A feasibility study of an algorithm that identifies ascites on image-guided paracentesis.

Prompt management of ascites via image-guided paracentesis can provide therapy for patients with ascites and identify potentially fatal infections. However, not all medical facilities have trained providers readily available. The goal of this study was to develop an algorithm that can reliably identify and localize ascites on abdominal ultrasound images autonomously. The proposed algorithm was developed via OpenCV image processing library on Python software and analyzed 16 random abdominal ultrasound images with multiple views to validate the software. The algorithm identified 100% of targeted ascitic regions. This study suggests that the proposed algorithm is a reliable tool for ascites detection.