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

In ulcerative colitis (UC) clinical trials, endoscopic disease activity is commonly assessed via central reading of the overall Mayo Endoscopic Score (MES). Segmental MES can provide a more detailed evaluation of mucosal response, but it is limited by high inter-rater variability in both anatomical landmark localization and disease activity grading. Automatic MES grading can assist reducing reader discrepancies and detect local mucosal changes that may not be estimated by global scoring. In this study, we developed and evaluated an artificial intelligence (AI)-based system for automated segmental MES grading enabling disease extent quantification and granular endoscopic remission estimation.

Aims & Methods

In contrast to previous approaches, the proposed AI system introduces a novel hierarchical framework for automated MES grading at the frame-, segment-, and video-level. The system comprises three modules, trained on 5,897 retrospectively acquired, aggregated, and anonymized endoscopic videos. A foundation model (FM), trained on 22 million frames, was developed to extract clinically relevant frames from full-length colonoscopies. A colon segmentation module was built upon the FM to localize three anatomical segments: descending colon (DC), sigmoid colon (SI), and rectum (RM). An automated MES classification module was then trained to perform frame-level MES grading. Hierarchical aggregation of local scores, combined with temporal smoothing and non-informative filtering, enabled both segmental and global MES estimation. For independent testing, 915 colonoscopy videos were annotated for each segment for MES scoring by expert gastroenterologists using a 2+1 reading paradigm. Colon segment reference annotations were automatically extracted from endoscopic videos based on recording software annotations. System performance was evaluated using the Quadratic Weighted Kappa (QWK) for both segmental and overall MES agreement. Classification accuracy in detecting endoscopic granular remission (MES 0, 1 vs 2, 3) was reported for all colon segments.

Results

The AI system demonstrated strong agreement (QWK=0.752 [95% CI: 0.719, 0.782]) with gastroenterologist assessments for overall MES on the test dataset. Good agreement was confirmed for SI (QWK=0.647 [95% CI: 0.602, 0.687]) and RM (QWK=0.687 [95% CI: 0.646, 0.724]), moderate agreement was found for DC (QWK=0.592 [95% CI: 0.541, 0.638]). Frame-level colon segment classification accuracy was 41% for DC, 69% for SI, and 78% for RM; with lower performance in DC linked to high variability in reference annotations. Colon segmentation enabled a 37.72% reduction in mean colonoscopy video time by filtering out-of-body and insertion-phase sections. The system showed very high accuracy in detecting both overall (ACC=90.38%) and segmental (DC: 78.80%; SI: 82.84%; RM: 85.03%) endoscopic remission. Mean accuracy in detecting the number of colon segments per video with active disease was 59.13%.

Conclusion

We introduced a novel AI system for automated, granular MES scoring in ulcerative colitis patients, hierarchically grading colonoscopy videos. Our framework demonstrated strong agreement with gastroenterologists in both overall and segmental endoscopic activity assessments. By integrating continuous scoring with anatomical landmarking, the AI system can offer a more comprehensive view of total disease burden in UC patients which can lead to improved precision of disease estimation and treatment response evaluation in clinical settings.

Disclosure

All authors are employees of Clario Inc., Philadelphia, USA.

Introduction

The Tokyo Guideline 2018 recommends laparoscopic cholecystectomy as the gold standard therapy for acute cholecystitis regardless of the severity and the onset of symptoms, as long as the patient is fit for surgery. Approximately 20% of the patients undergo acute cholecystectomy in our region, and in the remainder of the patients, we have to take into consideration the likelihood of recurrent inflammation after the regression with conservative therapy. According to the TG 2018, the drainage of the gallbladder is recommended in grade II and grade III cholecystitis. This can be carried out by interventional radiologist as percutaneous transhepatic gallbladder drainage (PTGBD), by endoscopist as transpapillary gallbladder drainage (TPGBD) or endosonography-guided gallbladder drainage (EUS-GBD).

