Search

Background and study aims Endoscopic reports are essential for the diagnosis and follow-up of gastrointestinal diseases. This study aimed to construct an intelligent system for automatic photo documentation during esophagogastroduodenoscopy (EGD) and test its utility in clinical practice. Patients and methods Seven convolutional neural networks trained and tested using 210,198 images were integrated to construct the endoscopic automatic image reporting system (EAIRS). We tested its performance through man-machine comparison at three levels: internal, external, and prospective test. Between May 2021 and June 2021, patients undergoing EGD at Renmin Hospital of Wuhan University were recruited. The primary outcomes were accuracy for capturing anatomical landmarks, completeness for capturing anatomical landmarks, and detected lesions. Results The EAIRS outperformed endoscopists in retrospective internal and external test. A total of 161 consecutive patients were enrolled in the prospective test. The EAIRS achieved an accuracy of 95.2% in capturing anatomical landmarks in the prospective test. It also achieved higher completeness on capturing anatomical landmarks compared with endoscopists: (93.1% vs. 88.8%), and was comparable to endoscopists on capturing detected lesions: (99.0% vs. 98.0%). Conclusions The EAIRS can generate qualified image reports and could be a powerful tool for generating endoscopic reports in clinical practice.

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 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.

Summary Background Colonoscopy performance varies among endoscopists, impairing the discovery of colorectal cancers and precursor lesions. We aimed to construct a real-time quality improvement system (ENDOANGEL) to monitor real-time withdrawal speed and colonoscopy withdrawal time and to remind endoscopists of blind spots caused by endoscope slipping. We also aimed to evaluate the effectiveness of this system for improving adenoma yield of everyday colonoscopy. Methods The ENDOANGEL system was developed using deep neural networks and perceptual hash algorithms. We recruited consecutive patients aged 18–75 years from Renmin Hospital of Wuhan University in China who provided written informed consent. We randomly assigned patients (1:1) using computer-generated random numbers and block randomisation (block size of four) to either colonoscopy with the ENDOANGEL system or unassisted colonoscopy (control). Endoscopists were not masked to the random assignment but analysts and patients were unaware of random assignments. The primary endpoint was the adenoma detection rate (ADR), which is the proportion of patients having one or more adenomas detected at colonoscopy. The primary analysis was done per protocol (ie, in all patients having colonoscopy done in accordance with the assigned intervention) and by intention to treat (ie, in all randomised patients). This trial is registered with http://www.chictr.org.cn , ChiCTR1900021984. Findings Between June 18, 2019, and Sept 6, 2019, 704 patients were randomly allocated colonoscopy with the ENDOANGEL system (n=355) or unassisted (control) colonoscopy (n=349). In the intention-to-treat population, ADR was significantly greater in the ENDOANGEL group than in the control group, with 58 (16%) of 355 patients allocated ENDOANGEL-assisted colonoscopy having one or more adenomas detected, compared with 27 (8%) of 349 allocated control colonoscopy (odds ratio [OR] 2·30, 95% CI 1·40–3·77; p=0·0010). In the per-protocol analysis, findings were similar, with 54 (17%) of 324 patients assigned ENDOANGEL-assisted colonoscopy and 26 (8%) of 318 patients assigned control colonoscopy having one or more adenomas detected (OR 2·18, 95% CI 1·31–3·62; p=0·0026). No adverse events were reported. Interpretation The ENDOANGEL system significantly improved the adenoma yield during colonoscopy and seems to be effective and safe for use during routine colonoscopy. Funding Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Hubei Province Major Science and Technology Innovation Project, and the National Natural Science Foundation of China.

Gastric cancer (GC) is one of the most common malignancies and its prognosis is extremely poor. This study identifies a novel oncogene, microfibrillar-associated protein 2 (MFAP2) in GC. With integrative reanalysis of transcriptomic data, we found MFAP2 as a GC prognosis-related gene. And the aberrant expression of MFAP2 was explored in GC samples. Subsequent experiments indicated that silencing and exogenous MFAP2 could affect motility of cancer cells. The inhibition of silencing MFAP2 could be rescued by another FAK activator, fibronectin. This process is probably through affecting the activation of focal adhesion process via modulating ITGB1 and ITGA5. MFAP2 regulated integrin expression through ERK1/2 activation. Silencing MFAP2 by shRNA inhibited tumorigenicity and metastasis in nude mice. We also revealed that MFAP2 is a novel target of microRNA-29, and miR-29/MFAP2/integrin α5β1/FAK/ERK1/2 could be an important oncogenic pathway in GC progression. In conclusion, our data identified MFAP2 as a novel oncogene in GC and revealed that miR-29/MFAP2/integrin α5β1/FAK/ERK1/2 could be an important oncogenic pathway in GC progression.

