Early gastric cancer detection and lesion segmentation based on deep learning and gastroscopic images.

Gastric cancer is a highly prevalent disease that poses a serious threat to public health. In clinical practice, gastroscopy is frequently used by medical practitioners to screen for gastric cancer. However, the symptoms of gastric cancer at different stages of advancement vary significantly, particularly in the case of early gastric cancer (EGC). The manifestations of EGC are often indistinct, leading to a detection rate of less than 10%. In recent years, researchers have focused on leveraging deep learning algorithms to assist medical professionals in detecting EGC and thereby improve detection rates. To enhance the ability of deep learning to detect EGC and segment lesions in gastroscopic images, an Improved Mask R-CNN (IMR-CNN) model was proposed. This model incorporates a "Bi-directional feature extraction and fusion module" and a "Purification module for feature channel and space" based on the Mask R-CNN (MR-CNN). Our study includes a dataset of 1120 images of EGC for training and validation of the models. The experimental results indicate that the IMR-CNN model outperforms the original MR-CNN model, with Precision, Recall, Accuracy, Specificity and F1-Score values of 92.9%, 95.3%, 93.9%, 92.5% and 94.1%, respectively. Therefore, our proposed IMR-CNN model has superior detection and lesion segmentation capabilities and can effectively aid doctors in diagnosing EGC from gastroscopic images.

The safety of remimazolam versus propofol in gastroscopic sedation: a meta-analysis.

BACKGROUND: This meta-analysis was designed to compare the safety and efficiency of remimazolam with those of propofol in patients undergoing gastroscope sedation. METHODS: We searched PubMed, Cochrane Library, Embase, Ovid, Wanfang Database, China National Knowledge Infrastructure, SINOMED, and ClinicalTrials.gov for studies that reported on remimazolam versus propofol for gastroscope sedation from establishment to February 25, 2023. The sedative efficiency and the incidence of adverse events were assessed as outcomes. Version 2 of the Cochrane risk-of-bias assessment tool was used to assess the risk of bias. Review Manager 5.4 and STATA 17 were used to perform all statistical analyses. RESULTS: A total of 26 randomized controlled trials involving 3,641 patients were included in this meta-analysis. The results showed that remimazolam had a significantly lower incidence of respiratory depression (risk ratio [RR] = 0.40, 95% confidence interval [CI]: 0.28-0.57; p < 0.01, GRADE high), hypoxemia (RR = 0.34, 95% CI: 0.23-0.49; p < 0.01, GRADE high), bradycardia (RR = 0.34, 95% CI: 0.23-0.51; p < 0.01, GRADE high), dizziness (RR = 0.45, 95% CI: 0.31-0.65; p < 0.01, GRADE high), injection site pain (RR = 0.06, 95% CI: 0.03-0.13; p < 0.01, GRADE high), nausea or vomiting (RR = 0.79, 95% CI: 0.62-1.00; p = 0.05, GRADE moderate), and hypotension (RR = 0.36, 95% CI: 0.26-0.48; p < 0.01, GRADE low). CONCLUSIONS: Remimazolam can be used safely in gastroscopic sedation and reduces the incidence of respiratory depression, hypoxemia, bradycardia, injection site pain, and dizziness compared with propofol, and doesn't increase the incidence of nausea and vomiting.

Effective doses of ciprofol combined with alfentanil in inhibiting responses to gastroscope insertion, a prospective, single-arm, single-center study.

