Clinical Outcome of Endoscopic Ultrasound-Guided Liver Abscess Drainage Using Self-Expandable Covered Metallic Stent (with Video).

BACKGROUND: Percutaneous drainage (PCD) is now the first-line drainage method for liver abscess because of its minimal invasiveness and high technical success rate. However, this procedure has several disadvantages, such as extra-drainage and self-tube removal. Recently, EUS-guided liver abscess drainage (EUS-AD) has been developed. However, only a few reports of EUS-AD have been reported. In addition, the clinical benefits of PCD and EUS-AD have not been reported. AIMS: In the present study, the safety and feasibility of EUS-AD using fully covered SEMS (FCSEMS) and the clinical outcomes of EUS-AD and PCD were examined retrospectively. METHODS: Twenty-seven consecutive patients who underwent PCD or EUS-AD between April 2012 and April 2015 were included in this study. EUS-AD was performed using FCSEMS. In addition, to prevent stent migration, 7-Fr pig tail plastic stent was placed within FCSEMS. RESULTS: Technical success was achieved in all patients of both groups. Clinical success was 100 % in the EUS-AD group although it was 89 % in PCD group (P = 034). Three adverse events were seen in the PCD group (self-tube removal n = 1, tube migration n = 2), but no adverse events were seen in the EUS-AD group. The median hospital stay was significantly shorter in the EUS-AD group than in the PCD group (21 vs 41 days, P = 0.03). CONCLUSION: Because of the short hospital stay, the high clinical success rate, and the low adverse event rate compared to PCD, EUS-AD has potential as a first-line treatment for liver abscess.

Artificial intelligence and computer-aided diagnosis for colonoscopy: where do we stand now?

Computer-aided diagnosis (CAD) for colonoscopy with use of artificial intelligence (AI) is catching increased attention of endoscopists. CAD allows automated detection and pathological prediction, namely optical biopsy, of colorectal polyps during real-time endoscopy, which help endoscopists avoid missing and/or misdiagnosing colorectal lesions. With the increased number of publications in this field and emergence of the AI medical device that have already secured regulatory approval, CAD in colonoscopy is now being implemented into clinical practice. On the other side, drawbacks and weak points of CAD in colonoscopy have not been thoroughly discussed. In this review, we provide an overview of CAD for optical biopsy of colorectal lesions with a particular focus on its clinical applications and limitations.