Background Gastric cancer is the third most lethal malignancy worldwide. A novel deep convolution neural network (DCNN) to perform visual tasks has been recently developed. The aim of this study was to build a system using the DCNN to detect early gastric cancer (EGC) without blind spots during esophagogastroduodenoscopy (EGD). Methods 3170 gastric cancer and 5981 benign images were collected to train the DCNN to detect EGC. A total of 24549 images from different parts of stomach were collected to train the DCNN to monitor blind spots. Class activation maps were developed to automatically cover suspicious cancerous regions. A grid model for the stomach was used to indicate the existence of blind spots in unprocessed EGD videos. Results The DCNN identified EGC from non-malignancy with an accuracy of 92.5 %, a sensitivity of 94.0 %, a specificity of 91.0 %, a positive predictive value of 91.3 %, and a negative predictive value of 93.8 %, outperforming all levels of endoscopists. In the task of classifying gastric locations into 10 or 26 parts, the DCNN achieved an accuracy of 90 % or 65.9 %, on a par with the performance of experts. In real-time unprocessed EGD videos, the DCNN achieved automated performance for detecting EGC and monitoring blind spots. Conclusions We developed a system based on a DCNN to accurately detect EGC and recognize gastric locations better than endoscopists, and proactively track suspicious cancerous lesions and monitor blind spots during EGD.

ObjectiveEsophagogastroduodenoscopy (EGD) is the pivotal procedure in the diagnosis of upper gastrointestinal lesions. However, there are significant variations in EGD performance among endoscopists, impairing the discovery rate of gastric cancers and precursor lesions. The aim of this study was to construct a real-time quality improving system, WISENSE, to monitor blind spots, time the procedure and automatically generate photodocumentation during EGD and thus raise the quality of everyday endoscopy.DesignWISENSE system was developed using the methods of deep convolutional neural networks and deep reinforcement learning. Patients referred because of health examination, symptoms, surveillance were recruited from Renmin hospital of Wuhan University. Enrolled patients were randomly assigned to groups that underwent EGD with or without the assistance of WISENSE. The primary end point was to ascertain if there was a difference in the rate of blind spots between WISENSE-assisted group and the control group.ResultsWISENSE monitored blind spots with an accuracy of 90.40% in real EGD videos. A total of 324 patients were recruited and randomised. 153 and 150 patients were analysed in the WISENSE and control group, respectively. Blind spot rate was lower in WISENSE group compared with the control (5.86% vs 22.46%, pConclusionsWISENSE significantly reduced blind spot rate of EGD procedure and could be used to improve the quality of everyday endoscopy.Trial registration numberChiCTR1800014809; Results.

Pancreatic cancer is one of the leading causes of cancer mortality worldwide due to the lack of reliable tools for early diagnosis of this cancer. In this study, we evaluated the feasibility of micro-optical coherence tomography (μOCT) as an imaging tool for the diagnosis of pancreatic cancers. Specifically, we constructed a μOCT device that achieves a resolution of 1.67 ± 0.01 μm and 1.79 ± 0.01 μm in axial and lateral directions, respectively, and acquired three-dimensional μOCT images of mouse, rat, and human pancreatic specimens ex vivo. We compared the results of μOCT with those of the corresponding histology. In μOCT images of normal pancreatic specimens, the detailed cellular and subcellular-level pancreatic microstructures, e.g., the islet of Langerhans (IL), IL cell nuclei, blood vessels, and serous acini, could be clearly resolved in different cases. To the best of our knowledge, this study is the first to demonstrate that the cellular and subcellular structures of pancreatic tissues were identified using OCT. More importantly, we showed that these normal cellular-level structures were lost in μOCT images of cancerous specimens, demonstrating the feasibility of differentiating malignant lesions from normal tissues using μOCT. Moving forward, the development of an intraoperative imaging device may realize optical biopsies in vivo or real-time cellular-resolution examination of specimens from needle aspiration biopsies. Ministry of Education (MOE) Nanyang Technological University National Medical Research Council (NMRC) National Research Foundation (NRF) Accepted version This work was supported in part by the National Natural Science Foundation of China under Grant 61705184, the Fundamental Research Funds for the Central Universities (G2018KY0308), in part by the National Research Foundation of Singapore (NRF-CRP13-2014-05), in part by the Ministry of Education of Singapore (MOE2013-T2-2-107), in part by the National Medical Research Council of Singapore (NMRC/CBRG/0036/2013), and in part by the NTU-AIT-MUV Program in Advanced Biomedical Imaging (NAM/15005).

