Introduction

Colonoscopy is the "gold-standard" technique for early diagnosis and resection of colorectal cancer precursor lesions. However, this technique has limitations, and can result in missed adenomas and polyps.
In recent years, artificial intelligence (AI) systems have been developed for the automatic detection of polyps. This study aims to investigate the impact of an AI system applied in real time on the detection rate, compared with conventional detection by the endoscopist.

Aims & Methods

A prospective observational study was carried out by seven gastroenterologists in the Digestive Endoscopy Unit of a tertiary hospital. Colonoscopies were performed on consecutive patients for polyp screening or surveillance. High-definition colonoscopes were used for the examinations and an AI system was applied in real time.
Each procedure consisted of two phases: (1) an initial assessment was performed by the endoscopist who withdrew the endoscope after reaching the cecum, identifying all visualized lesions without resecting them, and (2) the colonoscope was reintroduced up to the cecal pole with an AI device. The automatic detection of the AI device was assessed by means of a light and sound signal.
The primary objective was to compare the detection rate of adenomas and polyps. Secondary objectives were to compare the total number of polyps and serrated lesions detected, as well as detection of polyps by size, location and morphology, with and without the device.

Results

The sixty-six patients included in the analysis were examined simultaneously by colonoscopy, and the AI device was applied. The AI system identified a greater mean number of adenomas (2.85 vs 2.41, p<0.05) and polyps (3.68 vs 2.92, p<0.05), as well as a greater number of serrated lesions (0.83 vs 0.52, p <0.05), compared with the endoscopist. No significant differences were found in the adenoma detection rate (78.8% vs 75.7%; p > 0.05).
AI significantly increased the detection of small lesions (178 vs 135, p<0.001), and those of Paris type IIa flat morphology (165 vs 123, p<0.001). There were no differences in the detection of lesions larger than 5 mm or with other morphologies.

Conclusion

In a high-risk population, the application of an AI system allowed a significantly higher number of polyps and adenomatous lesions to be detected, at the expense of small lesions and those with flat morphology, compared with conventional evaluation by the endoscopist. There were no differences in the adenoma detection rate.

Introduction

Artificial Intelligence (AI)-powered Computer-aided diagnosis (CADx) systems provide real-time polyp histology prediction during colonoscopy, potentially improving accuracy in clinical decision-making. We aimed to assess CADx performance and its impact on endoscopist optical diagnosis for sessile serrated polyps (SSPs), traditional serrated adenomas (TSAs), adenomas with advanced histology, and cancers in a pragmatic implementation study.

Aims & Methods

We performed a secondary analysis of a large prospective cohort comprising patients undergoing diagnostic, screening, and surveillance colonoscopies. All patients and polyps with SSPs, TSAs, advanced adenomas and/or cancers detected, and prospectively documented CADx assisted or CADx unassisted optical diagnoses were included in the study. The primary outcome was the sensitivity of CADx assisted and unassisted optical diagnoses for SSP identification. Secondary outcomes included sensitivity for TSA, advanced adenoma, and cancer identification as well as the impact of CADx output on endoscopists’ optical diagnoses.

Results

Within a cohort of 2622 patients with 2456 eligible polyps there were 140 (5.7%) SSPs, 22 (0.9%) TSAs, 213 (8.7%) advanced adenomas, and 13 (0.5%) cancers. Sensitivity for SSP identification of CADx assisted and unassisted optical diagnosis was 53.2% (95% CI 42.3-63.8) and 37.8% (95% CI 24.1-53.9) respectively; p=0.12. In CADx assisted cases, endoscopists correctly identified SSPs more frequently when CADx classified these as non-neoplastic (56/79 cases) compared to neoplastic (23/79 cases), (66.1% [95% CI 53.0-77.1] vs 21.7% [95% CI 9.6-41.9]; p=0.0003). Sensitivity for TSA identification as neoplastic by CADx output was 61.6% (8/13), but CADx assisted and unassisted endoscopist optical diagnosis performed similarly, identifying TSAs as neoplastic in 83.3% and 66.7% of cases respectively; p=0.61. Sensitivity for advanced adenoma identification as adenoma/neoplastic did not differ between CADx assisted and unassisted cases (Table 1). Sensitivity for optical diagnosis of cancer was 50.0% and 42.9% for CADx assisted and unassisted optical diagnosis, with 3/6 and 4/7 of cancers misdiagnosed as adenomas, respectively.

Table 1. Diagnostic performance of CADx assisted and unassisted optical diagnosis

Conclusion

In our study, CADx use did neither harm nor improve optical diagnostic performance in polyps with SSP, TSA, advanced adenoma, or cancerous histology. Sensitivity for identification of these lesions trended universally higher with CADx assisted optical diagnosis, though statistical significance was not achieved at the present sample size. Whilst both CADx assisted and unassisted optical diagnosis reliably identified advanced adenomas as adenomas, optical diagnosis sensitivity to recognize SSPs and cancerous lesions was low.

