LAUSR

Early diagnosis of esophageal squamous cell carcinoma (ESCC) is crucial for improving its prognosis. Effective endoscopic biopsy is key to ensuring nomissed diagnoses or misdiagnosis of lesions occur and accurate delineation of the margins of lesions is essential for effective biopsies. Recently, the application of artificial intelligence (AI) in the endoscopic diagnosis of early ESCC has increased; however, most AI systems identified early ESCC with rough square frames [1–3]. For the purpose of precise lesion segmentation, we have developed a new AI system, based on a state-of-the-art algorithm called the YOLACT model [4], that integrates multiple endoscopic imaging modalities to detect and delineate the margins of early ESCC in real time. The AI systemwas successfully integrated into the endoscopy equipment. The upper left section of the endoscopy monitor showed the current endoscopic imaging modality and the probability score of suspected early ESCC. In this video demonstration, we show that the AI system not only correctly identified each endoscopic imaging modality, but also accurately detected and delineated the margin of a flat-type mucosal cancer with a size of approximately 3mm under white-light imaging and narrow-band imaging, with or without magnifying endoscopy and iodine staining (▶Fig. 1; ▶Video 1). Histopathology of the endoscopically resected specimen showed an early ESCC with invasion of the lamina propria (▶Fig. 2). Detecting and delineating subtle early ESCC with AI systems is challenging. To our knowledge, this is the first report of the use of an AI system to detect and deE-Videos