Computer-aided Polyp Detection Research Articles

Evaluation of a real-time computer-aided polyp detection system during screening colonoscopy: AI-DETECT study.

Polyp detection and resection during colonoscopy significantly reduce long-term colorectal cancer risk. Computer-aided detection (CADe) may increase polyp identification but has undergone limited clinical evaluation. Our aim was to assess the effectiveness of CADe at colonoscopy within a bowel cancer screening program (BCSP). This prospective, randomized controlled trial involved all eight screening-accredited colonoscopists at an English National Health Service (NHS) BCSP center (February 2020 to December 2021). Patients were randomized to CADe or standard colonoscopy. Patients meeting NHS criteria for bowel cancer screening were included. The primary outcome of interest was polyp detection rate (PDR). 658 patients were invited and 44 were excluded. A total of 614 patients were randomized to CADe (n = 308) or standard colonoscopy (n = 306); 35 cases were excluded from the per-protocol analysis due to poor bowel preparation (n = 10), an incomplete procedure (n = 24), or a data issue (n = 1). Endocuff Vision was frequently used and evenly distributed (71.7 % CADe and 69.2 % standard). On intention-to-treat (ITT) analysis, there was a borderline significant difference in PDR (85.7 % vs. 79.7 %; P = 0.05) but no significant difference in adenoma detection rate (ADR; 71.4 % vs. 65.0 %; P = 0.09) for CADe vs. standard groups, respectively. On per-protocol analysis, no significant difference was observed in these rates. There was no significant difference in procedure times. In high-performing colonoscopists in a BCSP who routinely used Endocuff Vision, CADe improved PDR but not ADR. CADe appeared to have limited benefit in a BCSP setting where procedures are performed by experienced colonoscopists.

S625 Adenoma Detection Rate Using LCI vs White Light Colonoscopy Both With and Without the Use of Artificial Intelligence: A Prospective Study in a Non-Academic Center in Latin America

Introduction: The adenoma detection rate (ADR) is a strong predictor of cancer prevention. The use of artificial intelligence could increase the detection of colorectal polyps. The Computer-Aided Polyp Detection systems (CADe) have shown high accuracy in polyp detection when retrospectively applied to endoscopy videos or images, but their live performance is still under scrutiny. There are other ways in which technology has helped in performance and efficiency, Linked Color Imaging (LCI) is a modern image-enhancing technology, its use along with artificial intelligence could be another tool in the detection of precancerous lesions. Methods: A prospective observational study was conducted on 637 subjects undergoing screening colonoscopies, follow up colonoscopies, or work-up from a fecal occult blood test, from January 2021 through June 10th, 2022, in a nonacademic center in the Dominican Republic. Colonoscopies performed during 2021 did not use the CADe technology, while patients in 2022 were exposed to the CADe technology, in addition, each patient was alternatively assigned to either LCI or white light colonoscopy. Two endoscopists performed the procedures during these two years. The primary outcome evaluated was the ADR using LCI vs. white light colonoscopy both with and without the use of artificial intelligence. Secondary outcomes were polyp detection rate (PDR) and average withdrawal time. Results: The ADR in patients not exposed to CADe (2021) was 56.6%, while patients exposed to CADe (2022) presented an ADR of 54.5%. PDR in 2021 was 72.3%, and in 2022 the result was 70.6%. The average withdrawal time in 2021 was 13 minutes and 14 minutes in 2022. When it comes to the use of LCI and white light without the use of AI (2021), the ADR with LCI was 52%, while the use of white light colonoscopy resulted in an ADR of 50.9%. The ADR in patients exposed to LCI with AI (2022) was 61.1%, while patients exposed to white light with AI presented an ADR of 61%. Conclusion: The polyp and adenoma detection rates calculated were higher than the average considered for a high-quality colonoscopy both with and without the use of artificial intelligence. When it comes to the use of other technologies like LCI, ADR was higher with LCI when compared to white light colonoscopy, while the NNT was 90. When comparing the use of both technologies, there was still no significant difference. Further studies are still needed to assess these new technologies and their effect on colonoscopy and polyp detection.