BACKGROUND: Ciprofol is a novel intravenous sedative and anesthetic. Studies have shown that it features a rapid onset of action, a fast recovery time, slight inhibition of respiratory and cardiovascular functions, and a low incidence of adverse reactions. This study aims to explore the median effective dose (ED50) and the 95% effective dose (ED95) of ciprofol in inhibiting responses to gastroscope insertion when combined with a low dose of alfentanil, and to evaluate its safety, to provide a reference for the rational use of ciprofol in clinical practices. METHODS: We included 25 patients aged 18-64 years of either sex who underwent gastroscopy under intravenous general anesthesia, with a Body Mass Index (BMI) 18-28 kg/m2, and an American Society of Anesthesiologists (ASA) grade I or II. In this study, the dose-finding strategy of ciprofol followed a modified Dixon's up-and-down method with an initial dose of 0.30 mg/kg and an increment of 0.02 mg/kg. Ciprofol was administered after intravenous injection of 7 µg/kg of alfentanil, and 2 min later a gastroscope was inserted. When the insertion response of one participant was positive (including body movement, coughing, and eye opening), an escalation of 0.02 mg/kg would be given to the next participant; otherwise, a de-escalation of 0.02 mg/kg would be administered. The study was terminated when negative response and positive response alternated 8 times. A Probit model was used to calculate the ED50 and ED95 of ciprofol in inhibiting responses to gastroscope insertion when combined with alfentanil. Patients' recovery time, discharge time, vital signs and occurrence of adverse reactions were recorded. RESULTS: The ED50 of single-dose intravenous ciprofol injection with 7 µg/kg of alfentanil in inhibiting gastroscope insertion responses was 0.217 mg/kg, and the ED95 was 0.247 mg/kg. Patients' recovery time and discharge time were 11.04 ± 1.49 min and 9.64 ± 2.38 min, respectively. The overall incidence of adverse reactions was 12%. CONCLUSION: The ED50 of ciprofol combined with 7 µg/kg of alfentanil in inhibiting gastroscope insertion responses was 0.217 mg/kg, and the ED95 was 0.247 mg/kg. Ciprofol showed a low incidence of anesthesia-related adverse events. TRIAL REGISTRATION: http://www.chictr.org.cn (ChiCTR2200061727).

Hemostatic Spray TC-325 (Hemospray®) and Unexpected Esophageal Entrapment of Gastroscope With Airway Management Considerations: A Case Report.

Bleeding from the upper gastrointestinal tract is responsible for approximately 2% of all hospital admissions annually, with an up to 17% mortality rate. Therapeutic endoscopic interventions are often indicated for establishing hemostasis. These interventions include but are not limited to thermal coagulation with cautery, mechanical methods using band ligation or hemostatic clips, and hemostatic spray. Anesthesia providers are frequently involved in providing sedation for those endoscopic procedures. In 2018, the United States Food and Drug Administration approved a hemostatic spray, Hemospray® TC-325 (Cook Medical, Winston- Salem, NC, USA) for controlling nonvariceal upper gastrointestinal bleeding. The inorganic, mineral-based powder forms a mechanical tamponade by absorbing water and attracting clotting factors to the bleeding site. Adverse events associated with using the product are reported as rare but have included perforation and difficulty in removing the gastroscope. This case presents unexpected entrapment of the gastroscope in a patient's esophagus after the bleeding site was treated with Hemospray. Potential difficulties with airway management strategies are discussed.

Exploring factors that influence the behavioural intention of medical students to use 3D gastroscopic model to learn how to operate gastroscope using UTAUT Model.

BACKGROUND: The application of virtual reality (VR) in gastroscopic operation teaching can be safe and effective, but the advantages can be realized only when students accept and use it. This study aims to identify the factors influencing Chinese clinical medical postgraduates on their intention to use the 3D gastroscopic model constructed based on VR technology using Unified Theory of Acceptance and Use of Technology (UTAUT) model. Students' demographic factors are also taken into consideration. METHODS: All methods were carried out in accordance with relevant guidelines. Data were collected from clinical medical postgraduates students in China using stratified sampling. A total of 292 questionnaires including valid responses were used in this study. Data were processed using Amos 24.0 and SPSS 26.0 software and the statistical analysis technique was based on structural equation modeling (SEM). RESULTS: The results showed that different from the mediator of home location and year of clinical learning, mediator of gender, university kind and graduate degree did not affect the behavioral intention. In addition, performance expectancy, facilitating condition, and social influence directly and indirectly have effect on behavioral intention. Also, the significance between social influence and performance expectancy, social influence and effort expectancy were verified. CONCLUSIONS: This study manifested that the proposed framework based on the UTAUT had explanatory power to identify the factors influencing the students' behavioral intention to use the 3D gastroscopic model constructed based on VR technology. Whereas, an important variable of effort expectancy in the frame of the SEM were not certified, thereby indicating that particular attention should be paid to this variable by universities and teachers before applying 3D gastroscopic model constructed based on VR technology in teaching. Added preparatory work is required such as explaining the basic knowledge of the operating steps of VR model and make students adequately understand its accessibility, which can probably improve the intentions of them to use it. The positive effects of social influence on performance expectancy and effort expectancy we proposed was also verified in this study, which provided a direction for future research.

