgical care using machine learning, computer vision, wearable devices, remote patient monitoring, and virtual and augmented reality. We describe ways these technologies can be used to improve the practice of surgery, and discuss opportunities and challenges to their widespread adoption and use in operating rooms and at the bedside.

Unlocking quality in endoscopic mucosal resection

A review of the development of the key performance metrics of endoscopic mucosal resection (EMR), learning from the experience of the establishment of widespread colonoscopy quality measurements. Potential future performance markers for both colonoscopy and EMR are also evaluated to ensure continued high quality performance is maintained with a focus service framework and predictors of patient outcome.

A Review of the Technology, Training, and Assessment Methods for the First Real-Time AI-Enhanced Medical Device for Endoscopy

Artificial intelligence (AI) has the potential to assist in endoscopy and improve decision making, particularly in situations where humans may make inconsistent judgments. The performance assessment of the medical devices operating in this context is a complex combination of bench tests, randomized controlled trials, and studies on the interaction between physicians and AI. We review the scientific evidence published about GI Genius, the first AI-powered medical device for colonoscopy to enter the market, and the device that is most widely tested by the scientific community. We provide an overview of its technical architecture, AI training and testing strategies, and regulatory path. In addition, we discuss the strengths and limitations of the current platform and its potential impact on clinical practice. The details of the algorithm architecture and the data that were used to train the AI device have been disclosed to the scientific community in the pursuit of a transparent AI. Overall, the first AI-enabled medical device for real-time video analysis represents a significant advancement in the use of AI for endoscopies and has the potential to improve the accuracy and efficiency of colonoscopy procedures.

Detection of Colorectal Polyps from Colonoscopy Using Machine Learning: A Survey on Modern Techniques

Given the increased interest in utilizing artificial intelligence as an assistive tool in the medical sector, colorectal polyp detection and classification using deep learning techniques has been an active area of research in recent years. The motivation for researching this topic is that physicians miss polyps from time to time due to fatigue and lack of experience carrying out the procedure. Unidentified polyps can cause further complications and ultimately lead to colorectal cancer (CRC), one of the leading causes of cancer mortality. Although various techniques have been presented recently, several key issues, such as the lack of enough training data, white light reflection, and blur affect the performance of such methods. This paper presents a survey on recently proposed methods for detecting polyps from colonoscopy. The survey covers benchmark dataset analysis, evaluation metrics, common challenges, standard methods of building polyp detectors and a review of the latest work in the literature. We conclude this paper by providing a precise analysis of the gaps and trends discovered in the reviewed literature for future work.

Experimental evidence of effective human-AI collaboration in medical decision-making

Artificial Intelligence (AI) systems are precious support for decision-making, with many applications also in the medical domain. The interaction between MDs and AI enjoys a renewed interest following the increased possibilities of deep learning devices. However, we still have limited evidence-based knowledge of the context, design, and psychological mechanisms that craft an optimal human-AI collaboration. In this multicentric study, 21 endoscopists reviewed 504 videos of lesions prospectively acquired from real colonoscopies. They were asked to provide an optical diagnosis with and without the assistance of an AI support system. Endoscopists were influenced by AI ([Formula: see text]), but not erratically: they followed the AI advice more when it was correct ([Formula: see text]) than incorrect ([Formula: see text]). Endoscopists achieved this outcome through a weighted integration of their and the AI opinions, considering the case-by-case estimations of the two reliabilities. This Bayesian-like rational behavior allowed the human-AI hybrid team to outperform both agents taken alone. We discuss the features of the human-AI interaction that determined this favorable outcome.