PRAPNet: A Parallel Residual Atrous Pyramid Network for Polyp Segmentation.

In a colonoscopy, accurate computer-aided polyp detection and segmentation can help endoscopists to remove abnormal tissue. This reduces the chance of polyps developing into cancer, which is of great importance. In this paper, we propose a neural network (parallel residual atrous pyramid network or PRAPNet) based on a parallel residual atrous pyramid module for the segmentation of intestinal polyp detection. We made full use of the global contextual information of the different regions by the proposed parallel residual atrous pyramid module. The experimental results showed that our proposed global prior module could effectively achieve better segmentation results in the intestinal polyp segmentation task compared with the previously published results. The mean intersection over union and dice coefficient of the model in the Kvasir-SEG dataset were 90.4% and 94.2%, respectively. The experimental results outperformed the scores achieved by the seven classical segmentation network models (U-Net, U-Net++, ResUNet++, praNet, CaraNet, SFFormer-L, TransFuse-L).

A video based benchmark data set (ENDOTEST) to evaluate computer-aided polyp detection systems

Background and aims Computer-aided polyp detection (CADe) may become a standard for polyp detection during colonoscopy. Several systems are already commercially available. We report on a video-based benchmark technique for the first preclinical assessment of such systems before comparative randomized trials are to be undertaken. Additionally, we compare a commercially available CADe system with our newly developed one. Methods ENDOTEST consisted in the combination of two datasets. The validation dataset contained 48 video-snippets with 22,856 manually annotated images of which 53.2% contained polyps. The performance dataset contained 10 full-length screening colonoscopies with 230,898 manually annotated images of which 15.8% contained a polyp. Assessment parameters were accuracy for polyp detection and time delay to first polyp detection after polyp appearance (FDT). Two CADe systems were assessed: a commercial CADe system (GI-Genius, Medtronic), and a self-developed new system (ENDOMIND). The latter being a convolutional neuronal network trained on 194,983 manually labeled images extracted from colonoscopy videos recorded in mainly six different gastroenterologic practices. Results On the ENDOTEST, both CADe systems detected all polyps in at least one image. The per-frame sensitivity and specificity in full colonoscopies was 48.1% and 93.7%, respectively for GI-Genius; and 54% and 92.7%, respectively for ENDOMIND. Median FDT of ENDOMIND with 217 ms (Inter-Quartile Range(IQR)8–1533) was significantly faster than GI-Genius with 1050 ms (IQR 358–2767, p = 0.003). Conclusions Our benchmark ENDOTEST may be helpful for preclinical testing of new CADe devices. There seems to be a correlation between a shorter FDT with a higher sensitivity and a lower specificity for polyp detection.

Pilot study of a new freely available computer-aided polyp detection system in clinical practice

PurposeComputer-aided polyp detection (CADe) systems for colonoscopy are already presented to increase adenoma detection rate (ADR) in randomized clinical trials. Those commercially available closed systems often do not allow for data collection and algorithm optimization, for example regarding the usage of different endoscopy processors. Here, we present the first clinical experiences of a, for research purposes publicly available, CADe system.MethodsWe developed an end-to-end data acquisition and polyp detection system named EndoMind. Examiners of four centers utilizing four different endoscopy processors used EndoMind during their clinical routine. Detected polyps, ADR, time to first detection of a polyp (TFD), and system usability were evaluated (NCT05006092).ResultsDuring 41 colonoscopies, EndoMind detected 29 of 29 adenomas in 66 of 66 polyps resulting in an ADR of 41.5%. Median TFD was 130 ms (95%-CI, 80–200 ms) while maintaining a median false positive rate of 2.2% (95%-CI, 1.7–2.8%). The four participating centers rated the system using the System Usability Scale with a median of 96.3 (95%-CI, 70–100).ConclusionEndoMind’s ability to acquire data, detect polyps in real-time, and high usability score indicate substantial practical value for research and clinical practice. Still, clinical benefit, measured by ADR, has to be determined in a prospective randomized controlled trial.

