A Noninvasive Technology Using Artificial Intelligence to Measure the Diameter of Esophageal Varices Under Endoscopy.

BACKGROUND: The diameter of esophageal varices (EVs) can not only predict variceal bleeding episodes but is also considered to be a significant factor in determining the endoscopic treatment of EVs. At present, visual observation is the most common method for estimating the diameter of EVs, the results of which may vary greatly between endoscopists. MATERIALS AND METHODS: Herein, a noninvasive measurement technology, a virtual ruler (VR), was designed using artificial intelligence. The diameter and pressure of EVs in 7 patients were measured using VR and an esophageal varix manometer (EVM). Statistical methods, including the Bland-Altman Plot and Pearson correlation coefficient analysis, were used to compare the aforementioned 2 methods. RESULTS: The results showed that the diameter of EVs measured using the aforementioned 2 methods did not differ. In addition, the time taken to measure the diameter of EVs using VR was 31 seconds (range, 25 to 44 s), significantly shorter compared with 159 seconds (range, 95 to 201 s) taken using an EVM ( P < 0.01). Furthermore, the diameter of EVs measured using an EVM exhibited a high linear correlation with pressure. CONCLUSIONS: The current study demonstrated that VR was more accurate in measuring the diameter of EVs compared with EVMs while reducing unnecessary early intervention and the risk of complications. In terms of clinical risk and economic cost, this technology is hardly a burden. Overall, VR could be a useful software for the endoscopic detection and treatment of EVs in patients with liver cirrhosis.

Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video).

The artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detection system in EGC based on a mask region-based convolutional neural network (Mask R-CNN) and to evaluate the performance in controlled trials. For this purpose, a total of 4,471 white light images (WLIs) and 2,662 narrow band images (NBIs) of EGC were obtained for training and testing. In total, 10 of the WLIs (videos) were obtained prospectively to examine the performance of the RCNN system. Furthermore, 400 WLIs were randomly selected for comparison between the Mask R-CNN system and doctors. The evaluation criteria included accuracy, sensitivity, specificity, positive predictive value and negative predictive value. The results revealed that there were no significant differences between the pathological diagnosis with the Mask R-CNN system in the WLI test (χ2 = 0.189, P=0.664; accuracy, 90.25%; sensitivity, 91.06%; specificity, 89.01%) and in the NBI test (χ2 = 0.063, P=0.802; accuracy, 95.12%; sensitivity, 97.59%). Among 10 WLI real-time videos, the speed of the test videos was up to 35 frames/sec, with an accuracy of 90.27%. In a controlled experiment of 400 WLIs, the sensitivity of the Mask R-CNN system was significantly higher than that of experts (χ2 = 7.059, P=0.000; 93.00% VS 80.20%), and the specificity was higher than that of the juniors (χ2 = 9.955, P=0.000, 82.67% VS 71.87%), and the overall accuracy rate was higher than that of the seniors (χ2 = 7.009, P=0.000, 85.25% VS 78.00%). On the whole, the present study demonstrates that the Mask R-CNN system exhibited an excellent performance status for the detection of EGC, particularly for the real-time analysis of WLIs. It may thus be effectively applied to clinical settings.