Disclosure

Daniel von Renteln has received research funding from ERBE Elektromedizin GmbH, Ventage, Pendopharm, Fujifilm, and Pentax, and has received consultant or speaker fees from Boston Scientific Inc., ERBE Elektromedizin GmbH, and Pendopharm. The remaining authors declare that they have no conflict of interest.

Introduction

Computer-aided detection (CADe) system increases the efficiency of adenoma detection during colonoscopy, which is expected to reduce the incidence of colorectal cancer as well as cancer treatment-associated medical costs. However, most lesions detected using CADe have been reported to be diminutive adenomas that may not affect patient prognosis. Additionally, CADe may impose an immediate economic burden because the system needs to be purchased. Consequently, the use of CADe for all colonoscopy procedures seems impractical. This study aimed to evaluate the usefulness of CADe in patients undergoing regular surveillance colonoscopy (SCS), to identify the characteristics of endoscopists and patients who may benefit significantly from CADe.

Aims & Methods

Patients who underwent regular SCS with CADe at Hiroshima University Hospital from January to March 2023 and had undergone colonoscopy at least twice in the previous three years using a conventional detection method were enrolled. Forty-eight endoscopists who had collectively performed ≥800 colonoscopies performed the examinations. Endoscopic resection was performed for lesions ≥6 mm in size, flat and depressed neoplastic lesions ≤5 mm in size, and lesions with suspected high-grade dysplasia or T1a carcinoma, according to Japanese guidelines. Diminutive polypoid adenomas ≤5 mm in size were followed up without resection. Lesions pathologically identified as adenomas >6 mm or carcinomas were defined as index lesions (ILs). Lesions pathologically identified as adenomas ≥10 mm in size, tubulovillous adenomas, and high-grade dysplasia were defined as advanced adenomas (AAs). The clinicopathological findings of the lesions detected by CADe were evaluated, and the outcomes were compared between the semi-clean colon (diminutive polypoid adenomas ≤5 mm in size followed up without resection) and clean colon (no adenomatous polyps) groups.

Results

Overall, 78 patients were included. CADe identified 46 adenomas that were not detected by previous colonoscopy in 28 patients, including three ILs but no AAs. The mean withdrawal time was 824 ± 353 s, and the mean tumor diameter was 3.3 mm (range, 2–8 mm). The most common gross type was 0-Is (70%), followed by 0-Isp (17%) and 0-IIa (13%). Most tumors were located in the ascending and sigmoid colons (28%), followed by the transverse colon (26%), cecum (7%), descending colon (7%), and rectum (4%). The ILs were 0-Isp Isp of 6 mm diameter in the ascending colon, 0-Is of 7 mm diameter in the transverse colon, and 0-Isp Isp of 6 mm diameter in the descending colon, all of which were adenomas with lesions on the folds. Overall, 34.1% and 38.2% of the patients in the semi-clean and clean colon groups, respectively, had newly detected adenomas. No new neoplastic lesions were detected using CADe in patients without a history of endoscopic resection. When comparing the clinical backgrounds of patients with and without new ILs detected in CADe SCS, a significant difference was found in the IL detection rate at the previous SCS between the groups (67% vs. 12%, p = 0.0319).

Conclusion

CADe may help detect adenoma in SCS for patients with semi-clean colons and those with clean colons and a history of endoscopic resection. Its effectiveness is considered more for patients with ILs at the previous SCS.

Introduction

Colonoscopy is a promising diagnostic procedure for removal colorectal neoplasia, which can help prevent colorectal cancer. With an increasing trend towards colorectal cancer prevention, the number of colonoscopies and polypectomies is increasing, with approximately 11 million colonoscopy procedures performed annually in the United States alone. This has resulted in a significant burden on physicians and healthcare resources. Previous studies have demonstrated the utility of computer-aided diagnosis (CADx) systems in improving the characterization of colorectal polyps. However, the time-saving aspect of implementing AI-based CADx systems has not been thoroughly investigated. In this study, we aim to evaluate the potential of CADx systems to reduce the time required for polyp characterization.

Aims & Methods

This was a single center, retrospective study, was conducted at a university hospital between July 2021 and January 2022. We randomly extracted pathologically confirmed 100 polyps and one representative NBI image was prepared for each lesion. Three non-experts (a resident with no endoscopic experience, a gastroenterologist with one year of experience, and a gastroenterologist with two years of experience) were included. Randomly selected NBI images were shown separately to these doctors separately using laptop computer. They diagnosed each lesion diagnosed each lesion as neoplastic or non-neoplastic. For this study, we considered sessile serrated lesions (SSLs) as neoplasms. In the first examination, non-experts diagnosed without any assistance. After a four-week interval, a second examination was conducted with the assistance of a CADx system that provided a pathological prediction (neoplastic or non-neoplastic). We recorded the time required for diagnosing each polyp and compared it between the first and second examinations. The outcomes were, difference in diagnostic time and diagnostic accuracy of the endoscopists with or without CADx assistance. Wilcoxon signed rank test and McNemar test were used.