Artificial intelligence for disease diagnosis: the criterion standard challenge

Artificial intelligence for disease diagnosis: the criterion standard challenge

Strengths and Weaknesses of an Artificial Intelligence Polyp Detection Program as Assessed by a High-Detecting Endoscopist

Strengths and Weaknesses of an Artificial Intelligence Polyp Detection Program as Assessed by a High-Detecting Endoscopist

The influence of computer-aided polyp detection systems on reaction time for polyp detection and eye gaze.

Background Multiple computer-aided systems for polyp detection (CADe) have been introduced into clinical practice, with an unclear effect on examiner behavior. This study aimed to measure the influence of a CADe system on reaction time, mucosa misinterpretation, and changes in visual gaze pattern. Methods Participants with variable levels of colonoscopy experience viewed video sequences (n = 29) while eye movement was tracked. Using a crossover design, videos were presented in two assessments, with and without CADe support. Reaction time for polyp detection and eye-tracking metrics were evaluated. Results 21 participants performed 1218 experiments. CADe was significantly faster in detecting polyps compared with participants (median 1.16 seconds [99 %CI 0.40–3.43] vs. 2.97 seconds [99 %CI 2.53–3.77], respectively). However, the reaction time of participants when using CADe (median 2.90 seconds [99 %CI 2.55–3.38]) was similar to that without CADe. CADe increased misinterpretation of normal mucosa and reduced the eye travel distance. Conclusions Results confirm that CADe systems detect polyps faster than humans. However, use of CADe did not improve human reaction times. It increased misinterpretation of normal mucosa and decreased the eye travel distance. Possible consequences of these findings might be prolonged examination time and deskilling.

Discovering the first US FDA-approved computer-aided polyp detection system.

Colorectal cancer is the third most common cancer worldwide. Because of the slow progression of the precancerous precursors, an efficient endoscopic surveillance strategy may be expected. It seems that around one-fourth of colorectal malignancies are still missed during colonoscopy. Several endoscopic technologies have been introduced, without radical changes. Interest in the development of artificial intelligence applications in the medical field has grown in the past decade. Artificial intelligence can help to highlight a specific region of interest that needs closer examination for the identification of polyps. The aim of this review is to report the first clinical experiences with the first US FDA-approved, real-time, deep-learning, computer-aided detection system (GI Genius™, Medtronic).

Can Real-time Computer-Aided Detection Systems Diminish the Risk of Postcolonoscopy Colorectal Cancer?

The adenoma detection rate is the constant subject of research and the main marker of quality in bowel cancer screening. However, by improving the quality of endoscopy via artificial intelligence methods, all polyps, including those with the potential for malignancy, can be removed, thereby reducing interval colorectal cancer rates. As such, the removal of all polyps may become the best marker of endoscopy quality. Thus, we present a viewpoint on integrating the computer-aided detection (CADe) of polyps with high-accuracy, real-time colonoscopy to challenge quality improvements in the performance of colonoscopy. Colonoscopy for bowel cancer screening involving the integration of a deep learning methodology (ie, integrating artificial intelligence with CADe systems) has been assessed in an effort to increase the adenoma detection rate. In this viewpoint, a few studies are described, and their results show that CADe systems are able to increase screening sensitivity. The detection of adenomatous polyps, which are associated with a potential risk of progression to colorectal cancer, and their removal are expected to reduce cancer incidence and mortality rates. However, so far, artificial intelligence methods do not increase the detection of cancer or large adenomatous polyps but contribute to the detection of small precancerous polyps.

