Introduction

Recently, artificial intelligence-based computer-aided detection (CADe) for colonoscopy is garnering significant attention due to its effectiveness in increasing adenoma detection rate (ADR). However, theoretically, CADe system cannot decrease exposure error which polyps obscured by an object. In this regard, computer-aided quality improvement (CAQ) which expects to induce the meticulous mucosal inspection and leading to a reduction of blind spot area. In this study, we developed and evaluated CAQ for colonoscopy.

Aims & Methods

This was a single center, retrospective study from period April 1, 2022 to February 25, 2023. We randomly extracted colonoscopy videos and created 18,922 training images. Quadrant images were made from one image and three endoscopists annotated the following scores; i) appropriateness for mucosal inspection, ii) appropriate distance, and iii) presence of blind area in the field of view (e.g., fold or flexure). We conducted supervised machine learning using annotated images. The CAQ deployed multi-head deep convolutional neural network model which can output multiclass prediction from one image. Consequently, the CAQ system outputs aforementioned score from whole colonoscopy video. To validate its performance, we retrospectively analyzed colonoscopy procedures performed by seven endoscopists using the CAQ. We compared calculated CAQ model scores and expertise of endoscopists.

Results

29 videos were included as validation samples (8 videos were performed by non-expert endoscopists) As a result, there was a significant difference in the proportion of appropriate images during the examination between experts and non-experts (median 56% vs. 49%, p=0.005, Mann–Whitney U test) and there was also a significant difference in the evaluation score of the distance between the colon mucosa and the endoscope (median 4.2 vs. 3.2, p=0.0004, Mann–Whitney U test). In addition, there was a significant difference in the scores evaluating the presence of blind areas in the field of view (median 1.6 vs. 1.2, p=0.0007, Mann-Whitney U test).

Conclusion

In this study, developed CAQ system could quantify the skill of the endoscopists. Such CAQ would be expected to standardize the observation technique of colonoscopy.

Introduction

Balloon dilation and plastic stent deployment have been performed as hepaticojejunostomy stricture (HJS) treatment techniques by PTBD or under DB-ERCP guidance. Although these techniques have shown favorable clinical results, the treatment period can be long because stent deployment is required. In addition, HJS may recur even after treatment because the scar tissue itself remains. To overcome these challenges, we developed an transluminal antegrade piecemeal dilation technique (TAPD) for treating HJS. The aim of this study was to evaluate the technical feasibility and safety of this technique in terms of the pre- and post-cholangioscopic findings.

Aims & Methods

This retrospective study included consecutive patients who were complicated with symptomatic HJS between November and February 2022. The primary outcome of this study was the technical success rate of TAPD using a drill dilator. Technical success was defined as resolution of the HJS, based on the cholangioscopic findings. The secondary outcome was adverse events associated with TAPD such as bleeding or perforation.

Results

TAPD was attempted at around 11 days after EUS-HGS in 19 patients. Among the 19 patients, passage of the guidewire across the HJS into the intestine was unsuccessful in 4 patients, and the technical success rate of this procedure was 78.9%. TAPD was successful in all 15 patients in whom passage of the guidewire was achieved. After TAPD, cholangioscopy identified no bleeding or perforation in any patient. During the follow-up period, no recurrence of HJS was observed in any patient who underwent TAPD.

Conclusion

In conclusion, TAPD appears to be technically feasible and safe. Although it is necessary to conduct a randomized trial in comparison with other methods, with long-term follow up, TAPD may be a useful option for the treatment of HJS.

Introduction

To prevent stent migration during EUS-HGS, intra-scope channel release technique is important, but are unfamiliar to non-expert hands. The self-expandable metal stent (SEMS) is an additional factor to prevent stent migration. However, no comparative studies of laser-cut and braided types during EUS-HGS have been reported.

Aims & Methods

The aim of this study was to compare the distance between the intrahepatic bile duct and stomach wall after EUS-HGS among laser-cut- and braided-type SEMS. To evaluate stent anchoring function, we measured the distance between the hepatic parenchyma and stomach wall before EUS-HGS, one day after EUS-HGS, and 7 days after EUS-HGS.　Also, propensity score matching was performed to create a propensity score for using Laser cut type group and Braided group with a logistic regression model.

Results

A total 144 patients were enrolled in this study. Among them, 24 patients underwent EUS-HGS using a laser-cut-type SEMS, and 118 patients underwent EUS-HGS using a braided-type SEMS. EUS-HGS using the laser-cut-type SEMS was mainly performed by non-expert endoscopists (n=21). However, EUS-HGS using braided-type SEMS was mainly performed by expert endoscopists (n=98), showing a significant difference. The distance after 1 day was significantly shorter with the laser-cut-type group (2.91 ± 1.88 mm) compared with the braided-type group (8.19 ± 6.07 mm). In addition, this distance remained significantly shorter in the laser-cut type group compared with the braided-type group after 7 days.　Although these results were similar after propensity score matching analysis, the distance between hepatic parenchyma and stomach after 7 days was increased 4mm compared with the distance after 1 day in Braided group. On the other hand, in Laser cut type group, the distance after 1 day and 7 days was almost same.

