Image recognition using artificial intelligence (AI) has dramatically developed with innovative technologies, such as machine learning and deep learning. Currently, it is considered that AI has exceeded human ability in terms of image recognition. In the field of gastric cancer, research on AI-based diagnosis, such as anatomical classification of esophagogastroduodenoscopy images, identification of Helicobacter pylori infection, and detection and qualitative diagnosis of gastric cancer, is being performed, and accuracy equivalent to that of endoscopists has been reported. Furthermore, AI that exceeds human ability will also transpire. However, medical AI has some drawbacks compared to existing medical devices, and there are major hurdles before its introduction to clinical practice. Currently, medical AI is regarded as a support tool that presents information that improves the efficiency of doctorsʼ work, and it is said that doctors will be the ones making the final diagnosis. It is expected that AI will be introduced in the medical field as a support tool for doctors, and the quality of medical care will improve in the near future.

[Objective] Sodium picosulfate/magnesium citrate (PICOPREP^Ⓡ) has been reported to have higher patient tolerability and a non-inferior colorectal cleansing effect compared with polyethylene glycol preparations. However, its colorectal cleansing effect appears to be poor in actual clinical practice. This study aimed to determine whether enhanced bowel preparation improves the colorectal cleansing effect of PICOPREP^Ⓡ while maintaining patient tolerability.

[Methods] Subjects were randomly assigned to either the PICOPREP^Ⓡ usual administration group (P/MC group) or the enhanced pretreatment group who additionally received 5 mL of 0.75% sodium picosulfate hydrate before bedtime on the previous day (enhanced P/MC group). The primary endpoint was the degree of colorectal cleansing on the Ottawa scale, and the secondary endpoint was tolerability.

[Results] The score for the degree of colorectal cleansing was significantly lower in the enhanced P/MC group (n = 49) than in the P/MC group (n = 49; 4.6 ± 0.5 vs. 6.6 ± 0.5; P＜0.001), showing a higher degree of cleansing in the enhanced P/MC group. Patient tolerability showed no significant difference between the two groups. There were no significant differences in the rates of complications between the two groups.

[Discussion] The addition of 0.75% sodium picosulfate hydrate to PICOPREP^Ⓡ improved its intestinal cleansing effect and maintained patient tolerability.

A 59-year-old man with a history of cardiac conduction disease underwent permanent pacemaker implantation. During his follow-up, gastrointestinal endoscopy performed as a medical checkup incidentally revealed varices from the upper to middle esophagus (F1, Cw, RC1(CRS)). The contrast-enhanced computed tomographic (CT) images demonstrated stenosis of the superior vena cava (SVC), a 7cm thrombus in the dilated right internal jugular vein and dilation of the azygous vein. He did not have portal hypertension, and the clinical diagnosis of downhill esophageal varices (DEV) due to SVC syndrome was made. To improve blood flow, he started anticoagulant treatment with rivaroxaban (15mg/day). Over five months of observation, the thrombus markedly decreased in size on CT imaging. The varices also improved one year after starting anticoagulant treatment. DEV is a rare form of esophageal varices induced by various causes, but there is no standard established treatment. We present a case of DEV due to SVC syndrome that was successfully treated with anticoagulant medicine.

Granulation polyps are found in the colorectum often in association with postoperative anastomotic sites or scars after endoscopic resection. Meanwhile, few cases of granulation polyps that occur in relation to colonic diverticula have been reported. Herein, we report three cases of diverticula-related granulation polyps in the colon. In all three cases, a reddish polyp that protruded from a diverticulum was found in the sigmoid colon. White exudate and tortuous capillaries were observed on the surface of the polyps. On magnifying endoscopic observation, the surface structure was unclear or had disappeared. We speculate that these endoscopic features are specific to granulation polyps in the colon. It is noteworthy that in one patient with laryngeal cancer, the polyp was false-positive for a tumor on positron emission tomography, showing significant tracer accumulation. Differentiation of granulation polyp from cancer metastasis to the colon is important in such patients. It is essential to be able to make a precise diagnosis of diverticula-related granulation polyp in the colon based on endoscopic features.