Deep Learning Computer-aided Polyp Detection Reduces Adenoma Miss Rate: A United States Multi-center Randomized Tandem Colonoscopy Study (CADeT-CS Trial)

Artificial intelligence-based computer-aided polyp detection (CADe) systems are intended to address the issue of missed polyps during colonoscopy. The effect of CADe during screening and surveillance colonoscopy has not previously been studied in a United States (U.S.) population. We conducted a prospective, multi-center, single-blind randomized tandem colonoscopy study to evaluate a deep-learning based CADe system (EndoScreener, Shanghai Wision AI, China). Patients were enrolled across 4 U.S. academic medical centers from 2019 through 2020. Patients presenting for colorectal cancer screening or surveillance were randomized to CADe colonoscopy first or high-definition white light (HDWL) colonoscopy first, followed immediately by the other procedure in tandem fashion by the same endoscopist. The primary outcome was adenoma miss rate (AMR), and secondary outcomes included sessile serrated lesion (SSL) miss rate and adenomas per colonoscopy (APC). A total of 232 patients entered the study, with 116 patients randomized to undergo CADe colonoscopy first and 116 patients randomized to undergo HDWL colonoscopy first. After the exclusion of 9 patients, the study cohort included 223 patients. AMR was lower in the CADe-first group compared with the HDWL-first group (20.12% [34/169] vs 31.25% [45/144]; odds ratio [OR], 1.8048; 95% confidence interval [CI], 1.0780-3.0217; P= .0247). SSL miss rate was lower in the CADe-first group (7.14% [1/14]) vs the HDWL-first group (42.11% [8/19]; P= .0482). First-pass APC was higher in the CADe-first group (1.19 [standard deviation (SD), 2.03] vs 0.90 [SD, 1.55]; P= .0323). First-pass ADR was 50.44% in the CADe-first group and 43.64 % in the HDWL-first group (P= .3091). In this U.S. multicenter tandem colonoscopy randomized controlled trial, we demonstrate a decrease in AMR and SSL miss rate and an increase in first-pass APC with the use of a CADe-system when compared with HDWL colonoscopy alone.

Author commentary on Erik A. Holzwanger et al.

Erik A. Holzwanger et al. Benchmarking definitions of false-positive alerts during computer-aided polyp detection in colonoscopy

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

Differential diagnosis of neoplasms and non-neoplasms is crucial in ensuring appropriate and proper medical management for patients undergoing colonoscopy. Diagnostic ability can vary, depending on the colonoscopist's experience. To overcome this issue, artificial intelligence (AI) may be effective. To assess the performance of a computer-aided detection (CADe) and a computer-aided diagnosis (CADx) system for the detection and characterization of colorectal polyps by comparing their data with those of experienced endoscopists. This retrospective, still image-based validation study was conducted at three Japanese medical centers. A total of 579 white-light images (WLIs) and 605 linked color images (LCIs) were used for testing the CADe and 308 WLIs and 296 blue laser/light images (BLIs) for testing the CADx. The performances of the CADe and CADx systems were assessed and compared with the correct answers provided by three experienced endoscopists. CADe in WLI demonstrated a sensitivity of 94.5% (95% confidence interval (CI), 92.0-96.9%) and a specificity of 87.2% (84.5-89.9%). CADe in LCI demonstrated a sensitivity of 96.0% (93.9-98.1%) and a specificity of 85.1% (82.3-87.9%). CADx in WLI demonstrated a sensitivity of 95.5% (92.9-98.1%) and a specificity of 84.4% (73.4-91.5%), resulting in an accuracy of 93.2% (90.4-96.0%). CADx in BLI showed a sensitivity of 96.3% (93.9-98.7%) and a specificity of 88.7% (77.1-95.1%), resulting in an accuracy of 94.9% (92.4-97.4%). CADe and CADx demonstrated sufficient diagnostic performance to support the use of an AI system.

Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations.

Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.

Application of artificial intelligence-driven endoscopic screening and diagnosis of gastric cancer.

The landscape of gastrointestinal endoscopy continues to evolve as new technologies and techniques become available. The advent of image-enhanced and magnifying endoscopies has highlighted the step toward perfecting endoscopic screening and diagnosis of gastric lesions. Simultaneously, with the development of convolutional neural network, artificial intelligence (AI) has made unprecedented breakthroughs in medical imaging, including the ongoing trials of computer-aided detection of colorectal polyps and gastrointestinal bleeding. In the past demi-decade, applications of AI systems in gastric cancer have also emerged. With AI’s efficient computational power and learning capacities, endoscopists can improve their diagnostic accuracies and avoid the missing or mischaracterization of gastric neoplastic changes. So far, several AI systems that incorporated both traditional and novel endoscopy technologies have been developed for various purposes, with most systems achieving an accuracy of more than 80%. However, their feasibility, effectiveness, and safety in clinical practice remain to be seen as there have been no clinical trials yet. Nonetheless, AI-assisted endoscopies shed light on more accurate and sensitive ways for early detection, treatment guidance and prognosis prediction of gastric lesions. This review summarizes the current status of various AI applications in gastric cancer and pinpoints directions for future research and clinical practice implementation from a clinical perspective.

