Remote Intelligent Assisted Diagnosis System for Hepatic Echinococcosis

Abstract

Hepatic echinococcosis (HE) is a serious parasitic disease. Because of its high efficiency and no side effects, ultrasound is the preferred method for the diagnosis of HE. However, HE mainly occurs in remote pastoral areas, where the economy is underdeveloped, medical conditions are backward, and ultrasound specialists are inadequate. Therefore, it is difficult for patients to receive timely and effective diagnosis and treatment. To address this issue, we propose a remote intelligent assisted diagnosis system for HE. Our contributions are twofold. First, we propose a novel hybrid detection network based on neural architecture search (NAS) for the intelligent assisted diagnosis of HE. Second, we propose a tele-operated robotic ultrasound system for the remote diagnosis of HE to mitigate the shortage of professional sonographers in remote areas. The experiments demonstrate that our hybrid detection network obtains mAP of 74.9% on a dataset of 2258 ultrasound images from 1628 patients. The efficacy of the proposed tele-operated robotic ultrasound system is verified in a remote clinical application trial of 90 HE patients with an accuracy of 86.7%. This framework provides an accurate and automatic remote intelligent assisted diagnostic tool for HE screening and has a good clinical application prospect.