Real-World Application of Artificial Intelligence for Detecting Pathologic Gastric Atypia and Neoplastic Lesions.

PURPOSE: Results of initial endoscopic biopsy of gastric lesions often differ from those of the final pathological diagnosis. We evaluated whether an artificial intelligence-based gastric lesion detection and diagnostic system, ENdoscopy as AI-powered Device Computer Aided Diagnosis for Gastroscopy (ENAD CAD-G), could reduce this discrepancy. MATERIALS AND METHODS: We retrospectively collected 24,948 endoscopic images of early gastric cancers (EGCs), dysplasia, and benign lesions from 9,892 patients who underwent esophagogastroduodenoscopy between 2011 and 2021. The diagnostic performance of ENAD CAD-G was evaluated using the following real-world datasets: patients referred from community clinics with initial biopsy results of atypia (n=154), participants who underwent endoscopic resection for neoplasms (Internal video set, n=140), and participants who underwent endoscopy for screening or suspicion of gastric neoplasm referred from community clinics (External video set, n=296). RESULTS: ENAD CAD-G classified the referred gastric lesions of atypia into EGC (accuracy, 82.47%; 95% confidence interval [CI], 76.46%-88.47%), dysplasia (88.31%; 83.24%-93.39%), and benign lesions (83.12%; 77.20%-89.03%). In the Internal video set, ENAD CAD-G identified dysplasia and EGC with diagnostic accuracies of 88.57% (95% CI, 83.30%-93.84%) and 91.43% (86.79%-96.07%), respectively, compared with an accuracy of 60.71% (52.62%-68.80%) for the initial biopsy results (P<0.001). In the External video set, ENAD CAD-G classified EGC, dysplasia, and benign lesions with diagnostic accuracies of 87.50% (83.73%-91.27%), 90.54% (87.21%-93.87%), and 88.85% (85.27%-92.44%), respectively. CONCLUSIONS: ENAD CAD-G is superior to initial biopsy for the detection and diagnosis of gastric lesions that require endoscopic resection. ENAD CAD-G can assist community endoscopists in identifying gastric lesions that require endoscopic resection.

Double contrast-enhanced ultrasonography improves diagnostic accuracy of T staging compared with multi-detector computed tomography in gastric cancer patients.

BACKGROUND: Gastric cancer (GC) is the most common malignant tumor and ranks third for cancer-related deaths among the worldwide. The disease poses a serious public health problem in China, ranking fifth for incidence and third for mortality. Knowledge of the invasive depth of the tumor is vital to treatment decisions. AIM: To evaluate the diagnostic performance of double contrast-enhanced ultrasonography (DCEUS) for preoperative T staging in patients with GC by comparing with multi-detector computed tomography (MDCT). METHODS: This single prospective study enrolled patients with GC confirmed by preoperative gastroscopy from July 2021 to March 2023. Patients underwent DCEUS, including ultrasonography (US) and intravenous contrast-enhanced ultrasonography (CEUS), and MDCT examinations for the assessment of preoperative T staging. Features of GC were identified on DCEUS and criteria developed to evaluate T staging according to the 8th edition of AJCC cancer staging manual. The diagnostic performance of DCEUS was evaluated by comparing it with that of MDCT and surgical-pathological findings were considered as the gold standard. RESULTS: A total of 229 patients with GC (80 T1, 33 T2, 59 T3 and 57 T4) were included. Overall accuracies were 86.9% for DCEUS and 61.1% for MDCT (P < 0.001). DCEUS was superior to MDCT for T1 (92.5% vs 70.0%, P < 0.001), T2 (72.7% vs 51.5%, P = 0.041), T3 (86.4% vs 45.8%, P < 0.001) and T4 (87.7% vs 70.2%, P = 0.022) staging of GC. CONCLUSION: DCEUS improved the diagnostic accuracy of preoperative T staging in patients with GC compared with MDCT, and constitutes a promising imaging modality for preoperative evaluation of GC to aid individualized treatment decision-making.

Endoscopic full-thickness resection of a large gastric schwannoma and iatrogenic cervical esophageal perforations: A case report.