Median effective dose (ED50) of esketamine combined with propofol for children to inhibit response of gastroscope insertion.

BACKGROUND: Propofol is the most commonly used drug for procedural sedation during gastroscopy. However, independent use of propofol can lead to increased dosage and additional side effects. Esketamine was found to be exceptional in combination with propofol for painless gastroscopy. No studies have calculated the median effective dose (ED50) of esketamine combined with propofol in pediatric painless gastroscopy. Here, we designed a research to study the ED50 of esketamine combined with propofol using the Dixon and Massey up-and-down sequential method for inhibiting the response of gastroscope insertion. METHODS: Children who met the inclusion and exclusion criteria were included in this study. Propofol and esketamine were used as anesthetics for painless gastroscopy in children. To explore the ED50, the initial propofol dose was set at 3 mg/kg in all children. The first child was given an esketamine dose of 0.1 mg/kg, followed by 30 s of slow bolus injection propofol. If anesthesia induction failed (coughing or body movement of children during gastroscope insertion), the esketamine dose was elevated in the next child, with a interval difference of 0.05 mg/kg. Otherwise, if the anesthesia induction was successful, the next dosage was reduced by 0.05 mg/kg. The study was stopped if nine crossover inflection points were reached. The ED50 of esketamine was calculated using probit regression, and the blood pressure, pulse oxygen saturation, heart rate, recovery time, and side effects were recorded in all children. RESULTS: A total of 26 children were included in this study. The ED50 of esketamine combined with 3 mg/kg propofol was 0.143 mg/kg (95% CI 0.047-0.398 mg/kg). The total consumption of propofol was 16.04 ± 5.37 mg. The recovery time was 16.38 ± 8.70 min. Adverse effects recorded were delayed awakening in two cases and increased oral secretions of another child during the examination inducing cough and hypoxemia (86% was the lowest). DISCUSSION: The ED50 of esketamine was 0.143 mg/kg when combined with 3 mg/kg propofol for successful sedation in pediatric gastroscope insertion. This sub-anaesthetic dose of esketamine was safe and efficacious with few complications in pediatric painless gastroscopy. TRIAL REGISTRATION: The study was registered at the Chinese Clinical Trial Registry ( www.chictr.org.cn ; registration number: ChiCTR2100052830 on 06/11/2021).

Evaluation of a single-use gastroscope in patients presenting with suspected upper gastrointestinal hemorrhage: a pilot feasibility study (One-Scope I).

BACKGROUND : Outbreaks of multidrug-resistant bacteria due to contaminated duodenoscopes and infection risks during the COVID-19 pandemic have driven the development of single-use endoscopes. The first single-use gastroscope is now available in Europe. Besides waste disposal and cost issues, the infection risk and performance remain unclear. We aimed to evaluate a single-use gastroscope in patients with signs of upper gastrointestinal bleeding. METHODS : 20 consecutive patients presenting with clinical signs of upper gastrointestinal bleeding between October and November 2022 were included in this case series. The primary aim was technical success, defined as access to the descending duodenum and adequate assessment of the upper gastrointestinal tract for the presence of a bleeding site. RESULTS : The primary aim was achieved in 19/20 patients (95 %). The bleeding site was identified in 18 patients. A therapeutic intervention was performed in six patients (two cap-mounted clips, one standard hemostatic clip, two variceal band ligations, one hemostatic powder, two adrenaline injections); technical and clinical success were achieved in all six patients. Two crossovers to a standard gastroscope occurred. CONCLUSIONS : Use of single-use gastroscopes may be feasible for patients presenting for urgent endoscopic evaluation and treatment of upper gastrointestinal bleeding.

Percutaneous transhepatic intraportal biopsy using gastroscope biopsy forceps for diagnosis of a pancreatic neuroendocrine neoplasm: A case report.

