Faculty Bibliography

PURPOSE OF REVIEW/OBJECTIVE:This review highlights the history, recent advances, and ongoing challenges of artificial intelligence (AI) technology in colonic polyp detection. RECENT FINDINGS/RESULTS:Hand-crafted AI algorithms have recently given way to convolutional neural networks with the ability to detect polyps in real-time. The first randomized controlled trial comparing an AI system to standard colonoscopy found a 9% increase in adenoma detection rate, but the improvement was restricted to polyps smaller than 10 mm and the results need validation. As this field rapidly evolves, important issues to consider include standardization of outcomes, dataset availability, real-world applications, and regulatory approval. AI has shown great potential for improving colonic polyp detection while requiring minimal training for endoscopists. The question of when AI will enter endoscopic practice depends on whether the technology can be integrated into existing hardware and an assessment of its added value for patient care.

BACKGROUND & AIMS/OBJECTIVE:Mucosal exposure devices improve detection of lesions during colonoscopy and have reduced examination times in uncontrolled studies. We performed a randomized trial of Endocuff Vision vs standard colonoscopy to compare differences in withdrawal time (the primary end point). We proposed that Endocuff Vision would allow complete mucosal inspection in a shorter time without impairing lesion detection. METHODS:Adults older than 40 years undergoing screening or surveillance colonoscopies were randomly assigned to the Endocuff group (n=101, 43.6% women) or the standard colonoscopy group (n=99; 57.6% women). One of 2 experienced endoscopists performed the colonoscopies, aiming for a thorough evaluation of the proximal sides of all haustral folds, flexures, and valves in the shortest time possible. Inspection time was measured with a stopwatch and calculated by subtracting washing, suctioning, polypectomy and biopsy times from total withdrawal time. RESULTS:There were significantly fewer women in the Endocuff arm (P=.0475) but there were no other demographic differences between groups. Mean insertion time with Endocuff was 4.0 min vs 4.4 min for standard colonoscopy (P=.14). Mean inspection time with Endocuff was 6.5 min vs 8.4 min for standard colonoscopy (P<.0001). Numbers of adenomas detected per colonoscopy (1.43 vs 1.07; P=.07), adenoma detection rate (61.4% vs 52%; P=0.21), number of sessile serrated polyps per colonoscopy (0.27 vs 0.21; P=0.12), and sessile serrated polyp detection rate (19.8% vs 11.1%; P= 0.09) were all higher with Endocuff Vision. Results did not differ significantly when we controlled for age, sex, or race. CONCLUSION/CONCLUSIONS:In a randomized trial, we found inclusion of Endocuff in screening or surveillance colonoscopies to decrease examination time without reducing lesion detection. ClinicalTrials.gov no.: NCT03361917.

BACKGROUND AND AIMS/OBJECTIVE:Although screening for Barrett's esophagus (BE) is recommended in individuals with multiple risk factors, the type and number of risk factors necessary to trigger screening is unclear. In this systematic review and meta-analysis, we aimed to assess the relationship between number of risk factors and prevalence of BE. METHODS:Through October 17, 2018, we searched studies that described the prevalence of BE in the general population and based on presence of risk factors that included GERD, male gender, age >50 years, family history of BE and esophageal adenocarcinoma (EAC), and obesity (defined as body mass index >35). Risk of BE based on number of risk factors was assessed using meta-regression while controlling for potential confounders. RESULTS:Of 2,741 studies, 49 were included in the analysis (307,273 individuals, 1,948 with biopsy-proven BE). Indications varied by study. The prevalence of BE for various populations was as follows: low-risk general population: 0.8% (95% CI, 0.6% - 1.1%); GERD: 3% (95% CI, 2.3% - 4%); GERD plus presence of any other risk factor: 12.2% (95% CI,10.2% - 14.6%); family history: 23.4% (95% CI,13.7% -37.2%); age > 50: 6.1% (95% CI, 4.6% - 8.1%); obesity: 1.9% (95% CI, 1.2% - 3%); and male sex: 6.8% (95% CI, 5.3% - 8.6%). Prevalence of BE varied significantly between Western and non-Western populations. In a meta-regression, controlling for the region of the study, age, and gender, there was a positive linear relationship between the number of risk factors and the prevalence of BE. CONCLUSIONS:Results of this study provide estimates of BE prevalence based on the presence and the number of risk factors. These results add credence to current guidelines that suggest screening in the presence of multiple risk factors.

INTRODUCTION: Meckel's diverticulum (MD) is the most common congenital malformation of the gastrointestinal (GI) tract, present in 2-4% of the population. Typically, it presents as GI bleeding and is usually diagnosed in childhood. However, some patients may remain asymptomatic through adulthood or present later in life with complications. We describe an unusual case of an adult male presenting with abdominal pain and maroon stools, who underwent an extensive workup and was eventually diagnosed with MD only after a double-balloon enteroscopy (