Aims & Methods

The primary endpoint of our prospective, non-randomized, observational study was to determine the technical (successful stent implantation into the gallbladder) and clinical success (repeated need for drainage and absence of recurrent cholecystitis) of TPGBD in those patients that underwent it from 01.01.2023 at the University of Szeged. Our secondary endpoint was the comparison of the time of hospitalization between the patients who underwent clinically successful TPGBD and those who underwent PTGBD for grade II/III cholecystitis.

Results

Altogether 19 patients had undergone TPGBD, 74% of them were female, the average age was 64,53. Previously 21% had cholecystitis, 47% had cholecystolithiasis, while 16% had choledocholithiasis and 11% of the patients gone under PTGBD. TPGBD was carried out because of grade II cholecystitis in 89% of the patients, and grade III in the rest of them. 63% was considered at least a 3 in the ASA physical status classification. Altogether the technical success rate was 58%, a cholangioscop was used in 37% of the cases. The successful canulation rate of the bile duct was 89%, while the canulation rate of the cystic duct was 68%. There were two cases, where after the canulation of the cystic duct the implantation of the plastic stent was not possible. 3 patients were referred for PTGBD after an unsuccessful TPGBD, the remainder patients with an unsuccessful TPGBD received conservative therapy. After a technically successful TPGBD, only one patient went under PTGBD due to his severe comorbidities, rather than a repeated TPGBD. 6 patients underwent cholecystectomy averagely in 8,5 weeks after the TPGBD, the remainder of patients did not have neither the need for repeated drainage nor any symptoms requiring urgent care due to cholelithiasis. Comparing this group with 11, randomly chosen patients who underwent PTGBD for at least grade II cholecystitis during the period of the study, we detected that the time of hospitalization after the drainage was less (8,2 days vs 13,3 days), and less patients required repeated drainage or had recurrent cholecystitis (1 vs 4).

Conclusion

Although TPGBD imposed a great challenge before the use of cholangioscop in everyday practice, nowadays it is becoming an accepted part of the therapeutic algorithm in the treatment of cholecystitis, where an acute cholecystectomy is not performed. Our results suggest that TPGBD can lead to shortened hospitalization and have less complications than TPGBD. Our findings will serve as a basis for a future extension of the study and for the design of a randomised prospective study with a control group.

Introduction

Quality assessment is a priority in the field of gastroenterology. However, limited data are available from Greece regarding adherence to quality standards in gastrointestinal endoscopy.

Aims & Methods

This study aims at assessing the knowledge and compliance of Greek gastroenterologists with established quality standards for upper and lower digestive endoscopy, while exploring factors that may influence compliance.
​This prospective study recorded data on the quality of upper and lower digestive endoscopy performed in Greece from October 2024 to January 2025. All members of the Hellenic Society of Gastroenterology (n=668) were invited to participate via an electronic survey. The survey included a questionnaire designed specifically for this study, covering demographic and professional characteristics, as well as quality indicators for gastroscopy and colonoscopy.

Results

A total of 164 gastroenterologists participated (response rate 24.55%), of whom 107(65.24%) were male, and 102(62.2%) working in public or academic hospitals. The duration of gastroscopy was not recorded by 116(70.73%) participants, while 102(62.2%) systematically used photodocumentation. Most participants utilized the Prague and Los Angeles classifications 156(95.12%) and 159(96.95%) respectively. Additionally, 140(85.37%) followed the Seattle protocol, and 158(96.34%) conducted biopsies according to ESGE guidelines for precancerous gastric lesions. However, 83(50.61%) don’t use a registry for patients with Barrett’s esophagus. Complications were systematically recorded after gastroscopy by 103(62.8%) and after colonoscopy by 90(54.88%).
In colonoscopy, 149(90.85%) use the BBPS scale, and 158(96.34%) reported successful cecal intubation. Withdrawal times exceeded six minutes for 151(92.07%) participants. An adenoma detection rate of over 25% was achieved by 117(71.78%), while 103(62.8%) consistently used the Paris classification. Proper polypectomy techniques were employed by 111(67.68%), but 100(60.98%) recommended follow-up intervals shorter than guidelines suggest. Patient experience following gastroscopy and colonoscopy was not recorded by 126(76.83%) and 116(70.73%) participants, respectively. Overall, compliance with quality indicators for upper and lower digestive endoscopy was observed in 87(53.05%) and 75(45.73%) participants, respectively. Multivariate analysis revealed that 5-15 years of experience (p=0.05), the use of video recording (p=0.01) and use of high-resolution endoscopes (p<0.01) were associated with improved compliance with quality indicators of upper endoscopy. Whereas age above 55 (p<0.01), use of high-resolution endoscopes(p<0.01), use of video recording (p=0.02) and attendance of educational seminars relevant with quality in endoscopy (p=0.05) were associated with improved compliance with quality indicators of colonoscopy.