Background and Aims Gastric precancerous conditions, including gastric atrophy (GA) and intestinal metaplasia (IM), play an important role in the development of gastric cancer. Image-enhanced endoscopy (IEE) shows great potential in diagnosing gastric precancerous conditions and adenocarcinoma. In this study, a deep convolutional neural network system, named ENDOANGEL, was constructed to detect gastric precancerous conditions by IEE. Methods Endoscopic images were retrospectively obtained from 5 hospitals in China for the development, validation, and internal and external test of the system. Prospective consecutive patients receiving IEE were enrolled from January 13, 2020 to October 29, 2020 in Renmin Hospital of Wuhan University to assess in real time the applicability of the proposed computer-aided detection (CADe) system in clinical practice, and the performance of CADe was compared with that of endoscopists. Results Six thousand two hundred fifty endoscopic images from 760 patients and 98 video clips from 77 individuals undergoing IEE were enrolled in this study. The diagnostic accuracy of GA was .901 (95% confidence interval [CI], .883-.917) in the internal test set, .864 (95% CI, .842-.884) in the multicenter external test set, and .878 (95% CI, .796-.935) in the prospective video test set. The diagnostic accuracy of IM was .908 (95% CI, .889-.924) in the internal test set, .859 (95% CI, .837-.880) in the multicenter external test set, and .898 (95% CI, .820-.950) in the prospective video test set. CADe achieved similar diagnostic accuracy to that of the experts for detecting GA (.869 [95% CI, .790-.927] vs .846 [95% CI, .808-.879], P = .396) and IM (.888 [95% CI, .812-.941] vs .820 [95% CI, .780-.855], P = .117) and was superior to that of nonexperts for GA (.750 [95% CI, .711-.786], P = .008) and IM (.736 [95% CI, .697-.773], P = .028). Conclusions CADe achieved high diagnostic accuracy in gastric precancerous conditions, which was similar to that of experts and superior to that of nonexperts. Thus, CADe provides possibilities for a wide application in assisting in the diagnosis of gastric precancerous conditions.

Background and study aims Endoscopy plays a crucial role in diagnosis of gastritis. Endoscopists have low accuracy in diagnosing atrophic gastritis with white-light endoscopy (WLE). High-risk factors (such as atrophic gastritis [AG]) for carcinogenesis demand early detection. Deep learning (DL)-based gastritis classification with WLE rarely has been reported. We built a system for improving the accuracy of diagnosis of AG with WLE to assist with this common gastritis diagnosis and help lessen endoscopist fatigue. Methods We collected a total of 8141 endoscopic images of common gastritis, other gastritis, and non-gastritis in 4587 cases and built a DL -based system constructed with UNet + + and Resnet-50. A system was developed to sort common gastritis images layer by layer: The first layer included non-gastritis/common gastritis/other gastritis, the second layer contained AG/non-atrophic gastritis, and the third layer included atrophy/intestinal metaplasia and erosion/hemorrhage. The convolutional neural networks were tested with three separate test sets. Results Rates of accuracy for classifying non-atrophic gastritis/AG, atrophy/intestinal metaplasia, and erosion/hemorrhage were 88.78 %, 87.40 %, and 93.67 % in internal test set, 91.23 %, 85.81 %, and 92.70 % in the external test set ,and 95.00 %, 92.86 %, and 94.74 % in the video set, respectively. The hit ratio with the segmentation model was 99.29 %. The accuracy for detection of non-gastritis/common gastritis/other gastritis was 93.6 %. Conclusions The system had decent specificity and accuracy in classification of gastritis lesions. DL has great potential in WLE gastritis classification for assisting with achieving accurate diagnoses after endoscopic procedures.

