Esophagogastric varices (EGVs) are a disease that occurs as a complication of the progression of liver cirrhosis, and since bleeding can be fatal, regular endoscopy is necessary. With the development of artificial intelligence (AI) in recent years, it is beginning to be applied to predicting the presence of EGVs, predicting bleeding, and making a diagnosis and prognosis. Based on previous reports, application methods of AI can be classified into the following four categories: (1) noninvasive prediction using clinical data obtained from clinical records such as laboratory data, past history, and present illness, (2) invasive detection and prediction using endoscopy and computed tomography (CT), (3) invasive prediction using multimodal AI (clinical data and endoscopy), (4) invasive virtual measurement on the image of endoscopy and CT. These methods currently allow for the use of AI in the following ways: (1) prediction of EGVs existence, variceal grade, bleeding risk, and survival rate, (2) detection and diagnosis of esophageal varices (EVs), (3) prediction of bleeding within 1 year, (4) prediction of variceal diameter and portal pressure gradient. This review explores current studies on AI applications in assessing EGVs, highlighting their benefits, limitations, and future directions.
Bilateral uncovered metal stent (UMS) placement is recommended for unresectable malignant hilar biliary obstructions (MHBO). However, recent improvements in antitumor therapies and patient survival have led to an increasing number of patients outliving UMS patency, necessitating more frequent reinterventions. This study evaluated the efficacy of novel suprapapillary stent-by-stent (SBS) placement using slim fully covered metal stents (FCMS) and compared them with UMS.
A total of 254 patients were included. Technical and clinical success, adverse events (AEs) including recurrent biliary obstruction (RBO), and reintervention were compared between the FCMS and UMS groups. Propensity score matching was performed to adjust for between-group differences.
Technical and clinical success rates and early and late AE rates were not significantly different between the groups. The FCMS group demonstrated a significantly lower RBO incidence rate (32.0% vs. 60.8%; p = 0.005) and a significantly longer time to RBO (median, NA vs. 204 days; p = 0.048). However, in the FCMS group, 4.0% of patients required stent removal because of suspected branch occlusion. The technical success rates of reintervention were 100% and 83.3% in the FCMS and UMS groups (p = 0.147), respectively. Compared to the UMS group, the FCMS group demonstrated a significantly shorter reintervention procedure time (median, 20 vs. 31 min; p = 0.005) and a significantly lower number of reinterventions (p = 0.029) and requirement for repeat reinterventions (p = 0.003).
Suprapapillary slim FCMS SBS placement may be a promising treatment option for patients with unresectable MHBO. However, early and unique events requiring stent removal should be carefully considered.
This pivotal study aimed to evaluate the performance of the CAD-EYE prototype in identifying esophageal squamous cell carcinoma (ESCC) and gastric neoplasm (GN) for regulatory approval of the Pharmaceuticals and Medical Devices Agency in Japan.
This retrospective study utilized image datasets comprising 15 consecutive video frames captured using non-magnifying white-light imaging (WLI), blue laser/light imaging (BLI), and linked color imaging (LCI). The sensitivity and specificity of the CAD-EYE prototype for successful detection were calculated using the gold standard, which consists of image datasets of neoplastic lesions annotated by experienced endoscopists.
A total of 620, 679, and 682 ESCC datasets were analyzed in the WLI, BLI, and LCI groups, respectively. The sensitivity and specificity of ESCC detection were 85.9% [81.1%–90.6%] and 93.3% [90.8%–95.7%] in the WLI group, 97.6% [95.6%–99.7%] and 92.9% [90.6%–95.3%] in the BLI group, and 96.6% [94.2%–99.1%] and 93.2% [91.0%–95.5%] in the LCI group. The sensitivities for pT1a ESCC were 85.3%, 97.3%, and 97.2% in the WLI, BLI, and LCI groups, respectively. For GN, 841 WLI and 882 LCI datasets were analyzed. The sensitivity, specificity, and specificity in the detection flag of GN detection were 95.5% [92.8%–98.1%], 86.1%, and 85.4% [82.6%–88.2%] in the WLI group, and 93.9% [91.1%–96.7%], 94.4%, and 93.9% [92.0%–95.8%] in the LCI group, respectively. The sensitivities for pT1a early gastric cancer were 93.8% and 92.4% in the WLI and LCI groups, respectively.
The CAD-EYE prototype demonstrated high sensitivity in detecting ESCC and GN, highlighting its potential as a promising tool for clinical applications.
Difficult biliary cannulation is a key challenge in endoscopic retrograde cholangiopancreatography and a major risk factor for post-ERCP pancreatitis. When the pancreatic duct is unintentionally accessed, double guidewire (DGW) is the primary rescue strategy, while transpancreatic sphincterotomy (TPS) is an alternative. Previous evidence suggests that TPS may achieve higher cannulation success and lower PEP rates compared to DGW, though direct comparative data remain limited. This review and meta-analysis assess the clinical outcomes of TPS and DGW in the setting of difficult biliary cannulation.
This review involved searching Medline, Embase, Lilacs, Central Cochrane, and Google Scholar. Outcomes assessed included PEP, successful biliary cannulation, mean cannulation time, and other adverse events (bleeding, cholangitis, perforation).