Conclusion

In this study, discrepancies were observed in the compliance of Greek endoscopists with endoscopic quality indicators, highlighting the need for further improvement. The systematic recording of these quality indicators is essential, underlining the important role of scientific societies in this process.

Introduction

Exocrine pancreatic insufficiency (EPI) is defined as a reduction in the exocrine pancreatic secretion and/or intraluminal activity of pancreatic enzymes below the level that allows normal digestion of nutrients. Currently, diagnosing EPI presents challenges: the most accurate method requires collecting faecal samples for several days to measure faecal fat excretion following a specific diet, while faecal elastase test, although simpler, has a high incidence of false positives.
The study assesses whether measuring lipase in blood, following the ingestion of a standard high-fat meal could provide a more accessible diagnosis of EPI. The hypothesis is that blood lipase increases proportionally to pancreatic secretion in individuals without EPI, allowing differentiation between patients with and without insufficiency.

Aims & Methods

The study's main objective was to investigate whether blood levels of lipase increase after a fatty meal in normal subjects. If blood lipase and lipase secreted by the pancreas have a correlation, by calculating the area under the curve of several determinations of blood lipase in healthy subjects, we could set a normal pattern of lipase secretion. In the future, this pattern can be compared to patients with EPI to test if it can be a screening tool for EPI.
For the study, 10 healthy volunteers were tested. All participants fasted before receiving a test meal designed to stimulate lipase secretion. Blood samples were then taken every 30 minutes for six hours to measure lipase blood levels and calculate the area under the curve (AUC) using the trapezoid method.

Results

The mean (standard deviation) of the maximum and minimum lipase blood levels was 24 (9) and 19 (8) U/L, respectively. The mean percentage change in lipase was 31% (standard deviation 16%). The area under the curve of blood lipase levels between the baseline sample and the sample at 360 minutes had a mean of 7749 (standard deviation 3129) units per litre per hour. The median time to peak lipase was 0 minutes, meaning that the expected peak in blood lipase did not occur after the test meal: in 60% of cases, the highest peak of all measurements was the baseline measurement, with no clear peak in response to the meal in the remaining cases, in contrast with pancreatic secretion into the duodenum.

Conclusion

According to our patient sample, lipase does not increase in the blood after stimulation with a test meal, as occurs in pancreatic lipase secretion into the duodenum. Lipasemia is, therefore, independent of pancreatic secretion and does not seem to be a promising parameter for screening exocrine pancreatic insufficiency.

References

1. Sastre J, Sabater L, Aparisi L. [Physiology of pancreatic secretion]. Gastroenterol Hepatol. 2005;28 Suppl 1:3-9.
2. Gonzalez-Sanchez V, Amrani R, Gonzalez V, Trigo C, Pico A, de-Madaria E. Diagnosis of exocrine pancreatic insufficiency in chronic pancreatitis: (13)C-Mixed Triglyceride Breath Test versus Fecal Elastase. Pancreatology. 2017;17(4):580-5.
3. Sabater L, Ausania F, Bakker OJ, Boadas J, Dominguez-Munoz JE, Falconi M, et al. Evidence-based Guidelines for the Management of Exocrine Pancreatic Insufficiency After Pancreatic Surgery. Ann Surg. 2016.
4. Lohr JM, Dominguez-Munoz E, Rosendahl J, Besselink M, Mayerle J, Lerch MM, et al. United European Gastroenterology evidence-based guidelines for the diagnosis and therapy of chronic pancreatitis (HaPanEU). United European Gastroenterol J. 2017;5(2):153-99.
5. Lundh G. Pancreatic exocrine function in neoplastic and inflammatory disease; a simple and reliable new test. Gastroenterology. 1962;42:275-80.