INTRODUCTION: Gastrointestinal schwannomas are most commonly found in the stomach. Owing to their nonspecific clinical and endoscopic presentations, distinguishing gastric schwannomas (GS) from other gastric submucosal tumors based on typical symptoms and endoscopic features is challenging. Endoscopic full-thickness resection (EFTR) is safe and effective for GS management; however, no standard method exists for the extraction of large gastric specimens after endoscopic treatment. CASE PRESENTATION: We report the case of a 72-year-old Chinese woman who presented with abdominal distension. DIAGNOSIS, INTERVENTIONS, AND OUTCOMES: Gastroscopy revealed a submucosal bulge on the anterior wall of the lower stomach near the greater curvature. Endoscopic ultrasonography and computed tomography suggested a stromal tumor. The patient underwent EFTR of the stomach, and the tumor was successfully removed. The surgical specimen, with a long-axis diameter of approximately 5.5 cm in vitro, was extracted using a snare. Subsequent endoscopic examination revealed longitudinal, full-thickness perforations > 2 cm at the esophageal entrance. Over 10 metal clips were used to seal the mucosa, and a gastrointestinal decompression tube was placed. Follow-up radiography performed at 1 week postoperatively revealed an esophageal mediastinal fistula, which required subsequent endoscopic intervention to close the fistula using metal clips. The patient showed improvement and was discharged at 3 weeks postoperatively. Follow-up esophageal radiography revealed no abnormalities. Postoperative immunohistochemical analysis indicated CD34 (-), CD117 (-), DOG-1 (-), Ki67 (1%), S-100 (+), SDHB (+), SOX-10 (+), and Desmin (-), confirming the diagnosis of GS. Three months postoperatively, gastroscopy showed that the esophageal perforation healed well, a white ulcer scar had formed locally, metal clips were found in the stomach body, and no recurrence was found. CONCLUSION: EFTR is effective for removing giant schwannomas, although the extraction of large specimens may result in iatrogenic cervical esophageal perforations. Perforations > 2 cm can be managed using endoscopic metal clip closure.

Gastroscopic observation and dose-volume histogram parameter study on gastrointestinal mucous injury for pancreatic cancer treated with TOMO.

To explore the relationships between gastrointestinal radiation injuries of pancreatic cancer patients treated with TOMO and dose-volume histogram parameters prospectively. Seventy patients with pancreatic cancer who underwent TOMO were enrolled in this prospective study from February 2015 to May 2020. The clinical and dose-volume histogram parameters of the patients were collected. The optimal dose parameters for gastrointestinal radiation ulcers were confirmed based on the receiver operating characteristic curve (ROC) and the area below the ROC curve. Acute gastrointestinal tract toxic and side effect and injury grading correlation analyzed by Kruskal-Wallis rank sum test. Gastrointestinal injury often occurs during radiotherapy for pancreatic cancer, as observed using gastroscopy. The main adverse reactions were radioactive gastrointestinal inflammation (58.5%), radioactive gastrointestinal ulcers (41.4%), active bleeding (10%), newly-developed gastric retention (8.6%), and gastric varices (5.7%). As for the stomach, Dmean and V10 were related to radiation ulcer injury. ROC curve indicated that for stomach a Dmean of 13.39 Gy (area under ROC curves = 0.74, P = .048) and a V10 of 72.21% (area = 0.74, P = .048) was the tolerated dose for the injury of stomach radiation ulcer. As for duodenum, aV20 and aV25 are related to radiation ulcer injury. ROC curve indicated that aV20 of 22.82 cm3 (area = 0.68, P = .025) and aV25 of 32.04 cm3 (area = 0.66, P < .047) was the tolerated dose for the injury of duodenum radiation ulcer. The acute gastrointestinal tract toxic and side effects have no significant correlation with injury grading under gastroscope. Dmean > 13.39 Gy and V10 > 72.21% were the key dosimetric indices for predicting radiation-induced gastric ulcer, and aV20 > 22.82 cm3 and aV25 > 32.04 cm3 were for duodenal. Gastrointestinal reactions cannot be used as an overall basis for the diagnosis of gastrointestinal injury, and gastroscopy is recommended as a review item after radiotherapy.

The long-term outcome and risk factors of histologic discrepancy between forceps biopsies and endoscopic resections in early gastric cancer: An observational study.

Although endoscopic forceps biopsy is the gold standard for early gastric cancer (EGC) diagnosis, the method can cause endoscopic resection of specimens and histological discrepancies. This study aims to examine the risk factors for histological discrepancies in EGC and long-term clinical outcomes. This retrospective study included patients diagnosed with differentiated-type EGC using forceps biopsy. Patients without histological discrepancies and with undifferentiated types in endoscopic resection histology were categorized into the concordant and discordant groups, respectively. Clinical characteristics and long-term outcomes related to histological discrepancies were analyzed. A total of 957 lesions from 936 patients were enrolled. An overall discrepancy rate of 8.7% was confirmed, with an undifferentiated-type discrepancy of 5.5%. The discordant group showed a higher tendency for lesions to be located in the upper third region, to have whitish discoloration, and to undergo a greater number of biopsies compared with the concordant group. Multivariate analysis confirmed that lesion location in the upper third region (odds ratio [OR]: 2.125; 95% confidence interval [CI]: 1.032-5.277; P = .041) and whitish surface discoloration (OR: 13.615; 95% CI: 6.028-28.728; P = .001) were significantly correlated with histologic discrepancy. Compared with the concordant group, the discordant group had a lower curative resection rate, but no differences were observed in complications, local recurrence, or survival rates. Upper third location and whitish discoloration were risk factors for the histologic discrepancy between differentiated and undifferentiated types in patients with EGC. For curative resections performed in patients with EGC and histologic discrepancies and without additional treatment, careful follow-up is possible.