A total of 463 patients from five randomized controlled trials were included. The DGW group showed a higher risk of PEP pancreatitis and other adverse events (p = 0.009; RR = 1.81 [1.16, 2.83]; I2 = 34%) and (p = 0.03; RR = 2.20 [1.10, 4.39]; I2 = 0%), respectively. A significant difference favoring TPS was found for successful cannulation and mild pancreatitis (p = 0.001; RR = 1.79 [1.26, 2.54]; I2 = 40%) and (p = 0.01; RR = 2.26 [1.20, 4.28]; I2 = 35%), respectively. No significant difference was observed for mean cannulation time or moderate to severe PEP (p = 0.18; SMD = −0.37 [−0.91, 0.17]; I2 = 79%) and (p = 0.32; RR = 1.50 [0.67, 3.36]; I2 = 0%), respectively. A restricted analysis excluding two studies affected by external factors inflating the pancreatitis rate did not reveal a significant difference (p = 0.61; RR = 1.16 [0.66, 2.04]; I2 = 0%).
Prior studies comparing TPS and DGW yield different results. This may occur because there are technical variables that are difficult to control. Overall, TPS demonstrated superior cannulation success, may have lower PEP rates, and fewer other complications, although more homogeneous studies are needed to validate these findings.
Percutaneous transhepatic gallbladder drainage (PTGBD) is often the first-line treatment for acute cholecystitis in high-risk patients. However, PTGBD may cause discomfort, leading to self-removal of the drainage tube and severe complications such as biliary peritonitis [1]. As an alternative, endoscopic transpapillary gallbladder drainage (ETGBD) has gained popularity, though it presents challenges like difficult cystic duct cannulation and stent occlusion due to gallstones in narrow-diameter stents [2]. Recently, acute cholecystitis was successfully treated by endoscopic ultrasound-guided gallbladder drainage (EUS-GBD) using a lumen-apposing metal stent (LAMS) [3]. Here, we report a case. A 93-year-old man was transported to our hospital with moderate acute cholecystitis. Initial antibiotic therapy led to temporary improvement, but symptoms recurred upon discontinuation. PTGBD was performed (Figure 1a), but on postoperative day 6, the patient developed an elevated serum CRP level (7.65 mg/dL). The abdominal x-ray revealed spontaneous removal of the drainage tube (Figure 1b). Despite further antibiotic treatment, cholecystitis due to gallstone impaction in the cystic duct recurred after stopping therapy. EUS-GBD was then indicated for sustained drainage. The gallbladder was punctured between the duodenal bulb and the superior duodenal angle under EUS guidance. The distal flange of the LAMS was deployed inside the gallbladder, then pulled back to appose it to the duodenal wall. Under fluoroscopic guidance, deployment of both flanges was confirmed, and drainage of purulent bile was observed (Video S1). The abdominal CT finding 4 days after EUS-GBD showed the stent was patent (Figure 2), so antibiotic administration was discontinued. The patient was discharged 8 days after EUS-GBD. Approximately 2 months have passed as EUS-GBD without removal of the LAMS, and no recurrence of cholecystitis has been observed. In this case, EUS-GBD using LAMS was a safe and effective treatment for a super-elderly patient with a high surgical risk.
Conception and design of the study: R.R., K.K., T.I. Drafting and revision of the manuscript: R.R., K.K., T.I. Approval of the final version of the manuscript: R.R., K.K., T.I.
The authors have nothing to report.
Informed consent was obtained from the patient regarding the procedure.
The authors declare no conflicts of interest.
For the management of walled-off necrosis (WON), applying direct endoscopic necrosectomy (DEN) to endoscopic ultrasound (EUS)-guided drainage reportedly accelerates disease resolution [1, 2]. However, conventional removal using grasping forceps can lead to prolonged procedures due to adhesive necrotic tissue, thereby reducing efficiency. The novel over-the-scope grasper (OTSG Xcavator; Ovesco Endoscopy AG, Tübingen, Germany) has been introduced recently [3]. Here, we describe a case in which the over-the-scope grasper (OTSG) was effectively used, outlining the key procedural steps along with practical tips that facilitated effective removal of necrotic tissue.
A 54-year-old man developed WON after severe acute pancreatitis (Figure 1). Despite multiple DEN sessions via the transgastric lumen-apposing metal stent (LAMS), necrotic tissue remained. During the fourth session, the OTSG was introduced. This involved applying an overtube to facilitate repeated extracorporeal removal of necrotic tissue. The procedure consisted of a three-step routine: (1) access via the LAMS into the WON, (2) grasping necrotic tissue using the OTSG, and (3) withdrawing the scope for extracorporeal release. A frequent complication was impaired vision from lens contamination by oil-rich tissues, which was managed with an anti-fog solution and olive oil coating between sessions (Video S1). A substantial volume of necrotic tissue was successfully removed during a single 60-min procedure without adverse events (Figure 2a–g). The patient underwent several additional conventional DEN sessions and was discharged 1 month after admission with near-complete resolution of the WON (Figure 2h).
One published study has demonstrated the safety and efficacy of the OTSG [3]. However, opening or closing the OTSG in confined spaces may injure vessels beneath debris. A key drawback of the OTSG is its larger tip diameter, which limits maneuverability. Therefore, it remains effective for a large single cavity WON. The OTSG facilitated effective DEN; however, further studies are required to validate its efficacy and safety.
Akira Shirohata conceived the study, acquired images, and drafted the manuscript. Arata Sakai and Atsuhiro Masuda contributed to the data interpretation, literature review, and critical revision of the manuscript.
The authors declare no conflicts of interest.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：