INTRODUCTION: “Resect and discard” paradigm is one of the main strategies to deal with colorectal diminutive polyps after optical diagnosis. However, there are risks that unrecognized potentially malignant lesions are discarded without accurate diagnosis. The purpose of this study is to validate the potential of microoptical coherence tomography (mOCT) to improve the diagnostic accuracy of colorectal lesions and help endoscopists make better clinical decision without additional pathology costs. METHODS: Fresh tissue samples were obtained from patients with colorectal polyps or colorectal cancer who received endoscopic therapy or laparoscopic surgery. These samples were instantly imaged by mOCT and then sent to pathological evaluation. Then, mOCT images were compared with corresponding HE sections. We created consensus mOCT image criteria and then tested to determine sensitivity, specificity, and accuracy of our system to discriminate neoplastic polyps from non-neoplastic polyps. RESULTS: Our mOCT system achieved a resolution of 2.0 mm in both axial and lateral directions, clearly illustrated both cross-sectional and en face subcellular-level microstructures of colorectal lesions ex vivo, demonstrating distinctive patterns for inflammatory granulation tissue, hyperplastic polyp, adenoma, and cancerous tissue. For the 58 cases of polyps, the accuracy of the model was 94.83% (95% confidence interval [CI], 85.30%–98.79%), the sensitivity for identification of adenomas was 96.88% (95% CI, 82.89%–99.99%), and the specificity was 92.31% (95% CI, 74.74%–98.98%). Our diagnostic criteria could help both expert endoscopists and nonexpert endoscopists to identify neoplastic from non-neoplastic polyps with satisfactory accuracy and good interobserver agreement. DISCUSSION: We propose a new strategy usingmOCT to differentiate benign polyps and adenomas after the lesions are resected. The application of mOCT can potentially reduce the cost of pathological examination and minimize the risk of discarding malignant lesions during colonosocpy examination. NRF (Natl Research Foundation, S’pore) MOE (Min. of Education, S’pore) NMRC (Natl Medical Research Council, S’pore) Published version

EGD is the most vital procedure for the diagnosis of upper GI lesions. We aimed to compare the performance of unsedated ultrathin transoral endoscopy (U-TOE), unsedated conventional EGD (C-EGD), and sedated C-EGD with or without the use of an artificial intelligence (AI) system.In this prospective, single-blind, 3-parallel-group, randomized, single-center trial, 437 patients scheduled to undergo outpatient EGD were randomized to unsedated U-TOE, unsedated C-EGD, or sedated C-EGD, and each group was then divided into 2 subgroups: with or without the assistance of an AI system to monitor blind spots during EGD. The primary outcome was the blind spot rate of these 3 groups with the assistance of AI. The secondary outcomes were to compare blind spot rates of unsedated U-TOE, unsedated, and sedated C-EGD with or without the assistance of AI, respectively, and the concordance between AI and the endoscopists' review.The blind spot rate with AI-assisted sedated C-EGD was significantly lower than that of unsedated U-TOE and unsedated C-EGD (3.42% vs 21.77% vs 31.23%, respectively; P .05). The blind spot rate of the AI subgroup was lower than that of the control subgroup in all 3 groups (sedated C-EGD: 3.42% vs 22.46%, P .001; unsedated U-TOE: 21.77% vs 29.92%, P .001; unsedated C-EGD: 31.23% vs 42.46%, P .001).The blind spot rate of sedated C-EGD was the lowest among the 3 types of EGD, and the addition of AI had a maximal effect on sedated C-EGD. (Clinical trial registration number: ChiCTR1900020920.).

As an emerging technique capable of providing cellular/subcellular-level tissue microstructure images, optical coherence tomography (OCT) is regarded to be a viable tool for early disease diagnosis, yet few studies on pancreatic imaging have ever been reported in literature. In this paper, we utilized a lab-built micro-OCT (μOCT) for cellular/subcellular pancreatic imaging for both normal tissues and those specimens with edema, and evaluate the feasibility of OCT as an imaging tool for early pancreatic disease diagnosis. Results show that the cellular/subcellular-level pancreatic microstructures of normal tissues could be clearly identified, and is quite different from those in tissues with edema. Such results demonstrate the great potential of μOCT as a viable tool for pancreatic tissue imaging in clinical practice.

