Abstract
The aim of this study was to evaluate the diagnostic value of artificial intelligence algorithm combined with ultrasound endoscopy in early esophageal cancer and precancerous lesions by comparing the examination of conventional endoscopy and artificial intelligence algorithm combined with ultrasound endoscopy, and by comparing the real-time diagnosis of endoscopy and the ultrasonic image characteristics of artificial intelligence algorithm combined with endoscopic detection and pathological results. 120 cases were selected. According to the inclusion and exclusion criteria, 80 patients who met the criteria were selected and randomly divided into two groups: endoscopic examination combined with ultrasound imaging based on intelligent algorithm processing (cascade region-convolutional neural network (Cascade RCNN) model algorithm group) and simple use of endoscopy group (control group). This study shows that the ultrasonic image of artificial intelligence algorithm is effective, and the detection performance is better than that of endoscopic detection. The results are close to the gold standard of doctor recognition, and the detection time is greatly shortened, and the recognition time is shortened by 71 frames per second. Compared with the traditional convolutional neural network (CNN) algorithm, the accuracy and recall of image analysis and segmentation using feature pyramid network are increased. The detection rates of CNN model, Cascade RCNN model, and endoscopic detection alone in early esophageal cancer and precancerous lesions are 56.3% (45/80), 88.8% (71/80), and 44.1% (35/80), respectively. The detection rate of Cascade RCNN model and CNN model was higher than that of endoscopy alone, and the difference was statistically significant (P < 0.05). The sensitivity, specificity, positive predictive value, and negative predictive value of Cascade RCNN model were higher than those of CNN model, which was close to the gold standard for physician identification. This provided a reference basis for endoscopic ultrasound identification of early upper gastrointestinal cancer or other gastrointestinal cancers.
Highlights
Gastrointestinal cancer refers to early gastrointestinal tumor [1]
convolutional neural network (CNN) model and Cascade RCNN model were used to identify the lesions of early cancer of upper gastrointestinal tract
Comparing the ultrasound image based on neural network recognition algorithm with the doctor’s manual recognition image, the doctor’s manual recognition was clear and accurate. e RCNN image was close to the gold standard for doctor’s recognition, but the reflective and shaded parts were identified as lesions in the endoscopic image
Summary
Gastrointestinal cancer refers to early gastrointestinal tumor [1]. Most patients have no special symptoms and are often found in high-risk people over the age of 40. High-risk people refer to long-term gastrointestinal diseases or gastrointestinal tumors in immediate relatives [2]. Esophageal cancer (EC) is a clinical malignant tumor, which is mostly seen in men over 40 years old [3]. Because there are no typical symptoms in the early stage of esophageal cancer, the sensitivity of patients to esophageal cancer is not high. Most patients with esophageal cancer are already in the advanced stage of gastrointestinal cancer. E survival rate of patients with early gastrointestinal cancer after surgical resection is high, but the survival rate of elderly patients is low because of weak physique and other elderly diseases [4]. Esophageal cancer only affects the submucosa and can be treated by minimally invasive surgery under ultrasonic
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
