Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos).

BACKGROUND AND AIMS: White-light endoscopy (WLE) is the most pivotal tool to detect gastric cancer in an early stage. However, the skill among endoscopists varies greatly. Here, we aim to develop a deep learning-based system named ENDOANGEL-LD (lesion detection) to assist in detecting all focal gastric lesions and predicting neoplasms by WLE. METHODS: Endoscopic images were retrospectively obtained from Renmin Hospital of Wuhan University (RHWU) for the development, validation, and internal test of the system. Additional external tests were conducted in 5 other hospitals to evaluate the robustness. Stored videos from RHWU were used for assessing and comparing the performance of ENDOANGEL-LD with that of experts. Prospective consecutive patients undergoing upper endoscopy were enrolled from May 6, 2021 to August 2, 2021 in RHWU to assess clinical practice applicability. RESULTS: Over 10,000 patients undergoing upper endoscopy were enrolled in this study. The sensitivities were 96.9% and 95.6% for detecting gastric lesions and 92.9% and 91.7% for diagnosing neoplasms in internal and external patients, respectively. In 100 videos, ENDOANGEL-LD achieved superior sensitivity and negative predictive value for detecting gastric neoplasms from that of experts (100% vs 85.5% ± 3.4% [P = .003] and 100% vs 86.4% ± 2.8% [P = .002], respectively). In 2010 prospective consecutive patients, ENDOANGEL-LD achieved a sensitivity of 92.8% for detecting gastric lesions with 3.04 ± 3.04 false positives per gastroscopy and a sensitivity of 91.8% and specificity of 92.4% for diagnosing neoplasms. CONCLUSIONS: Our results show that ENDOANGEL-LD has great potential for assisting endoscopists in screening gastric lesions and suspicious neoplasms in clinical work. (Clinical trial registration number: ChiCTR2100045963.).

Real-time use of artificial intelligence for diagnosing early gastric cancer by magnifying image-enhanced endoscopy: a multicenter diagnostic study (with videos).

BACKGROUND AND AIMS: Endoscopy is a pivotal method for detecting early gastric cancer (EGC). However, skill among endoscopists varies greatly. Here, we proposed a deep learning-based system named ENDOANGEL-ME to diagnose EGC in magnifying image-enhanced endoscopy (M-IEE). METHODS: M-IEE images were retrospectively obtained from 6 hospitals in China, including 4667 images for training and validation, 1324 images for internal tests, and 4702 images for external tests. One hundred eighty-seven stored videos from 2 hospitals were used to evaluate the performance of ENDOANGEL-ME and endoscopists and to assess the effect of ENDOANGEL-ME on improving the performance of endoscopists. Prospective consecutive patients undergoing M-IEE were enrolled from August 17, 2020 to August 2, 2021 in Renmin Hospital of Wuhan University to assess the applicability of ENDOANGEL-ME in clinical practice. RESULTS: A total of 3099 patients undergoing M-IEE were enrolled in this study. The diagnostic accuracy of ENDOANGEL-ME for diagnosing EGC was 88.44% and 90.49% in internal and external images, respectively. In 93 internal videos, ENDOANGEL-ME achieved an accuracy of 90.32% for diagnosing EGC, significantly superior to that of senior endoscopists (70.16% ± 8.78%). In 94 external videos, with the assistance of ENDOANGEL-ME, endoscopists showed improved accuracy and sensitivity (85.64% vs 80.32% and 82.03% vs 67.19%, respectively). In 194 prospective consecutive patients with 251 lesions, ENDOANGEL-ME achieved a sensitivity of 92.59% (25/27) and an accuracy of 83.67% (210/251) in real clinical practice. CONCLUSIONS: This multicenter diagnostic study showed that ENDOANGEL-ME can be well applied in the clinical setting. (Clinical trial registration number: ChiCTR2000035116.).

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial.

