Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial.

BACKGROUND: This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett's esophagus (BE). METHODS: 96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level. RESULTS: AI had a stand-alone sensitivity, specificity, and accuracy of 92.2%, 68.9%, and 81.3%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3%, 58.1%, and 71.5%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8% [95%CI 65.2%-74.2%] to 78.0% [95%CI 74.0%-82.0%]; specificity 67.3% [95%CI 62.5%-72.2%] to 72.7% [95%CI 68.2%-77.3%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI. CONCLUSION: BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists' decisions to follow or discard AI advice.

Curative endoscopic full-thickness resection of a fundic gland-type gastric adenocarcinoma.

Video 1Summary of the presented case. Macroscopic images of the lesion in a white-light endoscopy and narrow-band imaging and in an underwater view followed by scenes from the resection with circular marking, submucosal injection, circumferential incision, and submucosal dissection using a multi-bend double-channel endoscope, as well as clip traction, controlled full-thickness dissection, and inspection of the defect plus closure of the defect with the clip-and-loop technique.

Effect of Real-Time Computer-Aided Polyp Detection System (ENDO-AID) on Adenoma Detection in Endoscopists-in-Training: A Randomized Trial.

BACKGROUND: The effect of computer-aided polyp detection (CADe) on adenoma detection rate (ADR) among endoscopists-in-training remains unknown. METHODS: We performed a single-blind, parallel-group, randomized controlled trial in Hong Kong between April 2021 and July 2022 (NCT04838951). Eligible subjects undergoing screening/surveillance/diagnostic colonoscopies were randomized 1:1 to receive colonoscopies with CADe (ENDO-AID[OIP-1]) or not (control) during withdrawal. Procedures were performed by endoscopists-in-training with <500 procedures and <3 years' experience. Randomization was stratified by patient age, sex, and endoscopist experience (beginner vs intermediate level, <200 vs 200-500 procedures). Image enhancement and distal attachment devices were disallowed. Subjects with incomplete colonoscopies or inadequate bowel preparation were excluded. Treatment allocation was blinded to outcome assessors. The primary outcome was ADR. Secondary outcomes were ADR for different adenoma sizes and locations, mean number of adenomas, and non-neoplastic resection rate. RESULTS: A total of 386 and 380 subjects were randomized to CADe and control groups, respectively. The overall ADR was significantly higher in the CADe group than in the control group (57.5% vs 44.5%; adjusted relative risk, 1.41; 95% CI, 1.17-1.72; P < .001). The ADRs for <5 mm (40.4% vs 25.0%) and 5- to 10-mm adenomas (36.8% vs 29.2%) were higher in the CADe group. The ADRs were higher in the CADe group in both the right colon (42.0% vs 30.8%) and left colon (34.5% vs 27.6%), but there was no significant difference in advanced ADR. The ADRs were higher in the CADe group among beginner (60.0% vs 41.9%) and intermediate-level (56.5% vs 45.5%) endoscopists. Mean number of adenomas (1.48 vs 0.86) and non-neoplastic resection rate (52.1% vs 35.0%) were higher in the CADe group. CONCLUSIONS: Among endoscopists-in-training, the use of CADe during colonoscopies was associated with increased overall ADR. (ClinicalTrials.gov, Number: NCT04838951).

Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm.

BACKGROUND AND AIMS: Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance. METHODS: A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 board-certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. RESULTS: External validation of the AI algorithm yielded values of 90%, 76%, and 84% for sensitivity, specificity, and accuracy, respectively. Fellows scored corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable. CONCLUSIONS: In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases.

Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm.

In this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63% and 76%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.

mTOR-mediated podocyte hypertrophy regulates glomerular integrity in mice and humans.

The cellular origins of glomerulosclerosis involve activation of parietal epithelial cells (PECs) and progressive podocyte depletion. While mammalian target of rapamycin-mediated (mTOR-mediated) podocyte hypertrophy is recognized as an important signaling pathway in the context of glomerular disease, the role of podocyte hypertrophy as a compensatory mechanism preventing PEC activation and glomerulosclerosis remains poorly understood. In this study, we show that glomerular mTOR and PEC activation-related genes were both upregulated and intercorrelated in biopsies from patients with focal segmental glomerulosclerosis (FSGS) and diabetic nephropathy, suggesting both compensatory and pathological roles. Advanced morphometric analyses in murine and human tissues identified podocyte hypertrophy as a compensatory mechanism aiming to regulate glomerular functional integrity in response to somatic growth, podocyte depletion, and even glomerulosclerosis - all of this in the absence of detectable podocyte regeneration. In mice, pharmacological inhibition of mTOR signaling during acute podocyte loss impaired hypertrophy of remaining podocytes, resulting in unexpected albuminuria, PEC activation, and glomerulosclerosis. Exacerbated and persistent podocyte hypertrophy enabled a vicious cycle of podocyte loss and PEC activation, suggesting a limit to its beneficial effects. In summary, our data highlight a critical protective role of mTOR-mediated podocyte hypertrophy following podocyte loss in order to preserve glomerular integrity, preventing PEC activation and glomerulosclerosis.