Detection of multiple lesions of gastrointestinal tract for endoscopy using artificial intelligence model: a pilot study.

BACKGROUND: This study was aimed to develop a computer-aided diagnosis (CAD) system with deep-learning technique and to validate its efficiency on detecting the four categories of lesions such as polyps, advanced cancer, erosion/ulcer and varices at endoscopy. METHODS: A deep convolutional neural network (CNN) that consists of more than 50 layers were trained with a big dataset containing 327,121 white light images (WLI) of endoscopy from 117,005 cases collected from 2012 to 2017. Two CAD models were developed using images with or without annotation of the training dataset. The efficiency of the CAD system detecting the four categories of lesions was validated by another dataset containing consecutive cases from 2018 to 2019. RESULTS: A total of 1734 cases with 33,959 images were included in the validation datasets which containing lesions of polyps 1265, advanced cancer 500, erosion/ulcer 486, and varices 248. The CAD system developed in this study may detect polyps, advanced cancer, erosion/ulcer and varices as abnormality with the sensitivity of 88.3% and specificity of 90.3%, respectively, in 0.05 s. The training datasets with annotation may enhance either sensitivity or specificity about 20%, p = 0.000. The sensitivities and specificities for polyps, advanced cancer, erosion/ulcer and varices reached about 90%, respectively. The detect efficiency for the four categories of lesions reached to 89.7%. CONCLUSION: The CAD model for detection of multiple lesions in gastrointestinal lumen would be potentially developed into a double check along with real-time assessment and interpretation of the findings encountered by the endoscopists and may be a benefit to reduce the events of missing lesions.

Negative-Pressure Isolation Mask for Endoscopic Examination During the Coronavirus Disease 2019 Pandemic: A Randomized Controlled Trial.

INTRODUCTION: During the coronavirus disease 2019 (COVID-19) pandemic, endoscopists have high risks of exposure to exhaled air from patients during gastroscopy. To minimize this risk, we transformed the oxygen mask into a fully closed negative-pressure gastroscope isolation mask. This study aimed to evaluate the effectiveness, safety, and feasibility of use of this mask during gastroscopy. METHODS: From February 28, 2020, to March 10, 2020, 320 patients undergoing gastroscopy were randomly assigned into the mask group (n = 160) or conventional group (n = 160). Patients in the mask group wore the isolation mask during gastroscopy, whereas patients in the conventional group did not wear the mask. The adenosine triphosphate fluorescence and carbon dioxide (CO2) concentration in patients' exhaled air were measured to reflect the degree of environmental pollution by exhaled air. Patients' vital signs, operation time, and adverse events during endoscopy were also evaluated. RESULTS: Four patients were excluded because of noncooperation or incomplete data. A total of 316 patients were included in the final analysis. The difference between the highest CO2 concentration around patients' mouth and CO2 concentration in the environment was significantly decreased in the mask group compared with the conventional group. There was no significant difference in the adenosine triphosphate fluorescence, vital signs, and operation time between the 2 groups. No severe adverse events related to the isolation mask, endoscopy failure, or new coronavirus infection during follow-up were recorded. DISCUSSION: This new isolation mask showed excellent feasibility of use and safety compared with routine gastroscopy during the COVID-19 pandemic.

Management of an endoscopy center during the outbreak of COVID-19: Experience from West China Hospital.

Since the outbreak of the coronavirus disease 2019 (COVID-19), various measures have been taken to protect against the infection. As droplet and contact transmission are the main routes of COVID-19 infection, endoscopy centers are considered to be high-risk areas for exposure to COVID-19. We have undertaken several countermeasures in our endoscopic center during the pandemic, and have gained significant experience in terms of prevention and control of COVID-19. We here present our experience and strategies adopted for preventing hospital infection in our endoscopy center during the COVID-19 pandemic. We describe our management of the environment, endoscope, patients, and medical staff, and our self-made masks.