BACKGROUND: Esophagogastroduodenoscopy (EGD) is a prerequisite for detecting upper gastrointestinal lesions especially early gastric cancer (EGC). An artificial intelligence system has been shown to monitor blind spots during EGD. In this study, we updated the system (ENDOANGEL), verified its effectiveness in improving endoscopy quality, and pretested its performance in detecting EGC in a multicenter randomized controlled trial. METHODS: ENDOANGEL was developed using deep convolutional neural networks and deep reinforcement learning. Patients undergoing EGD in five hospitals were randomly assigned to the ENDOANGEL-assisted group or to a control group without use of ENDOANGEL. The primary outcome was the number of blind spots. Secondary outcomes included performance of ENDOANGEL in predicting EGC in a clinical setting. RESULTS: 1050 patients were randomized, and 498 and 504 patients in the ENDOANGEL and control groups, respectively, were analyzed. Compared with the control group, the ENDOANGEL group had fewer blind spots (mean 5.38 [standard deviation (SD) 4.32] vs. 9.82 [SD 4.98]; P < 0.001) and longer inspection time (5.40 [SD 3.82] vs. 4.38 [SD 3.91] minutes; P < 0.001). In the ENDOANGEL group, 196 gastric lesions with pathological results were identified. ENDOANGEL correctly predicted all three EGCs (one mucosal carcinoma and two high grade neoplasias) and two advanced gastric cancers, with a per-lesion accuracy of 84.7 %, sensitivity of 100 %, and specificity of 84.3 % for detecting gastric cancer. CONCLUSIONS: In this multicenter study, ENDOANGEL was an effective and robust system to improve the quality of EGD and has the potential to detect EGC in real time.

Repression of Death Receptor-Mediated Apoptosis of Hepatocytes by Hepatitis B Virus e Antigen.

Hepatitis B virus (HBV) e antigen (HBeAg) is associated with viral persistence and pathogenesis. Resistance of HBV-infected hepatocytes to apoptosis is seen as one of the primary promotors for HBV chronicity and malignancy. Fas receptor/ligand (Fas/FasL) and the tumor necrosis factor (TNF)-related apoptosis-inducing ligand (TRAIL) system plays a key role in hepatic death during HBV infection. We found that HBeAg mediates resistance of hepatocytes to FasL or TRAIL-induced apoptosis. Introduction of HBeAg into human hepatocytes rendered resistance to FasL or TRAIL cytotoxicity in a p53-dependent manner. HBeAg further inhibited the expression of p53, total Fas, membrane-bound Fas, TNF receptor superfamily member 10a, and TNF receptor superfamily member 10b at both mRNA and protein levels. In contrast, HBeAg enhanced the expression of soluble forms of Fas through facilitation of Fas alternative mRNA splicing. In a mouse model, expression of HBeAg in mice injected with recombinant adenovirus-associated virus 8 inhibited agonistic anti-Fas antibody-induced hepatic apoptosis. Xenograft tumorigenicity assay also found that HBeAg-induced carcinogenesis was resistant to the proapoptotic effect of TRAIL and chemotherapeutic drugs. These results indicate that HBeAg may prevent hepatocytes from FasL and TRAIL-induced apoptosis by regulating the expression of the proapoptotic and antiapoptotic forms of death receptors, which may contribute to the survival and persistence of infected hepatocytes during HBV infection.

Hepatitis B virus core protein promotes hepatocarcinogenesis by enhancing Src expression and activating the Src/PI3K/Akt pathway.

Hepatitis B virus core protein (HBc) is expressed preferentially in hepatitis B virus (HBV)-associated hepatocellular carcinoma (HCC). HBc can function as an oncogene arising from its gene regulatory properties, but how it contributes functionally to hepatocarcinogenesis remains unclear. In this study, we determined the molecular and functional roles of HBc during HBV-associated hepatocellular tumorigenesis. HBc increased tumor formation of hepatoma cells. Moreover, expression of HBc specifically promoted proliferation of hepatoma cells in vitro. Mechanistic investigations revealed that these effects were caused by activation of the Src/PI3K/Akt pathway through proximal switch from inactive Src to the active form of the kinase by HBc. HBc-mediated sarcoma (Src) kinase activation was associated with down-regulation of C-terminal Src kinase (Csk). In addition, HBc enhances Src expression by activation of alternative Src 1A promoter in an Sp1 transcription factor-dependent manner. Proliferation induced by stable HBc expression was associated with increased G1-S cell cycle progression mediated by Src kinase activation. HBc-induced cellular proliferation and tumor formation were reversed by administration of the Src inhibitor saracatinib. Together, our findings suggest that HBc promotes tumorigenesis of hepatoma cells by enhancing the expression of total Src and the active form of the kinase and subsequently activates Src/PI3K/Akt signaling pathway, revealing novel insights into the underlying mechanisms of HBV-associated hepatocarcinogenesis.-Liu, W., Guo, T.-F., Jing, Z.-T., Yang, Z., Liu, L., Yang, Y.-P., Lin, X., Tong, Q.-Y. Hepatitis B virus core protein promotes hepatocarcinogenesis by enhancing Src expression and activating the Src/PI3K/Akt pathway.

