Objectives: Detecting early gastric cancer is difficult, and it may even be overlooked by experienced endoscopists. Recently, artificial intelligence based on deep learning through convolutional neural networks (CNNs) has enabled significant advancements in the field of gastroenterology. However, it remains unclear whether a CNN can outperform endoscopists. In this study, we evaluated whether the performance of a CNN in detecting early gastric cancer is better than that of endoscopists. Methods: The CNN was constructed using 13,584 endoscopic images from 2639 lesions of gastric cancer. Subsequently, its diagnostic ability was compared to that of 67 endoscopists using an independent test dataset (2940 images from 140 cases). Results: The average diagnostic time for analyzing 2940 test endoscopic images by the CNN and endoscopists were 45.5 AE 1.8 s and 173.0 AE 66.0 min, respectively. The sensitivity, specificity, and positive and negative predictive values for the CNN were 58.4%, 87.3%, 26.0%, and 96.5%, respectively. These values for the 67 endoscopists were 31.9%, 97.2%, 46.2%, and 94.9%, respectively. The CNN had a significantly higher sensitivity than the endoscopists (by 26.5%; 95% confidence interval, 14.9-32.5%). Conclusion: The CNN detected more early gastric cancer cases in a shorter time than the endoscopists. The CNN needs further training to achieve higher diagnostic accuracy. However, a diagnostic support tool for gastric cancer using a CNN will be realized in the near future.

The role of Toll-like receptor (TLR) signaling has attracted much attention in the development of hepatic inflammation and hepatocellular carcinoma (HCC). We herein sought to determine the role of TLRs and responsible cells in steatohepatitisrelated HCC. We used hepatocyte-specific Pten-deficient (Pten ⌬hep ) mice, which exhibit steatohepatitis followed by liver tumor formation, including HCC. We then generated Pten ⌬hep / Tlr4

The composition of gut microbiota and IL-17 expression varied considerably between mice administrated different experimental diets to induce steatohepatitis.

https://onlinelibrary.wiley.com/page/journal/14431661/den13306-sup-0001-vids1.htm a video of this article

Nonalcoholic steatohepatitis (NASH) is a common cause of liver cirrhosis and hepatocellular carcinoma (HCC). However, effective therapeutic strategies for preventing and treating NASH‐mediated liver cirrhosis and HCC are lacking. Cholesterol is closely associated with vascular endothelial growth factor (VEGF), a key factor that promotes HCC. Recent reports have demonstrated that statins could prevent HCC development. In contrast, we have little information on ezetimibe, an inhibitor of cholesterol absorption, in regards to the prevention of NASH‐related liver cirrhosis and HCC. In the present study, a steatohepatitis‐related HCC model, hepatocyte‐specific phosphatase and tensin homolog (Pten)‐deficient (Pten Δhep) mice were fed a high‐fat (HF) diet with/without ezetimibe. In the standard‐diet group, ezetimibe did not reduce the development of liver tumors in Pten Δhep mice, in which the increase of serum cholesterol levels was mild. Feeding of a HF diet increased serum cholesterol levels markedly and subsequently increased serum levels of VEGF, a crucial component of angiogenesis. The HF diet increased the number of VEGF‐positive cells and vascular endothelial cells in the tumors of Pten Δhep mice. Kupffer cells, macrophages in the liver, increased VEGF expression in response to fat overload. Ezetimibe treatment lowered cholesterol levels and these angiogenetic processes. As a result, ezetimibe also suppressed inflammation, liver fibrosis and tumor growth in Pten Δhep mice on the HF diet. Tumor cells were highly proliferative with HF‐diet feeding, which was inhibited by ezetimibe. In conclusion, ezetimibe suppressed development of liver tumors by inhibiting angiogenesis in Pten Δhep mice with hypercholesterolemia.