A 10-month-old boy with biliary atresia who had undergone the Kasai procedure, was admitted to our hospital due to tarry stool. We performed emergency esophagogastroduodenoscopy and found severe esophagogastric varices. There was a spurting bleeding site at the lower esophagus. We implemented endoscopic injection sclerotherapy (EIS) for esophagogastric variceal bleeding, since it was impossible to insert the scope through the esophagus with an endoscopic variceal ligation device attached. After performing four sessions of EIS, the patient developed esophageal ulcers and stricture related to EIS, leading to poor oral intake and body weight loss. We were able to manage these adverse events with conservative treatment. After healing of the esophageal ulcers and stricture, two additional sessions of EIS were performed. The patientʼs esophagogastric varices disappeared completely.

Intra-variceal EIS followed by para-variceal EIS by polidocanol was reported to be effective and relatively safe for the treatment of esophageal varices in adult patients. The aim of para-variceal EIS is to form ulcers at the injection sites, resulting in the development of fibrosis of the mucosa during the healing process. This mucosal fibrosis is considered important for preventing recurrence of varices. There is little evidence for the safety and efficacy of intra-variceal EIS followed by para-variceal EIS in pediatric patients.

Although we should be cautious of EIS-related stricture due to esophageal ulcer, especially in children who have a narrower esophageal lumen than adults, we have experienced a successful case of EIS for esophageal varices in an infant with biliary atresia.

An 82-year-old man was referred to our hospital with a complaint of hematuria. Bladder endoscopy revealed a mass lesion in the left side of the urinary bladder and urine cytology showed class Ⅴ. He was diagnosed with bladder carcinoma based on these results. Transurethral resection of the bladder tumor was performed. Histopathological examination showed features of small cell carcinoma. The pretreatment diagnosis was small cell carcinoma of the bladder, T3b N0 M0 stage Ⅳ according to the TMN classification. The patient was treated by systemic chemotherapy and radiation therapy. Eight months after diagnosis, he complained of jaundice and anorexia. Contrast-enhanced computed tomography revealed a hypovascular tumor in the pancreatic head with the largest diameter of 37mm. Endoscopic ultrasonography (EUS) revealed a 35mm lesion that contained hyper- and hypoechoic areas in the pancreatic head. EUS-guided fine needle aspiration (FNA) was performed and histopathological examination revealed small cell carcinoma. Immunohistochemical examination revealed synaptophysin- and CD56- positive, chromogranin-negative tumor cells, which were similar to the primary urinary bladder tumor cells. Thus, we diagnosed the lesion as pancreatic metastasis from small cell carcinoma of the urinary bladder. Despite chemotherapy with gemcitabine after diagnosis, the patient died two months later.

Colorectal obstruction (CO) is a complication that occurs at a certain frequency after patients take electrolyte lavage solution even with careful attention. Routine colonoscopy may lead to a serious iatrogenic outcome, in which a small percentage of patients may require colostomy, which would lead to a significant decrease in quality of life (QOL), and may sometimes even have a fatal course. However, in patients who develop CO after oral intake of electrolyte lavage solution, it may be possible to avoid emergency surgery by performing self-expandable metallic stent (SEMS) placement. We attempted SEMS placement in 8 of the 12 patients who developed CO after oral intake of electrolyte lavage solution. Stent placement was successfully performed in the 6 patients with stenosis due to circumferential type 2 lesions. We chose adaptations according to the Japan Colonic Stent Safe Procedure Research Group (JCSSPRG) Mini-Guidelines, and placement of a colonic stent for CO could be performed safely in cases of CO related to intake of electrolyte lavage solution. SEMS placement enables minimally invasive intestinal decompression, and it may be possible to avoid emergency surgery and deterioration of QOL.