The tumor suppressor gene phosphatase and tensin homolog (PTEN) is frequently mutated in colon cancer. However, the potential contribution of loss of PTEN to colon cancer progression remains unclear. In this study, we demonstrated that PTEN overexpression or knockdown in Lovo colon cancer cells decreased or increased paxillin expression, respectively. Moreover, paxillin reversed PTEN-mediated inhibition of Lovo cell invasion and migration. Overexpression of PTEN in an orthotropic colon cancer nude mice model inhibited tumor formation and progression. In addition, PTEN protein level was negatively correlated with that of paxillin in human colon cancer tissues. Mechanistically, we identified three NF-κB binding sites on paxillin promoter and confirmed that paxillin was a direct transcriptional target of NF-κB. Our findings reveal a novel mechanism by which PTEN inhibits the progression of colon cancer by inhibiting paxillin expression downstream of PI3K/AKT/NF-κB pathway. Thereby, PTEN/PI3K/AKT/NF-κB/paxillin signaling cascade is an attractive therapeutic target for colon cancer progression.

The gemcitabine-insensitivity remains the main challenge for pancreatic cancer treatment. Thymoquinone, the predominant bioactive ingredient of Nigella sativa, has been shown to possess promising anti-cancer and chemo-sensitizing effects on pancreatic cancer, however, its meticulous mechanism is still indistinct.The objective of the present study was to investigate the potency of thymoquinone in combination with gemcitabine in inducing apoptosis and preventing the development of gemcitabine-insensitivity in pancreatic cancer cells.The anti-tumor effects of thymoquinone and gemcitabine were analyzed via evaluation of alterations of cell viability, tumor weight, apoptosis-related proteins, caspase-3, -9 activities and NF-κB DNA binding activity in pancreatic cancer cells in vitro and PANC-1 cells orthotopic xenograft in vivo.Thymoquinone pretreatment following gemcitabine treatment synergistically caused an increase in pancreatic cancer cells apoptosis and tumor growth inhibition both in vitro and in vivo. The novel combinational regimen also contributes to alterations of multiple molecular signaling targets, such as the suppression of Notch1, NICD accompanying with up-regulation of PTEN, the inactivation of Akt/mTOR/S6 signaling pathways, and the suppression of phosphorylation and nuclear translocation of p65 induced by TNF-α. Thymoquinone pretreatment and gemcitabine also induced down-regulation of anti-apoptotic Bcl-2, Bcl-xL, XIAP and up-regulation and activation of pro-apoptotic molecules including Caspase-3, Caspase-9, Bax and increased release of cytochrome c.This novel modality of thymoquinone pretreatment can enhance the anti-cancer activity of gemcitabine and may be a promising option in the treatment of pancreatic cancer.

Pancreatic cancer is highly metastatic and with poor prognosis. In previous studies, lysophosphatidic acid (LPA) was shown to be a critical component of ascites which promoted the invasion and metastasis of pancreatic cancer. Two focal adhesion proteins, focal adhesion kinase (FAK) and paxillin, were crucially involved in cell migration, cytoskeleton reorganization, and the dynamics of focal adhesion. This study examined the involvement of LPA1–3 in LPA-induced activation of FAK and paxillin, and in cell motility, in pancreatic cancer PANC-1 cells. Reverse transcriptase polymerase chain reaction analysis was used to examine mRNA expression of LPA receptors in PANC-1. Cellular protein expression of FAK and paxillin was analyzed by western blotting. The subcellular location of FAK and paxillin was visualized by immunofluorescence. Cell migration was measured by use of a transwell migration chamber. Three LPA receptors (LPA1, LPA2, and LPA3) were significantly expressed in PANC-1 cells. Treatment with LPA induced both time and dose-dependent tyrosine phosphorylation of FAK and paxillin. LPA also affected translocation of FAK and paxillin from cytoplasm to focal adhesions at the cell periphery and enhanced cell motility of PANC-1. Pretreatment with 3-(4-(4-((1-(2-chlorophenyl)ethoxy)carbonyl amino)-3-methyl-5-isoxazolyl)benzylsulfanyl)propanoic acid (Ki16425), an antagonist of LPA1 and LPA3, before LPA attenuated the LPA-induced tyrosine phosphorylation and redistribution of FAK and paxillin and abrogated LPA-induced cellular migration activity. These results suggest LPA induces activation of FAK and paxillin via LPA1–3, which may contribute to the increased cell motility in human pancreatic cancer PANC-1 cells. Thus, an understanding of the regulation by LPA of cell motility in pancreatic cancer could identify novel targets for therapy.

We report a multiscale optical coherence tomography (OCT) system that is capable of providing three-dimensional (3D) human skin imaging in vivo both cellular-level resolution mode and large area scanning mode.