Introduction

Esophageal squamous cell carcinoma (ESCC) often develops the synchronous or metachronous multiple ESCC. Although the Japanese guideline recommended endoscopic examination as surveillance at least once a year after endoscopic resection (ER) of ESCC, the optimal surveillance modality was not specified. In clinical practice, image-enhanced endoscopy (IEE) followed by Lugol chromoendoscopy (LCE) is commonly performed. While LCE reduces the proportion of missed lesion, it has low specificity and causes severe discomfort to the patients, so attempts have been made to omit Lugol's staining. It is unknown what lesions may be missed at this time point by omitting LCE in surveillance after esophageal ER.

Aims & Methods

Thus, this study aimed to clarify clinicopathological characteristics of synchronous or metachronous multiple ESCCs missed by IEE but detected by LCE in surveillance endoscopy after esophageal ER. We retrospectively analyzed the consecutive lesions that fulfilled all of the following inclusion criteria: (1) treated with endoscopic submucosal dissection (ESD) or endoscopic mucosal resection (EMR) at our institution between April 2021 and March 2022; (2) newly detected during surveillance endoscopy after ER or during preoperative endoscopy for other ESCC; (3) underwent narrow-band imaging (NBI) or blue laser imaging (BLI) observation followed by LCE observation in the esophagus using a high-definition endoscope at the endoscopic examination of lesion detection; and (4) biopsy-proven or strongly suspected squamous cell carcinoma. Patients with a history of chemotherapy, radiotherapy, or surgery for esophageal cancer were excluded. Lesions were classified into the IEE group (detected by NBI/BLI) and the LCE group (detected only after Lugol staining). The lesion in the IEE group were defined when the lesion was clearly visualized and in focus on the endoscopic images with NBI or BLI, or the endoscopic report described that it was detected with NBI/BLI. We evaluated the features of the lesions in the LCE group by comparing the clinicopathological characteristics between the lesions in the IEE group and LCE group. The endpoints were proportion of　LCE detected lesion and the proportion of target ESCC, defined as ESCC with pathological invasion depth of the muscularis mucosae (pT1a-MM) or deeper and/or positive lymphovascular invasion (LVI) on histological evaluation after ER.

Results

A total of 122 lesions in 96 patients were included. The IEE group comprised 99 lesions (81.1%) in 75 patients, while the LCE group comprised 23 lesions (18.9%) in 21 patients, thus proportion of LCE detected lesion was 18.9%. Most patients (92.7%, 89/96) had grade C of Lugol voiding staining. The median lesion size was 15 mm (range: 4-60 in the IEE group, which was higher than that in the LCE group at 10 mm (5-30). The lesions located on the anterior (23.5%) and left wall (31.3%) tended to be more frequently detected by LCE than those on the right (10.8%) and posterior wall (13.9%). Finally, 26 lesions were treated with EMR and 96 with ESD. The pathological diagnosis was pT1a-MM in 5 lesions and pT1b-SM1 in 2, resulting in the proportion of target ESCC of 5.7% (7/122). By group, the proportions of target ESCC were 7.1% (7/99) in the IEE group and 0% in the LCE group.

Conclusion

The characteristics of missed lesions in IEE observation tended to be small and located on the left or anterior wall of esophagus at surveillance endoscopy. Furthermore, all of these lesions were curatively resected with ER, resulting pT1a-EP/LPM without LVI in the pathological diagnosis.