Indigo carmine and Lugol are frequently used as dyes for chromoendoscopy in the upper gastrointestinal tract. Indigo carmine is used in portions of the digestive tract that are covered with columnar epithelium such as the stomach and duodenum. It does not chemically react with the cell surface or intracellular substances, and makes it easier to recognize minute changes by highlighting the unevenness of the mucosal surface. This is the so-called contrast method. Therefore, it is essential that the mucus on the surface is thoroughly flushed before indigo carmine is carefully sprayed. Lugol is a liquid containing iodine, glycerin, etc. The iodine-starch reaction occurs between iodine and glycogen granules contained in normal esophageal squamous epithelium, and the normal epithelium turns brown. However, in patients with esophageal cancer, the epithelium does not contain glycogen granules and does not turn brown upon Lugol spraying. The staining method using Lugol facilitates recognition of esophageal cancer due to the presence or absence of glycogen granules. In the case of multiple Lugol-voiding lesions, the so-called pink color sign in which the cancerous part turns pink within a few minutes after application of Lugol, is useful for distinguishing between cancerous and non-cancerous tissues.

In cholangiocarcinoma, preoperative diagnosis of local extension including invasion of the vessels and proximal and/or distal intraepithelial tumor spread (ITS) is important. The mode of local extension of cholangiocarcinoma greatly differs depending on the gross type of the main tumor. In general, the mode of local extension of cholangiocarcinoma is classified into two types: i) papillary and nodular type and ii) infiltrating type. The papillary and nodular type grossly appears as an elevated lesion with a relatively clearly formed border. In the papillary and nodular type, the incidence of extensive ITS, which is continuous with the main tumor and extends ≥ 2cm into the mucosal epithelium, is 25-36%. On the other hand, extramural invasion and submucosal intramural spread are common in the infiltrating type. In the infiltrating type, the incidence of extensive ITS is approximately 3-4%. Therefore, in order to perform curative resection, the extent of ITS into the bile duct mucosal epithelia must be accurately diagnosed in the papillary and nodular type, and the extent of submucosal intramural and extramural spread must be evaluated in the infiltrating type. In this article, the role of endoscopy in the evaluation and management of distal cholangiocarcinoma will be discussed.

Background and Aim: Few studies have reported on a national, population-based endoscopic retrograde cholangiopancreatography (ERCP) database. Hence, in 2015, we established a multicenter ERCP database registry, the Japan Endoscopic Database (JED) Project in preparation for a nationwide endoscopic database. The objective the present study was to evaluate this registry before the establishment of a nationwide endoscopic database.

Methods: From 1 January 2015 to 31 March 2017, we collected and analyzed the ERCP data of all patients who underwent ERCP in four participating centers in the JED Project based on the JED protocol.

Results: Four centers carried out 4,104 ERCP on 2,173 patients. Data entry of ERCP information (age, 100%; gender, 100%; American Society of Anesthesiologists Physical Status Classification System, 74.5%; scope, 92.7%; time to ERCP, 100%; antithrombotic drug information, 55.0%; primary selective common bile duct [CBD] cannulation methods, 73.0%; number of attempts at primary selective CBD cannulation, 67.6%; overall selective CBD cannulation methods, 68.9%; ERCP procedure time, 66.3%; fluoroscopy time, 65.1%; adverse events, 74.9%; serum amylase levels 1 day post- ERCP, 36.5%) was accurately extracted from the four centers. Success rate of CBD cannulation by level of ERCP difficulty was 98.5%, 99.0%, and 96.4% in grades 1, 2, and 3, respectively. Complication rate by overall selective CBD cannulation method was 5.6%, 7.6%, and 10.5% in the contrast-assisted technique, guidewire-assisted technique, and cross-over method, respectively.

Conclusion: Data from this evaluation of the JED Project, a multicenter ERCP database registry, suggest the feasibility of establishing a nationwide ERCP database and its challenges.