Search

Background There are several types of pancreatic mass, so it is important to distinguish between them before treatment. Artificial intelligence (AI) is a mathematical technique that automates learning and recognition of data patterns. This study aimed to investigate the efficacy of our AI model using endoscopic ultrasonography (EUS) images of multiple types of pancreatic mass (pancreatic ductal adenocarcinoma [PDAC], pancreatic adenosquamous carcinoma [PASC], acinar cell carcinoma [ACC], metastatic pancreatic tumor [MPT], neuroendocrine carcinoma [NEC], neuroendocrine tumor [NET], solid pseudopapillary neoplasm [SPN], chronic pancreatitis, and autoimmune pancreatitis [AIP]). Methods Patients who underwent EUS were included in this retrospective study. The included patients were divided into training, validation, and test cohorts. Using these cohorts, an AI model that can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions was developed using a deep-learning architecture and the diagnostic performance of the AI model was evaluated. Results 22 000 images were generated from 933 patients. The area under the curve, sensitivity, specificity, and accuracy (95 %CI) of the AI model for the diagnosis of pancreatic carcinomas in the test cohort were 0.90 (0.84–0.97), 0.94 (0.88–0.98), 0.82 (0.68–0.92), and 0.91 (0.85–0.95), respectively. The per-category sensitivities (95 %CI) of each disease were PDAC 0.96 (0.90–0.99), PASC 1.00 (0.05–1.00), ACC 1.00 (0.22–1.00), MPT 0.33 (0.01–0.91), NEC 1.00 (0.22–1.00), NET 0.93 (0.66–1.00), SPN 1.00 (0.22–1.00), chronic pancreatitis 0.78 (0.52–0.94), and AIP 0.73 (0.39–0.94). Conclusions Our developed AI model can distinguish pancreatic carcinomas from noncarcinomatous pancreatic lesions, but external validation is needed.

Background and study aims Anastomotic stricture is a late complication after biliary reconstructive surgery, but standard treatments are currently lacking. We selected patients who had undergone pancreaticoduodenectomy and Child’s procedure, and aimed to evaluate the safety and efficacy of temporary placement of fully covered self-expandable metal stents (FCSEMSs) to treat postoperative anastomotic stricture. Patients and methods This study retrospectively analyzed 13 patients who underwent treatment with FCSEMSs for anastomotic stricture between June 2011 and March 2016. We evaluated technical and clinical success, complications, duration of patency after FCSEMS removal, and re-stenosis. Results All of the anastomotic strictures were improved by FCSEMS placement and luminal patency was maintained throughout the follow-up period, with no complications. After 2 months, the FCSEMSs were removed endoscopically in nine patients, and in four patients the stent had been expelled spontaneously per rectum. Median duration of follow-up was 225 days (range 30 – 935 days). No re-stenosis occurred in any of the 13 cases following stent removal. Conclusion Deployment of FCSEMSs for anastomotic stricture offers a safe and promising treatment that may replace percutaneous transhepatic biliary drainage and deployment of multiple plastic stents as the first-line treatment.

BACKGROUND AND STUDY AIM Malignancy in pancreatic neuroendocrine tumors (PNETs) is graded by assessing the resected specimens according to the World Health Organization (WHO) 2010 criteria. The feasibility of such grading using endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) specimens remains unclear. The aim of this study was to ascertain the optimal method of measuring the Ki-67 index in EUS-FNA specimens, using resected specimens as the criterion standard. PATIENTS AND METHODS A total of 58 consecutive patients diagnosed with PNETs between March 1998 and May 2011 were included. The study measured intratumoral Ki-67 index heterogeneity, concordance rates of PNET grading by EUS-FNA with grade of the resected tumor, optimal method of measuring the Ki-67 index in EUS-FNA specimens, and survival analysis based on EUS-FNA specimen grading. RESULTS Intratumoral dispersion of Ki-67 index in resected specimens was 0.033 for Grade 1 and 0.782 for Grade 2 tumors (P

Endoscopic ultrasound-guided fine-needle tattooing (EUS-FNT) is an ideal technique for preoperative marking of lesions detected on preoperative examination. Although India ink has been used for endoscopic tattooing, there have been numerous reports of complications associated with its use. This is the first report of EUS-FNT using indocyanine green (ICG) and describes its use for preoperative marking of a tumor in a 78-year-old man with multiple pancreatic tumors. There were no complications associated with the EUS-FNT procedure and it is suggested that ICG is a more suitable dye for tattooing of pancreatic lesions than India ink, being far less frequently associated with side effects.