INTRODUCTION: Screening for Barrett's Esophagus (BE) in chronic gastroesophageal reflux disease (GERD) using targeted and random forceps biopsy (FB) is recommended by current ACG guidelines. A recent study of 10,412 screening patients showed that Wide Area Transepithelial Sampling with 3D computer-assisted tissue analysis (WATS) increases detection of Barrett's esophagus (BE) when used adjunctively to FB. We analyzed the cost-effectiveness implications of this study's findings.
METHOD(S): A decision analytic model compared the effectiveness and cost-effectiveness of two alternative screening strategies for BE in chronic GERD patients: FB alone vs. FB combined with WATS. The reference case was a 60 year old male. BE detected by positive FB or WATS was referred for surveillance. False positive WATS+/FB- were confirmed after a second negative surveillance FB. Cost and effectiveness of surveillance were based on published models with ablation for low or high grade dysplasia, available on the National Cancer Institute CISNET website. See Table 1 for an overview of model parameters. Effectiveness was measured in quality-adjusted life years (QALYs). Cost was measured in 2018 US$ and the incremental cost-effectiveness ratio (ICER) was measured in $/QALY. Model parameters are outlined in Table 2. We considered 3 values of added yield (213% from the study, half of that, one-third of that) and 3 values of false positives among the added yield (5%, 15%, 25%) and calculated the ICER for all 9 pairwise combinations of those two parameters. We considered two thresholds for cost-effectiveness: $100K/QALY and $150K/QALY. Cost and QALYs were discounted at 3% per year.
RESULT(S): The ICERs for all 9 combinations of added yield and false positives are in Table 3. Use of FB plus WATS was cost-effective in all 9 combinations at the lower $100K/QALY threshold. Using the worst case for added yield (1/3 of the value from the study), FB plus WATS was cost-effective at the $150K/QALY for a false positive rate below 56%. Using the worst case for false positive rate (25%), FB plus WATS was cost-effective at the $150K/QALY for added yield of over 38%.
CONCLUSION(S): We demonstrate that WATS, when used adjunctively with FB for screening 60 year old males with chronic GERD, is a cost-effective approach to reducing morbidity and mortality from esophageal cancer

INTRODUCTION: Missed lesions are considered a major cause of interval cancer of the colon. The new Automatic Polyp Detection System (APDS) from Magentiq Eye was developed to enhance the ability of endoscopists to detect polyps. It is designed for offline use with future real-time applications. The system uses recorded colonoscopy videos to assess endoscopist performance against the APDS. The APDS reviews the videos to generate a computerized automatic signature of polyps; a separate screen then shows the corresponding ?heat map' contour of areas suspicious for presence of polyps (see Figure 1).
METHOD(S): In this proof-of-concept study, the performance of the trained system was compared with a known testing database of 35 videos (each sequence approximately 30 seconds and 1000 frames). Overall, the testing database included 35,290 frames, with polyps found in the right colon (cecum and ascending colon, 10), transverse colon (5), and left colon (sigmoid and rectum, 20). Of the 35, 33 polyps were sessile and 2 were pedunculated; sizes ranged from less than 3 mm (10), 3 to 6 mm (16), 6 to 10 mm (5), and over 10 mm (4). Our goal was to define the optimal system working point in terms of sensitivity and specificity to detect polyps present in at least 3 consecutive frames. Physicians reviewed videos for polyps that were missed by the APDS and compare it with those missed by the endoscopists.
RESULT(S): The best working point of the system showed 88% sensitivity with 98.4% specificity (0.016 false positive rate). This resulted in a system polyp detection rate (SPDR) of 85.8% with 5 missed polyps. Missed lesions were found in the ascending (2), transverse (2), and descending (1) colon. All were sessile with sizes of less than 3 mm (1), 3 to 6 mm (3), 6 to 10 mm (1). The physicians missed 4 polyps found in the transverse colon (3) and descending colon (1). All polyps missed by physicians were sessile with sizes of less than 3 mm (1), 3 to 6 mm (2), and 6 to 10 mm (1). Only one polyp was missed both by the APDS and the physician.
CONCLUSION(S): Given that only one polyp was missed both by the APDS and the endoscopists, the APDS demonstrated the potential to behave as a complementary tool during colonoscopy in order to alert the endoscopist to lesions that may otherwise be missed, aiming to decrease the incidence of interval colon cancers

INTRODUCTION: Colorectal cancer remains the second leading cause of cancer death in the world. Incidence has declined as rates of screening colonoscopy have increased, but colonoscopy is not perfect. Low adenoma detection rates (ADR's) have been associated with increased interval cancers. Both optical and mechanical devices for improving ADR have shown promising results. Here we demonstrate a novel colonoscope with a 360degree integrated view to improve visualization behind folds (Figure 1). The aim of this study is to compare polyp detection rates using the novel 360degree scope and a standard forward only view (FOV) scope in colon models.
METHOD(S): 324 endoscopists around the US were enrolled in the study. 20 anatomic colon models (Champerlain Group, Great Barrington, MA) containing simulated 6-15 mm polyps were used. Polyps varied in number, location, and shape. Models were examined in a tandem fashion with the 360degree scope and the FOV scope. Endoscopists were randomly assigned to perform the initial exam with either scope. The primary outcome was the number of polyps identified during withdrawal. Subgroup analysis was performed evaluating effects of order of examination, experience, and practice setting. Means were compared with a paired T-test and subgroups were compared with ANOVA.
RESULT(S): 153 endoscopists performed their initial exam with the 360degree scope, and 171 with the FOV scope. The 360degree view colonoscope identified significantly more polyps overall (13.2 vs 7.7, mean difference 5.5, P< 0.0001). Each individual endoscopist identified more polyps with the 360degree scope. The difference persisted regardless of which scope was used first. The difference also persisted between endoscopists of different experience and practice environments (Table 1). The only statistically significant difference was between endoscopists stratified by years of training, in which the <5 year group had a larger difference in polyp detection (P=0.0006).
CONCLUSION(S): This study shows that the 360degree integrated view colonoscope is more effective at polyp detection than a traditional colonoscope in simulated models. The increased polyp detection is not dependent on experience level or practice environment. The expanded field of view allows endoscopists to identify polyps that may be missed by a traditional scope such as behind folds. Further studies in humans will be needed to prove safety/efficacy for clinical use but these initial results show promise for increasing ADR using this novel colonoscope (Figure Presented)