Conclusion

In conclusion, EUS-HGS using a laser-cut-type SEMS may be safe to prevent stent migration, even in non-expert hands, compared with a braided-type SEMS, although a randomized trial is warranted.

Disclosure

None

Introduction

Computer-aided detection (CADe) systems improve adenoma detection rate (ADR). However, there is some concern that the long-term use of CADe systems might lead to a decline in endoscopists’ independent detection skills, particularly their ability to detect lesions without assistance—a phenomenon referred to as "deskilling".

Aims & Methods

This study aims to evaluate the impact of CADe on the learning curve of endoscopists for ADR. This was a propensity score–matched (PSM), prospective, single-center, observational study conducted at a tertiary care hospital from January 2021 to December 2023. CADe systems were installed in half of the endoscopy units, and patients were equally distributed between the rooms. Patients in CADe-equipped rooms were examined using EndoBRAIN-EYE (Olympus Corp, Tokyo, Japan). Patients aged ≥ 20 years scheduled for colonoscopy were included, excluding those with polyposis, inflammatory bowel disease, known polyps, incomplete colonoscopy, emergency cases, previous colorectal surgery, and examination by novices. Endoscopists were classified as high-detectors (ADR ≥ 25%) or low-detectors (ADR < 25%) based on the ADR recorded before CADe implementation. The primary outcome was to evaluate the learning effect of CADe using cumulative summation (CUSUM) analysis based on ADR during both CADe and non-CADe procedures to assess skill acquisition and transfer. The CUSUM scores were calculated from the acceptable probability of failure and unacceptable probability of failure. Acceptable and unacceptable ADR were defined as 40% and 30% for high detectors, and 35% and 25% for low detectors, respectively. Performance was judged based on the boundary lines (h0 and h1): acceptable if the CUSUM plot fell below h0, unacceptable if it went above h1, and inconclusive requiring further observation if it stayed between these boundaries. The secondary outcomes included ADR, advanced adenoma detection rate (AADR), and sessile serrated lesion detection rate (SSLDR). The study received ethics approval (no.19H072) and complied with the Declaration of Helsinki.

Results

Out of 5,717 patients initially enrolled, 4,712 patients (2,356 in CADe group and 2,356 in non-CADe group) were analyzed after PSM for known factors (age, sex, indication, and bowel preparation). During CADe-assisted procedures, both high-detectors and low-detectors showed patterns below the acceptable performance line (h0), indicating improved adenoma detection performance with AI support. However, during non-CADe procedures, the patterns diverged significantly. For high-detectors, their CUSUM plots consistently fell below the acceptable performance line (h0) over time during non-CADe colonoscopies, indicating that they successfully acquired and maintained improved adenoma detection skills even without AI assistance. In contrast, the CUSUM plots of the low-detectors remained between the acceptable (h0) and unacceptable (h1) limits throughout the study period, showing no significant change in learning trajectory during non-CADe procedures. The CADe group had a significantly higher ADR (40.5% [95% CI: 38.5-42.5%]) compared to non-CADe group (32.4% [95% CI: 30.5-34.4%]; p < 0.001). SSLDR was also significantly higher in the CADe group (6.9% [95% CI: 5.9-8.0%] vs. 4.5% [95% CI: 3.7-5.4%]; p = 0.001), while AADR showed no significant difference (4.1% [95% CI: 3.4-5.0%] vs. 4.7% [95% CI: 3.9-5.6%]; p = 0.39).

Conclusion

The implementation of the CADe system did not result in deskilling regarding adenoma detection.

Disclosure

The conflict of interests were following: Shin-ei Kudo and Masashi Misawa received speaking honoraria from Olympus Corporation and have an ownership interest of the products of Cybernet Systems. Kensaku Mori received research grants from Cybernet Systems, Morita Mfg, Atom Medical Inc, and Asahi Intecc. Additionally, Kensaku Mori serves as a Technical Advisor for Sanyu Industry. Tetsuo Nemoto received a research grant from Olympus Corporation for other studies. Other authors have nothing to declare.

Introduction

AI (artificial intelligence)-driven computer-aided detection (CADe) systems are typically trained using high-quality, standardized colonoscopy images/videos, assuming its use under optimal bowel preparation. However, it remains uncertain how varying levels of bowel cleanliness affect CADe performance.

Aims & Methods

To measure the impact of bowel preparation quality on the adenoma detection capability of CADe systems.
This is a cumulative post-hoc analysis of individual data from three randomized controlled studies with similar design comparing CADe-assisted with standard colonoscopy (SC). Only patients with adequate bowel preparation (Boston Bowel Preparation Scale [BBPS] >2 in each colonic segment) were included. The primary outcome measure was the difference in adenoma detection rate (ADR) and adenoma per colonoscopy (APC) between the CADe-assisted and SC groups, according to the quality level of bowel preparation, classified as good (BBPS 6–7) or excellent (BBPS 8–9).