BACKGROUND: Pancreatic neuroendocrine neoplasms (PNENs) are a rare group of neoplasms originating from the islets of the Langerhans. Portal vein tumor thrombosis has been reported in 33% of patients with PNENs. While the histopathological diagnosis of PNENs is usually based on percutaneous biopsy or endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA), these approaches may be impeded by gastric varices, poor access windows, or anatomically contiguous critical structures. Obtaining a pathological diagnosis using a gastroscope biopsy forceps via percutaneous transhepatic intravascular pathway is an innovative method that has rarely been reported. CASE SUMMARY: A 72-year-old man was referred to our hospital for abdominal pain and melena. Abdominal contrast-enhanced magnetic resonance imaging revealed a well-enhanced tumor (size: 2.4 cm × 1.2 cm × 1.2 cm) in the pancreatic tail with portal vein invasion. Traditional pathological diagnosis via EUS-FNA was not possible because of diffuse gastric varices. We performed a percutaneous transportal biopsy of the portal vein tumor thrombus using a gastroscope biopsy forceps. Histopathologic examination revealed a pancreatic neuroendocrine neoplasm (G2) with somatostatin receptors 2 (+), allowing systemic treatment. CONCLUSION: Intravascular biopsy using gastroscope biopsy forceps appears to be a safe and effective method for obtaining a histopathological diagnosis. Although well-designed clinic trials are required to obtain more definitive evidence, this procedure may help improve the diagnosis of portal vein thrombosis and related diseases.

Efficacy of a Gastroscope for Cecal Intubation during Colonoscopy in Patients with Severe Sigmoid Adhesion.

BACKGROUND: Cecal intubation during colonoscopy is difficult to achieve in patients with severe sigmoid adhesions. This retrospective observational study assessed the efficacy of using a gastroscope for colonoscopy in patients with severe sigmoid adhesions. Furthermore, the ability of computed tomography (CT) to predict the possibility of cecal intubation using a gastroscope was examined. METHODS: A total of 1,626 patients who underwent colonoscopy for total colon observation by one endoscopist were enrolled. Cecal intubation rate and other procedure-related outcomes were evaluated. We also investigated whether identification of the sigmoid colon pathway by CT was involved in cecal intubation rate using a gastroscope. RESULTS: Of the enrolled patients, cecal intubation by colonoscope was not feasible in 19 patients (1.2%) because of severe sigmoid adhesions. Cecal intubation was possible in 13 patients (68.4%) using a gastroscope, and the cecal intubation rate of peritoneal carcinomatosis (0%, p < 0.01) was significantly lower than that of other causes such as a diverticulum (100%) and history of gynecologic surgery (80%). The identifiable case of the sigmoid colon pathway by horizontal section on CT showed significantly higher cecal intubation rate compared to those of unidentifiable cases (92.3% vs. 16.7%, p < 0.01). CONCLUSION: Using a gastroscope is effective in performing cecal intubation during colonoscopy in patients with severe sigmoid adhesions. However, in patients with sigmoid adhesions caused by peritoneal carcinomatosis, cecal intubation may be difficult, even when a gastroscope is used. The ability of CT to identify the sigmoid colon pathway may predict success of cecal intubation.

Effect of an automated flexible endoscope channel brushing system on improving reprocessing quality: a randomized controlled study.

BACKGROUND: Qualified reprocessing, of which meticulous channel brushing is the most crucial step, is essential for prevention and control of endoscopy-associated infections. However, channel brushing is often omitted in practice. This study aimed to evaluate the effect of an automated flexible endoscope channel brushing system (AECBS) on improving the quality of endoscope reprocessing. METHODS: This prospective, randomized controlled study was conducted between 24 November 2021 and 22 January 2022 at Renmin Hospital of Wuhan University, China. Eligible endoscopes were randomly allocated to the auto group (channels brushed by AECBS) or the manual group (channels brushed manually), with sampling and culturing after high-level disinfection and drying. The primary end point was the proportion of endoscopes with positive cultures. RESULTS: 204 endoscopes in the auto group and 205 in the manual group were analyzed. The proportion of endoscopes with positive cultures was significantly lower in the auto group (15.2 % [95 %CI 10.7 %-21.0 %]) than in the manual group (23.4 % [95 %CI 17.9 %-29.9 %]). CONCLUSIONS: AECBS could effectively reduce bioburden and improve reprocessing quality of gastroscopes and colonoscopes. AECBS has the potential to replace manual brushing and lower the risk of endoscopy-associated infections, providing a new option for the optimization of reprocessing.

