Yoon Jin Choi, Yong Chan Lee, Jung Mogg Kim, Jin Il Kim, Jeong Seop Moon, Yun Jeong Lim, Gwang Ho Baik, Byoung Kwan Son, Hang Lak Lee, Kyoung Oh Kim, Nayoung Kim, Kwang Hyun Ko, Hye-Kyung Jung, Ki-Nam Shim, Hoon Jai Chun, Byung-Wook Kim, Hyuk Lee, Jie-Hyun Kim, Hyunsoo Chung, Sang Gyun Kim, and Jae Young Jang. Gut and Liver 2022;16:535-46. https://doi.org/10.5009/gnl220055

Min Kyu Jung, Akinkunmi Paul Okekunle, Jung Eun Lee, Mi Kyung Sung, Yun Jeong Lim. J Cancer Prev 2021;26:237-43. https://doi.org/10.15430/JCP.2021.26.4.237

Choi JH, et al. Yonsei Med J. 2013 Jan;54(1):160-165. https://doi.org/10.3349/ymj.2013.54.1.160

Neuroendocrine tumors (NETs) of the esophagus are extremely rare, and few cases have been reported worldwide. Thus, a comprehensive nationwide study is needed to understand the characteristics of and treatment strategy for esophageal NETs. We collected data on esophageal NET patients from 25 hospitals in Korea from 2002–2012. The incidence, location, clinical symptoms, histopathology, treatment response, and the biochemical, radiologic and endoscopic characteristics of esophageal NETs were surveyed. Among 2,037 NETs arising in different gastrointestinal sites, esophageal NETs were found in 26 cases (1.3%). The mean patient age was 60.12 ± 9.30 years with a 4:1 male predominance. In endoscopic findings, 76.9% (20/26) of NETs were located in the lower third of the esophagus and the mean size was 2.34 ± 1.63 cm. At diagnosis, more than half the patients (15/26, 57.7%) had regional lymph node metastasis or widespread metastasis. Endoscopic resection was conducted in three cases, and in all three of them, lymph node metastasis was not found and tumor size was below 1.0 cm. All tumors were completely removable through endoscopic procedures and there was no recurrence during the follow-up period. Eighteen other patients received an operation, chemotherapy or both. Among them, nine patients (50.0%) expired because of the progression of their cancer or post-operative complications. In Kaplan-Meier survival analysis, only tumor size (more than 2.0 cm) showed prognostic significance (P = 0.045). Despite the general assumption that gastrointestinal NETs are benign and slow-growing tumors, the prognosis of advanced esophageal NETs is not favorable.

Endoscopic investigation has a critical role in the diagnosis and treatment of gastrointestinal (GI) diseases. Since 2001, capsule endoscopy (CE) has been available for small-bowel exploration and is under continuous development. During the past decade, CE has achieved impressive improvements in areas such as miniaturization, resolution, and battery life. As a result, CE is currently a first-line tool for the investigation of the small bowel in obscure gastrointestinal bleeding and is a useful alternative to wired enteroscopy. Nevertheless, CE still has several limitations, such as incomplete examination and limited diagnostic and therapeutic capabilities. To resolve these problems, many groups have suggested several models (e.g., controlled CO2 insufflation system, magnetic navigation system, mobile robotic platform, tagging and biopsy equipment, and targeted drug-delivery system), which are in development. In the near future, new technological advances will improve the capabilities of CE and broaden its spectrum of applications not only for the small bowel but also for the colon, stomach, and esophagus. The purpose of this review is to introduce the current status of CE and to review the ongoing development of solutions to address its limitations.

A standardized small bowel (SB) cleansing scale is currently not available. The aim of this study was to develop an automated calculation software for SB cleansing score using deep learning. Consecutively performed capsule endoscopy cases were enrolled from three hospitals. A 5-step scoring system based on mucosal visibility was trained for deep learning in the training set. Performance of the trained software was evaluated in the validation set. Average cleansing score (1.0 to 5.0) by deep learning was compared to clinical grading (A to C) reviewed by clinicians. Cleansing scores decreased as clinical grading worsened (scores of 4.1, 3.5, and 2.9 for grades A, B, and C, respectively, P < 0.001). Adequate preparation was achieved for 91.7% of validation cases. The average cleansing score was significantly different between adequate and inadequate group (4.0 vs. 2.9, P < 0.001). ROC curve analysis revealed that a cut-off value of cleansing score at 3.25 had an AUC of 0.977. Diagnostic yields for small, hard-to-find lesions were associated with high cleansing scores (4.3 vs. 3.8, P < 0.001). We developed a novel scoring software which calculates objective, automated cleansing scores for SB preparation. The cut-off value we suggested provides a standard criterion for adequate bowel preparation as a quality indicator.