Results

A total of 2103 patients (1047 CADe, 1056 SC; mean age 61.5 ± 9.2 years; 50.4% male) were included. Bowel preparation was rated as good in 906 patients (43.1%) and excellent in 1197 patients (56.9%). CADe increased ADR and APC compared to SC in both good (52.2% vs. 43.8%; 1.21 vs. 0.93) and excellent (54.5% vs. 43.9%; 1.09 vs. 0.89) bowel preparation groups. The absolute increase in ADR with CADe was +8.4% (95% CI: 1.9–14.9) and +10.6% (95% CI: 5.0–16.2) in good and excellent preparation groups, respectively, with no significant interaction between preparation quality and CADe effect (Δ = +2.2%, 95% CI: -6.4–10.8; interaction p = 0.612). Similarly, APC increases were +0.28 (95% CI: 0.06–0.50) and +0.20 (95% CI: 0.03–0.36) for the good and excellent preparation groups, respectively, without significant interaction observed (Δ = -0.08, 95% CI: –0.22 to +0.06, interaction p = 0.261). Similar trends were observed when the analysis was restricted to the right colon or to diminutive adenomas.

Conclusion

In patients with adequate bowel preparation, CADe improves adenoma detection regardless of cleansing quality grades.

References

1. Repici, A, Badalament M, Maselli R et al. Efficacy of Real-Time Computer-Aided Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology 2020; 159: 512–520
2. Repici A, Spadaccini M, Antonelli G, et al. Artificial intelligence and colonoscopy experience: lessons from two randomised trials. Gut 2022; 71: 757-765.
3. Rondonotti E, Di Paolo D, Rizzotto ER, et al. Efficacy of a computer-aided detection system in a fecal immunochemical test-based organized colorectal cancer screening program: a randomized controlled trial (AIFIT study). Endoscopy. 2022; 54: 1171-1179.

Introduction

In the carcinogenic pathway of colorectal cancer, the first concept is the "adenoma-carcinoma sequence" and the second concept is the " serrated pathway ". In these concepts, adenomas and serrated lesions gradually progress to cancer. The third concept is the "de novo pathway," in which cancer develops without adenomas or serrated lesions and is also characterized by high malignancy and rapid progression. We have endoscopically characterized depressed colorectal cancers considered to be of the "de novo pathway" and validated the usefulness of pit pattern and EC classification.

Aims & Methods

A total of 54819 colorectal neoplasms were resected endoscopically or surgically in our institution from April 2001 to December 2024. They were subjects of this study. Advanced cancers were excluded. Of these, 1694 lesions were submucosally invasive (T1) carcinomas, 7330 lesions were classified as high-grade dysplasia and 39977 lesions as low-grade dysplasia. Morphologically, they were divided into 3 types: depressed, flat, and protruded type comprising 1.0 (%), 46.4 (%),and 52.6（%), respectively. Specifically, the distinctive features of depressed type neoplasms concerning their pit pattern and EC classification were examined. EC classification is a classification for an endocytoscopy that can evaluate pathology, such as nuclear atypia and glandular structure, by magnifying stained cells. EC1a is diagnosed as normal mucosa, EC1b is diagnosed as hyperplastic polyps, and if slit-like glandular ducts or spindle-shaped nuclei are present, it is classified as EC2 and diagnosed as an adenoma or intramucosal carcinoma. If irregularly shaped glandular ducts or nuclei with a high N/C ratio are found, it is classified as EC3a, and diagnosed as intramucosal carcinoma or SM lightly invasive carcinoma. If the glandular ducts are indistinct and the nucleus is irregularly shaped and darkly stained, it is classified as EC3b and diagnosed as SM highly invasive carcinoma.

Results

Most of the flat (91.5%) and protruded type (94.9%) lesions showed type IIIL or IV pit pattern, which are common findings in adenomas. On the other hand, most of the depressed type lesions (92.6%) classified as type IIIs, VI or VN pit patterns, are typically seen in carcinomas. As for endocytoscopy, most of flat and protruded type lesions were identified as EC2 corresponding to adenomas. In contrast, relatively high rates of depressed type lesions were categorized as EC3a (40.3%) and EC3b (52.4%), consistent with invasive carcinomas.
The proportion of T1 carcinomas in depressed type lesions was 58.7%, whereas in flat and protruded type lesions it was 2.5% and 2.5%, respectively. Additionally, 12.0% of depressed type lesions less than 5mm in diameter were T1 carcinomas, whereas flat and protruded type lesions were 0.01% and 0%, respectively.

Conclusion

This study revealed that depressed lesions were classified as type IIIs, VI or VN pit patterns on magnifying endoscopy and as type EC3a or EC3b on endocytoscopy. Lesions with these features or pit patterns tend to invade the submucosal layer even if they are small size. Despite their high potential for malignancy, depressed lesions are often ignored. However, it is critical to recognize their features and accurately diagnose lesions based on morphology, pit pattern, and EC classification.

Disclosure

Shin-ei Kudo and Masashi Misawa received speaking honoraria from Olympus Corporation and have an ownership interest of the products of Cybernet Systems. Tetsuo Nemoto received a research grant from Olympus Corporation for other studies. Other authors have nothing to declare.