Oncological consequence of emergent resection of perforated colon cancer with complete obstruction after stent insertion as a bridge to surgery.

PURPOSE: Colonic perforation is a life-threatening complication after colonic stent insertion as a bridge to surgery for acute obstruction caused by colorectal cancer. The oncological consequence of colonic perforation after emergent surgical intervention was unknown. The aim of this short communication was to investigate whether or not the perforation and emergent surgery had obviously impact on the peritoneal recurrence and long-term survival of patients. METHODS: Data of the patients who underwent colorectal stenting as a bridge to surgery in 5 years from 2012 to 2017 was collected by the Endoscopical Surgery Group of Hubei. The perforated cases treated by emergent operation were retrospectively analyzed. RESULTS: During 5 years from 2012 to 2017, 116 cases of colorectal stenting as a bridge to surgery had been performed, and 7 patients had perforation after stent placement and treated by emergent surgery, including 1 case of synchronic liver metastasis treated by one-stage metastasectomy. One of the 7 patients died of septic shock after operation, and the remaining patients were followed up for 6-60 months. There was no evidence of abdominal implantation or extra-abdominal metastasis. CONCLUSION: This small case series implicated that colonic perforation after stent insertion for malignant colorectal obstruction treated by emergent surgery might not obviously increase the peritoneal implantation and metastasis.

Development and validation of a three-dimensional deep learning-based system for assessing bowel preparation on colonoscopy video.

Background: The performance of existing image-based training models in evaluating bowel preparation on colonoscopy videos was relatively low, and only a few models used external data to prove their generalization. Therefore, this study attempted to develop a more precise and stable AI system for assessing bowel preparation of colonoscopy video. Methods: We proposed a system named ViENDO to assess the bowel preparation quality, including two CNNs. First, Information-Net was used to identify and filter out colonoscopy video frames unsuitable for Boston bowel preparation scale (BBPS) scoring. Second, BBPS-Net was trained and tested with 5,566 suitable short video clips through three-dimensional (3D) convolutional neural network (CNN) technology to detect BBPS-based insufficient bowel preparation. Then, ViENDO was applied to complete withdrawal colonoscopy videos from multiple centers to predict BBPS segment scores in clinical settings. We also conducted a human-machine contest to compare its performance with endoscopists. Results: In video clips, BBPS-Net for determining inadequate bowel preparation generated an area under the curve of up to 0.98 and accuracy of 95.2%. When applied to full-length withdrawal colonoscopy videos, ViENDO assessed bowel cleanliness with an accuracy of 93.8% in the internal test set and 91.7% in the external dataset. The human-machine contest demonstrated that the accuracy of ViENDO was slightly superior compared to most endoscopists, though no statistical significance was found. Conclusion: The 3D-CNN-based AI model showed good performance in evaluating full-length bowel preparation on colonoscopy video. It has the potential as a substitute for endoscopists to provide BBPS-based assessments during daily clinical practice.

Puerarin Exerts the Hepatoprotection from Chronic Alcohol-Induced Liver Injury via Inhibiting the Cyclooxygenase-2 and the 5-Lipoxygenase Pathway in Rats.

