Efficacy and safety of piecemeal submucosal tunneling endoscopic resection for giant esophageal leiomyoma.

BACKGROUND AND AIMS: Giant esophageal leiomyoma usually requires a thoracotomy or thoracoscopic surgery, which is more invasive than an endoscopic treatment. The purpose of this study is to evaluate the efficacy and safety of piecemeal submucosal tunneling endoscopic resection (P-STER) for giant leiomyoma originating from the muscularis propria (MP) layer of the esophagus. METHODS: This is a retrospective study. Patients with giant esophageal leiomyoma (transverse diameter ≥ 3 cm) who underwent P-STER were enrolled from November 2012 to May 2023. Clinical data and results were investigated. RESULTS: A total of 16 patients were enrolled for analysis. The lesion mean transverse diameter and longitudinal diameter were 4.22 ± 1.20 cm and 6.20 ± 1.57 cm, respectively. Our mean operation time was 195.38 ± 84.99 min. The mean number of piecemeal resected was 4.31 ± 2.36. An adverse event noted was an esophageal fistula that occurred in one case (6.25%) and was treated conservatively. The mean length of hospital stay was around 11.81 ± 7.30 days. The mean total hospitalization cost was U.S. dollars (USD) $5976.50 ± 2866.39. No recurrence or metastasis was found during the follow-up period. CONCLUSIONS: P-STER can be an effective and safe treatment for giant leiomyoma originating from the MP layer of the esophagus.

Magnifying image-enhanced endoscopy-only mode boosted early cancer diagnostic efficiency: a multicenter randomized controlled trial.

BACKGROUND AND AIMS: Magnifying image-enhanced endoscopy (MIEE) is an advanced endoscopy with image enhancement and magnification used in preoperative examination. However, its impact on the detection rate is unknown. METHODS: We conducted an open-label, randomized, parallel (1:1:1), controlled trial in 6 hospitals in China. Patients were recruited between February 14, 2022 and July 30, 2022. Eligible patients were aged ≥18 years and undergoing gastroscopy in outpatient departments. Participants were randomly assigned to the MIEE-only mode (o-MIEE) group, white-light endoscopy-only mode (o-WLE) group, and MIEE when necessary mode (n-MIEE) group (initial WLE followed by switching to another endoscope with MIEE if necessary). Biopsy sampling of suspicious lesions of the lesser curvature of the gastric antrum was performed. Primary and secondary aims were to compare detection rates and positive predictive value (PPV) of early cancer and precancerous lesions in these 3 modes, respectively. RESULTS: A total of 5100 recruited patients were randomly assigned to the o-MIEE (n = 1700), o-WLE (n = 1700), and n-MIEE (n = 1700) groups. In the o-MIEE, o-WLE, and n-MIEE groups, 29 (1.51%; 95% confidence interval [CI], 1.05-2.16), 4 (.21%; 95% CI, .08-.54), and 8 (.43%; 95% CI, .22-.85) early cancers were found, respectively (P < .001). The PPV for early cancer was higher in the o-MIEE group compared with the o-WLE and n-MIEE groups (63.04%, 33.33%, and 38.1%, respectively; P = .062). The same trend was seen for precancerous lesions (36.67%, 10.00%, and 21.74%, respectively). CONCLUSIONS: The o-MIEE mode resulted in a significant improvement in diagnosing early upper GI cancer and precancerous lesions; thus, it could be used for opportunistic screening. (Clinical trial registration number: ChiCTR2200064174.).

Development and Validation of an Artificial Intelligence Model for Small Bowel Capsule Endoscopy Video Review.

Importance: Reading small bowel capsule endoscopy (SBCE) videos is a tedious task for clinicians, and a new method should be applied to solve the situation. Objectives: To develop and evaluate the performance of a convolutional neural network algorithm for SBCE video review in real-life clinical care. Design, Setting, and Participants: In this multicenter, retrospective diagnostic study, a deep learning neural network (SmartScan) was trained and validated for the SBCE video review. A total of 2927 SBCE examinations from 29 medical centers were used to train SmartScan to detect 17 types of CE structured terminology (CEST) findings from January 1, 2019, to June 30, 2020. SmartScan was later validated with conventional reading (CR) and SmartScan-assisted reading (SSAR) in 2898 SBCE examinations collected from 22 medical centers. Data analysis was performed from January 25 to December 31, 2021. Exposure: An artificial intelligence-based tool for interpreting clinical images of SBCE. Main Outcomes and Measures: The detection rate and efficiency of CEST findings detected by SSAR and CR were compared. Results: A total of 5825 SBCE examinations were retrospectively collected; 2898 examinations (1765 male participants [60.9%]; mean [SD] age, 49.8 [15.5] years) were included in the validation phase. From a total of 6084 CEST-classified SB findings, SSAR detected 5834 findings (95.9%; 95% CI, 95.4%-96.4%), significantly higher than CR, which detected 4630 findings (76.1%; 95% CI, 75.0%-77.2%). SmartScan-assisted reading achieved a higher per-patient detection rate (79.3% [2298 of 2898]) for CEST findings compared with CR (70.7% [2048 of 2298]; 95% CI, 69.0%-72.3%). With SSAR, the mean (SD) number of images (per SBCE video) requiring review was reduced to 779.2 (337.2) compared with 27 910.8 (12 882.9) with CR, for a mean (SD) reduction rate of 96.1% (4.3%). The mean (SD) reading time with SSAR was shortened to 5.4 (1.5) minutes compared with CR (51.4 [11.6] minutes), for a mean (SD) reduction rate of 89.3% (3.1%). Conclusions and Relevance: This study suggests that a convolutional neural network-based algorithm is associated with an increased detection rate of SBCE findings and reduced SBCE video reading time.