Results

Out of the 100 lesions, there were 72 adenomas/intramucosal carcinomas, 6 SSLs, 21 hyperplastic polyps, and 1 juvenile polyp. With the use of CADx, the mean (±SD) diagnostic time was significantly shorter than without CADx assistance (10.7±8.2 sec vs 5.3±3.6 sec, P value < 0.001). Regarding the diagnostic performance for differentiating neoplasms from non-neoplasms, diagnostic accuracy was significantly higher in with CADx assistance (75%　[95%CI 69.7-79.8] vs 92.3% [95%CI 88.7-95.1], P value < 0.001). Assuming the mean number of polyps per patient as 1.87 (Taku Sakamoto, et al. United European Gastroenterol J, 2019), time saving effect was estimated as 17 min / 100 colonoscopies.

Conclusion

Our study demonstrates that the utilization of the CADx can save diagnosing time and increase accuracy for non-experts. Therefore, we suggest that the CADx has the potential to decrease examination time by expediting the diagnosis of lesions.

Introduction

In clinical practice, colonoscopy withdrawal time (CWT) is measured from the caecum to the anal verge without accounting for cleaning (washing or suctioning) and polypectomy events during withdrawal. The evidence for the correlation of CWT and adenoma detection rate (ADR) is somewhat conflicting, partially due to research relying on retrospective data, which does not account for cleaning and polypectomy events and is subject to inaccuracies in time measurement.

A randomized controlled trial recently demonstrated that ADR increases as colonoscopy inspection time (CIT) rise from 6 to 13 minutes ¹. CIT was defined as withdrawal from the caecum to the anal verge with the timer manually stopped during cleaning and polypectomy events, but CIT measurement cannot be implemented in clinical practice without dedicated staff to pause a timer during these events.

Aims & Methods

Recent years have demonstrated the ability of artificial intelligence (AI) models to measure CWT by detecting cecal landmarks and the anal verge. Our aim was to develop convolutional neural networks (CNN) to detect phases of cleaning and polypectomy during withdrawal to facilitate automated measurement of CIT.

One hundred endoscopy videos were prospectively collected for training data. We reviewed each individual frame during withdrawal (defined as frames after a cecal landmark was first visualized). Each frame during ‘cleaning’ and ‘polypectomy’ events were annotated with respective image-level labels, and the remaining withdrawal frames labelled as ‘inspection’. Cleaning events was defined as frames during suctioning of intra-colonic content or washing. Polypectomy events was defined as the first frame with visualisation of the injection needle or forceps/snare if the polyp was not lifted until completion of inspection of post-polypectomy resection margins. These annotations were referenced as ground truth.

From the 100 videos, two ResNet-101 CNNs were developed to detect cleaning (213,936 training frames) and polypectomy (56,273 training frames). The CNNs were then evaluated with 80 colonoscopy videos. This included 40 colonoscopy videos from five expert (ADR >45%) and 40 videos from six non-expert (ADR <30%) endoscopists. Consecutive procedures were used to minimize selection bias. Videos were annotated following the above methodology.

Results

For the test set of 80 procedures, the median WT documented in the endoscopy reporting system (EPIC) was 15.0 minutes (IQR 10.0–23.0), annotated ground truth median CIT was 7.1 minutes (IQR 5.3–9.6), and AI predicted median CIT was 6.9 minutes (IQR 5.1–9.0) with a correlation coefficient (r) of 98.2%. For expert procedures (n=40), these were 16.5 minutes (IQR 11.0–25.3), 7.1 minutes (IQR 5.1–8.6) and 6.9 minutes (IQR 4.9–8.8), respectively. Amongst non-expert procedures (n=40), these were 14.0 minutes (IQR 10.0–22.0), 7.0 minutes (IQR 5.8–10.7) and 7.0 minutes (IQR 5.3–10.2), respectively. The AI system correctly categorized 96.3% (77/80) of procedures as less or more than 6 minutes CIT.

Conclusion

We have demonstrated the feasibility of AI to differentiate the phases of withdrawal to facilitate automated measurement of CIT and the considerable difference in time between CIT and the CWT documented in an endoscopy reporting system.

References

1. Desai M, Rex DK, Bohm ME, et al. Impact of withdrawal time on adenoma detection rate: results from a prospective, multi-center trial. Gastrointest Endosc. 2022 Oct 10:S0016-5107(22)02039-9

Disclosure

Professor Laurence B Lovat is a minority shareholder and consultant advisor for Odin Vision. Professor Danail Stoyanov is a shareholder for Odin Vision.