A monocular SLAM system based on SIFT features for gastroscope tracking.

During flexible gastroscopy, physicians have extreme difficulties to self-localize. Camera tracking method such as simultaneous localization and mapping (SLAM) has become a research hotspot in recent years, allowing tracking of the endoscope. However, most of the existing solutions have focused on tasks in which sufficient texture information is available, such as laparoscope tracking, and cannot be applied to gastroscope tracking since gastroscopic images have fewer textures than laparoscopic images. This paper proposes a new monocular SLAM framework based on scale-invariant feature transform (SIFT) and narrow-band imaging (NBI), which extracts SIFT features instead of oriented features from accelerated segment test (FAST) and rotated binary robust independent elementary features (BRIEF) features from gastroscopic NBI images, and performs feature retention based on the response sorting strategy for achieving more matches. Experimental results show that the root mean squared error of the proposed algorithm can reach a minimum of 2.074 mm, and the pose accuracy can be improved by up to 25.73% compared with oriented FAST and rotated BRIEF (ORB)-SLAM. SIFT features and response sorting strategy can achieve more accurate matching in gastroscopic NBI images than other features and homogenization strategy, and the proposed algorithm can also run successfully on real clinical gastroscopic data. The proposed algorithm has the potential clinical value to assist physicians in locating the gastroscope during gastroscopy.

Endoscopic full-thickness resection of a complete extraluminal growth gastric gastrointestinal stromal tumor with a single-channel gastroscope.

A 54-year-old man was found a suspected gastric mass in a routine physical examination of chest computed tomography without abdominal symptoms for 1-month duration. Abdominal contrast-enhanced computed tomography demonstrated a clear boundary and complete extraluminal growth mass in the greater gastric curvature, which measured 20-mm with central punctate calcification and homogeneous enhancement.

Effect of intravenous lidocaine on the ED50 of propofol for inserting gastroscope without body movement in adult patients: a randomized, controlled study.

BACKGROUND: Circulatory and respiratory depression are common problems that occur in propofol alone sedation during gastroscopy. As a widely used analgesic adjuvant, intravenous lidocaine can reduce the consumption of propofol during Endoscopic retrograde cholangiopancreatography (ERCP) or colonoscopy. However, it is still unknown the median effective dose (ED50) of propofol when combined with lidocaine intravenously. This study aimed to compare the ED50 of propofol with or without intravenous lidocaine for inserting gastrointestinal endoscope successfully. METHODS: Fifty nine patients undergoing gastroscopy or gastrointestinal (GI) endoscopy were randomly divided into control group (Group C, normal saline + propofol) or lidocaine group (Group L, lidocaine + propofol). Patients were initially injected a bolus of 1.5 mg/kg lidocaine in Group L, whereas equivalent volume of 0.9% saline in Group C. Anaesthesia was then induced with a single bolus of propofol in all subjects. The induction dose of propofol was determined by the modified Dixon's up-and-down method, and the initial dose was 1.5 mg/kg in both groups. The primary outcome was the ED50 of propofol induction dose with or without intravenous lidocaine. The secondary outcomes were the induction time, the first propofol bolus time (FPBT: from MOAA/S score ≤ 1 to first rescue bolus propofol), and adverse events (AEs: hypoxemia, bradycardia, hypotension, and body movements). RESULTS: Totally, 59 patients were enrolled and completed this study. The ED50 of propofol combined with lidocaine was 1.68 ± 0.11 mg/kg, significantly reduced compared with the normal saline group, 1.88 ± 0.13 mg/kg (P = 0.002). There was no statistical difference in induction time (P = 0.115) and the FPBT (P = 0.655) between the two groups. There was no significantly difference about the AEs between the two groups. CONCLUSION: The ED50 of propofol combined with intravenous lidocaine for successful endoscope insertion in adult patients, was 1.68 ± 0.11 mg/kg significantly reduced compared with the control group. TRIAL REGISTRATION: Chinese Clinical Trial Registry, No: ChiCTR2200059450. Registered on 29 April 2022. Prospective registration. http://www.chictr.org.cn .