Computer-aided detection of colorectal polyps using a newly generated deep convolutional neural network: from development to first clinical experience.

AimThe use of artificial intelligence represents an objective approach to increase endoscopist’s adenoma detection rate (ADR) and limit interoperator variability. In this study, we evaluated a newly developed deep convolutional neural network (DCNN) for automated detection of colorectal polyps ex vivo as well as in a first in-human trial.MethodsFor training of the DCNN, 116 529 colonoscopy images from 278 patients with 788 different polyps were collected. A subset of 10 467 images containing 504 different polyps were manually annotated and treated as the gold standard. An independent set of 45 videos consisting of 15 534 single frames was used for ex vivo performance testing. In vivo real-time detection of colorectal polyps during routine colonoscopy by the DCNN was tested in 42 patients in a back-to-back approach.ResultsWhen analyzing the test set of 15 534 single frames, the DCNN’s sensitivity and specificity for polyp detection and localization within the frame was 90% and 80%, respectively, with an area under the curve of 0.92. In vivo, baseline polyp detection rate and ADR were 38% and 26% and significantly increased to 50% (P = 0.023) and 36% (P = 0.044), respectively, with the use of the DCNN. Of the 13 additionally with the DCNN detected lesions, the majority were diminutive and flat, among them three sessile serrated adenomas.ConclusionThis newly developed DCNN enables highly sensitive automated detection of colorectal polyps both ex vivo and during first in-human clinical testing and could potentially increase the detection of colorectal polyps during colonoscopy.

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

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

WCE polyp detection with triplet based embeddings

Wireless capsule endoscopy is a medical procedure used to visualize the entire gastrointestinal tract and to diagnose intestinal conditions, such as polyps or bleeding. Current analyses are performed by manually inspecting nearly each one of the frames of the video, a tedious and error-prone task. Automatic image analysis methods can be used to reduce the time needed for physicians to evaluate a capsule endoscopy video. However these methods are still in a research phase.In this paper we focus on computer-aided polyp detection in capsule endoscopy images. This is a challenging problem because of the diversity of polyp appearance, the imbalanced dataset structure and the scarcity of data. We have developed a new polyp computer-aided decision system that combines a deep convolutional neural network and metric learning. The key point of the method is the use of the Triplet Loss function with the aim of improving feature extraction from the images when having small dataset. The Triplet Loss function allows to train robust detectors by forcing images from the same category to be represented by similar embedding vectors while ensuring that images from different categories are represented by dissimilar vectors. Empirical results show a meaningful increase of AUC values compared to state-of-the-art methods.A good performance is not the only requirement when considering the adoption of this technology to clinical practice. Trust and explainability of decisions are as important as performance. With this purpose, we also provide a method to generate visual explanations of the outcome of our polyp detector. These explanations can be used to build a physician's trust in the system and also to convey information about the inner working of the method to the designer for debugging purposes.

S0338 Is Artificial Intelligence for Colonoscopy Ready for Prime-Time: A Systematic Review and Meta-Analysis of Randomized Controlled Trials

