Utilization of Ultrasonic Image Characteristics Combined with Endoscopic Detection on the Basis of Artificial Intelligence Algorithm in Diagnosis of Early Upper Gastrointestinal Cancer

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.

Application Value of Emergency Bedside Echocardiography in Early Warning of Acute and Severe Shock and Clinical Classification

“…The results of this study show that the AUC of the diagnostic ultrasound group for the diagnosis of shock type is 0.854, which is of high diagnostic value, which is basically consistent with the conclusions of previous studies. The same idea can be found in the study put forward by Wang et al [30]. They have applied new methods in the study, and the conclusions drawn can also give some support to this study.…”

AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels

“…For surgeon B, no significant differences across different segmental arteries were detected (p = 0.083). The accuracies of LA 1+2 , LA 4 , LA 5 , and LA 6 were less than 50%.…”

“…For surgeon A, a significant difference across different segmental arteries was detected (p = 0.033), among which RA 1 and RA 4+5 showed higher accuracy and LA 1+2 showed significant lower accuracy. The accuracies of RA 2 , RA 6 , LA 4 , LA 5 , and LA 6 were also below 50%. For surgeon B, no significant differences across different segmental arteries were detected (p = 0.083).…”

“…AI algorithms have been widely applied in every aspect of medicine recently ( 5 – 9 ). From the screening of the pulmonary nodule ( 10 ) to the diagnosis of skin cancer ( 11 ) and diabetic retinopathy ( 12 ) and even in the development of new treatment drugs ( 13 – 15 ), utilizing the AI algorithm has been revolutionizing.…”

A deep learning-based approach toward differentiating scalp psoriasis and seborrheic dermatitis from dermoscopic images

“…The representative DL technique, namely convolutional neural networks (CNNs) exhibit remarkable capability in feature extraction and thus has been widely employed for image classification (3)(4)(5). Over the past few years, a variety of DLbased medical applications have been reported, such as the assisted diagnosis of digestive tract tumors with pathology, MRI, and ultrasound images (6)(7)(8)(9), the diagnosis of dysphagia with photographs of the anterior neck (10), and the precise location and identification of cells in microscopic images (11). In the dermatology field, DL uses trunk or longitudinal skin stratification images of patients' lesions to diagnose skin tumors, atopic dermatitis, psoriasis, and fungal infections (12)(13)(14)(15).…”