A prospective clinical study was conducted to evaluate the safety, feasibility, and efficacy of endoscopic ultrasound (EUS)-guided choledochoduodenostomy (CDS) with direct metallic stent placement using a prototype forward-viewing echoendoscope. The indication for EUS – CDS in this study was lower biliary obstruction only, and not failed endoscopic biliary drainage, because the aim was to evaluate EUS – CDS for first-line biliary drainage therapy. The technical and functional success rates were 94 % (17 /18) and 94 % (16 /17), respectively. Early complications (focal peritonitis) were encountered in two patients (11 %). No patients developed late complications. EUS – CDS with direct metallic stent placement using a forward-viewing echoendoscope was generally feasible and effective for malignant distal biliary tract obstruction. The forward-viewing echoendoscope was useful, especially for deploying the metallic stent.

BACKGROUND AND STUDY AIMS: Side-branch intraductal papillary mucinous neoplasms (SB-IPMNs), and associated synchronous and metachronous pancreatic cancers are increasingly detected as imaging modalities become more sensitive. We investigated the natural history of SB-IPMN, and the incidence and characteristics of pancreatic cancers among patients undergoing long-term follow-up. PATIENTS AND METHODS: We reviewed the clinical, imaging, and pathological features in 103 patients, diagnosed at the Aichi Cancer Center between September 1988 and September 2006 as having SB-IPMN, and conservatively followed up for ≥ 2 years (median 59 months) based on an endoscopic ultrasonography (EUS) database. RESULTS: 74 (71.8 %) patients had nonprogressive lesions. Overall, six patients (5.8 %) developed pancreatic cancers during follow-up, with intraductal papillary mucinous (IPM) carcinoma in four, and ductal carcinoma of pancreas that was not IPMN in two patients. Of the six pancreatic cancers, five were diagnosed at a resectable stage. The 5-year and 10-year actuarial rates of development of pancreatic cancer were 2.4 % and 20.0 %, respectively. Although, at the last follow-up, cyst size, main pancreatic duct (MPD) diameter, mural nodule size, and frequency of metachronous and/or synchronous cancers of other organs were significantly higher in patients who developed IPM carcinoma, resected SB-IPMNs without mural nodules and dilated MPDs had no IPM carcinomas. CONCLUSIONS: The frequency of pancreatic cancers is high on long-term follow-up of SB-IPMN. Although conservative management is appropriate for selected patients, regular and long-term imaging, especially by EUS is essential, even if SB-IPMN remains unchanged for 2 years. Presence of mural nodule and dilated MPD seem to be more appropriate indicators for resection than cyst size alone for SB-IPMNs.

Five patients with obstructive jaundice caused by malignant periampullary biliary stenosis underwent EUS-guided choledochoduodenostomy (EUS-CDS) from the first portion of the duodenum using a convex echoendoscope and a needle knife. All the steps of the procedure including passage dilatation and the plastic stent placement were performed through the accessory channel of the echoendoscope over the guide wire. Stent insertion was technically successful in all five patients. The procedure was also clinically effective in relieving jaundice in all cases. One patient developed pneumoperitoneum, which resolved with conservative management. Stent exchange was successful in seven of eight attempts in patients with stent occlusion. One failure was due to tumor invasion to the choledochoduodenal fistula. Stent patency was maintained in the remaining patients throughout their survival period. The average stent patency was 211.8 days. EUS-CDS from the first portion of the duodenum appears to be feasible and safe in cases of obstructive jaundice caused by distal bile duct obstruction.