INTRODUCTION: Colonoscopy is the best tool for to screen for colorectal cancer. Adenoma detection rate (ADR) is the main quality control indicator for colonoscopy. An improvement in ADR translates into a reduction in the number of index and interval colorectal cancers. Computer-aided polyp detection (CADe) can improve ADR but the impact of real-time CADe on colonoscopy metrics has not been rigorously studied. We aim to conduct a systematic review with meta-analysis of randomized controlled trials (RCTs) to evaluate the efficacy of CADe to detect colorectal neoplasia. METHODS: Electronic databases (Pubmed Central, OVID Medline, Embase, EBM Reviews Cochrane Central Register of Controlled Trials) were interrogated from inception until May 2020 for RCTs that compared real-time CADe with standard colonoscopy (E). Data was reviewed separately by two authors. Adult patients undergoing diagnostic and screening colonoscopies were included. Primary outcomes were polyp detection rate (PDR) and ADR. Secondary outcomes were total number of polyps detected, pooled ADR and withdrawal time. A random effects model was used to estimate mean differences (MD), odds ratios (OR) and rate ratios (RR) with 95% confidence intervals (95% CI). Heterogeneity was assessed with I2 statistic, with >50% considered substantial. RESULTS: The search yielded 923 results. 6 studies met inclusion criteria. Controls included a sham system and colonoscopies without AI. The total number of subjects included in all studies were 5214. The mean age of patients was 49.49 years, and 47.55 % of the subjects were female. The mean BPPS in the CADe group was 6.7 (95% CI 6.61,6.8), similar to that in the E group. The pooled ADR for colonoscopy with CAD was 33%, and the pooled ADR for colonoscopy alone was 22.8%. Both, ADR and PDR were higher with CADe, OR 1.54 (95% CI 1.23–1.94) and OR 1.49 (95% CI 1.24–1.80), I2 = 0 for both. Number of polyps detected was also higher with CADe, OR 2.42 (95% CI 2.12–2.76), I2 = 0. Withdrawal time was significantly longer (by less than a minute) in the CADe group, MD of 0.74 (95% CI). CONCLUSION: Automatic polyp detection systems resulted in improved polyp and adenoma detection rates, but with increased withdrawal times, compared to standard colonoscopy. CADe use was associated with a significantly higher adenoma detection rate (ADR; 34% vs. 23%). CADe and standard colonoscopies had comparable detection rates of polyps 5–10 mm in size, but CADe had higher ADRs for diminutive polyps, and for polyps greater than 10 mm.Table 1.: Secondary Outcomes.Figure 1.: Adenoma Detection Rate: Higher in Computer-Aided Diagnosis group with an Odds Ratio of 1.54 (95% CI 1.23–1.94), I-squared = 0.00.Figure 2.: Polyp Detection Rate: Higher in Computer-Aided Diagnosis group with an Odds Ratio of 1.49 (95% CI 1.24–1.80), I-squared = 0.00.

Training a computer-aided polyp detection system to detect sessile serrated adenomas using public domain colonoscopy videos

Background Colorectal cancer (CRC) is a major public health burden worldwide, and colonoscopy is the most commonly used CRC screening tool. Still, there is variability in adenoma detection rate (ADR) among endoscopists. Recent studies have reported improved ADR using deep learning models trained on videos curated largely from private in-house datasets. Few have focused on the detection of sessile serrated adenomas (SSAs), which are the most challenging target clinically. Methods We identified 23 colonoscopy videos available in the public domain and for which pathology data were provided, totaling 390 minutes of footage. Expert endoscopists annotated segments of video with adenomatous polyps, from which we captured 509 polyp-positive and 6,875 polyp-free frames. Via data augmentation, we generated 15,270 adenomatous polyp-positive images, of which 2,310 were SSAs, and 20,625 polyp-negative images. We used the CNN AlexNet and fine-tuned its parameters using 90 % of the images, before testing its performance on the remaining 10 % of images unseen by the model. Results We trained the model on 32,305 images and tested performance on 3,590 images with the same proportion of SSA, non-SSA polyp-positive, and polyp-negative images. The overall accuracy of the model was 0.86, with a sensitivity of 0.73 and a specificity of 0.96. Positive predictive value was 0.93 and negative predictive value was 0.96. The area under the curve was 0.94. SSAs were detected in 93 % of SSA-positive images. Conclusions Using a relatively small set of publicly-available colonoscopy data, we obtained sizable training and validation sets of endoscopic images using data augmentation, and achieved an excellent performance in adenomatous polyp detection.