BACKGROUND: Puerarin (PR) as one of the main ingredients of the root of the traditional herb Kudzu has been suggested to improve chronic alcohol-induced liver injury. We explore the specific mechanisms of PR on hepatocellular changes after administration of alcohol. METHODS: Sprague-Dawley rats were treated with 55% alcohol for 12 weeks to induce a chronic alcoholic liver damage model. Then the rats in each group were administered by oral gavage with zileuton, celecoxib, and PR for 2 weeks, respectively. RESULTS: In the PR group, the weight loss was markedly improved and the abnormal serum alanine aminotransferase and aspartate aminotransferase were significantly lowered after PR treatment when compared to the alcoholic liver injured model group. Pathological examination indicated that alcohol-induced hepatocellular injury was improved by the PR treatment. The 5-lipoxygenase (5-Lox) and cyclooxygenase-2 (Cox-2) at the protein level and the mRNA level were obviously downregulated accompanied with the PR treatment. Meanwhile, the peroxisome proliferator-activated receptor γ (PPAR-γ) at the protein and mRNA level was notably elevated and the tumor necrosis factor α at the protein and mRNA level was markedly decreased following the PR treatment. CONCLUSION: The possible cytoprotective mechanisms of PR may be involved inhibition of the Cox-2 pathway and the 5-Lox pathway to suppress inflammatory response and regulate the protective factor PPAR-γ expression.

Anti-inflammation Effects of Sinomenine on Macrophages through Suppressing Activated TLR4/NF-κB Signaling Pathway.

Sinomenine (SN) has been used in the clinical treatment of systemic lupus erythematosus and rheumatoid arthritis for many years. Studies showed that SN held protective effects such as anti-inflammation, scavenging free radicals and suppressing immune response in many autoimmune diseases. The purpose of the present study is to explore the mechanism of anti-inflammation of SN on lipopolysaccharide (LPS)-induced macrophages activation and investigate whether the TLR4/NF-κB signaling pathway participated in. Macrophages isolated from mouse peritoneal cavity were stimulated by 1 µg/mL LPS for 24 h. And then the cells were treated with various concentrations of SN, TLR4 inhibitor respectively for additional 48 h. Drug toxicity was detected by MTT assay and Transwell experiment was used to assess chemotaxis. Furthermore, TLR4 and MyD88 mRNA levels were detected by real-time PCR. Western blotting was used to examine TLR4, MyD88 and phosphorylated IκB protein expression in macrophages. Immunofluorescence assay was applied to observe p65 NF-κB protein expression in macrophage nucleus. We extracted macrophages with high purity and activity from the abdominal cavity of mice. SN remarkably inhibited the chemotaxis and secretion function of LPS-stimulated macrophages. It also down-regulated both the protein levels of inflammatory cytokines (TNF-α, IL-1ß and IL-6) and the RNA and protein levels of the key factors (TLR4, MyD88, P-IκB) in TLR4 pathway. The expression of p65 NF-κB protein in nuclei was down-regulated, which was correlated with a similar decrease in P-IκB protein level. In conclusion, SN can inhibit the LPS induced immune responses in macrophages by blocking the activated TLR4/NF-κB signaling pathway. These results may provide a therapeutic approach to regulate inflammatory responses.

Anti-inflammatory effect of fucoxanthin on dextran sulfate sodium-induced colitis in mice.

The anti-inflammatory activities of fucoxanthin, a marine carotenoid derived from the macroalgae and microalgae, have been demonstrated in the previous studies. However, the effect of fucoxanthin on ulcerative colitis (UC), an inflammatory bowel disease, was still unclear. In this study, we evaluated the in vivo anti-inflammatory effect of fucoxanthin on dextran sulfate sodium(DSS)-induced colitis in mice. Fucoxanthin at the doses of 50 and 100 mg/kg/day significantly protected against DSS-induced gradual loss of body weight, exhibited inhibitory effects on the DSS-induced increase of disease activity index and colon shortening. Moreover, fucoxanthin treatment resulted in a marked amelioration of the histological damage in the colon, and reduced the colonic PGE2 levels in colitic mice. In addition, the DSS-induced overexpressions of inflammation-related molecules including COX-2 and NF-κB were significantly decreased in fucoxanthin-treated mice. These finding suggested that the use of fucoxanthin provides a new and attractive alternative to control UC.