The Outcome of Snare-Assisted Traction Endoscopic Full-Thickness Resection for the Gastric Fundus Submucosal Tumors Originating from the Muscularis Propria.

Aim: To explore the feasibility and effectiveness of snare-assisted traction endoscopic full thickness resection (EFTR) on gastric fundus submucosal tumors (SMTs). Methods: The clinical and pathological data of patients with gastric SMTs who underwent EFTR treatment at the Endoscopy Center of Kaifeng Central Hospital from January 2018 to June 2023 were collected. Among them, 36 patients underwent snare-assisted traction EFTR (SAT-EFTR) and 46 patients underwent standard EFTR (S-EFTR). The clinical baseline data, operative data, adverse events, and follow-up results of the two groups were collected and compared. Results: All patients successfully completed EFTR technique. There were 34 male and 48 female patients, with an average age of (56.62 ± 11.31) years. The average operation time was shorter in the snare-assisted EFTR group than the S-EFTR group (73.39 ± 31.33 minutes versus 92.89 ± 37.57 minutes, P = .014). In addition, the resection speed of the snare-assisted EFTR group was also significantly faster than that of the S-EFTR group (4.04 ± 2.23 versus 2.48 ± 0.93 mm2/min, P < .001). There was no statistically significant difference in the age, gender, lesion size, postoperative fasting duration, and postoperative hospitalization stay between the two groups (P > .05). One patient in the SAT-EFTR group developed delayed postoperative perforation which was close with purse­string suture technique. All patients were discharged successfully, and there was no recurrence or metastasis during the follow-up period. Conclusion: Snare-assisted traction of EFTR could shorten the operation time, reduce the difficulty of the operation, and improve the efficiency of the operation. At the same time, this method is simple and easy to learn, more suitable for beginners, and worthy of clinical promotion and application.

Determination of ED50 and ED95 of remimazolam besylate combined with alfentanil for adult gastroscopy: a prospective dose-finding study.

BACKGROUND: To explore the median effective dose (ED50) and 95% effective dose (ED95) of remimazolam besylate combined with alfentanil for adult gastroscopy. METHODS: This prospective studyenrolled 31 patients scheduled to painless gastroscopy at Anhui No. 2 Provincial People's Hospital between April and May, 2022. 5 µg.kg-1 of alfentanil hydrochloride was used for pre-analgesia. The initial single loading dose of remimazolam besylate was 0.12 mg.kg-1, increased or reduced by 0.01 mg.kg-1 for the next patient with modified Dixon sequential method. The modified Observer's Assessment of Alertness/Sedation Scale (MOAA/S) was used to assess sedation. RESULTS: Combined with alfentanil, the ED50 of remimazolam besylate was 0.147 mg.kg-1 (95% CI: 0.138-0.160 mg.kg-1) and ED95 0.171 mg.kg-1 (95% CI: 0.159-0.245 mg.kg-1). The induction time after injection of remimazolam besylate was 70 ± 25 s, with the anesthesia recovery time and the observation time in resuscitation room 5.13 ± 2.13 min and 2.32 ± 1.6 min, respectively. Twenty nine patients' vital signs were within acceptable limits during gastroscopy. CONCLUSIONS: The ED50 of remimazolam besylate combined with alfentanil for painless gastroscopy was 0.147 mg.kg-1, and the ED95 was 0.171 mg.kg-1.

Artificial intelligence for gastric cancer in endoscopy: From diagnostic reasoning to market.

Recognition of gastric conditions during endoscopy exams, including gastric cancer, usually requires specialized training and a long learning curve. Besides that, the interobserver variability is frequently high due to the different morphological characteristics of the lesions and grades of mucosal inflammation. In this sense, artificial intelligence tools based on deep learning models have been developed to support physicians to detect, classify, and predict gastric lesions more efficiently. Even though a growing number of studies exists in the literature, there are multiple challenges to bring a model to practice in this field, such as the need for more robust validation studies and regulatory hurdles. Therefore, the aim of this review is to provide a comprehensive assessment of the current use of artificial intelligence applied to endoscopic imaging to evaluate gastric precancerous and cancerous lesions and the barriers to widespread implementation of this technology in clinical routine.

Diagnostic Performance of Near-Infrared Fluorescent Marking Clips in Laparoscopic Gastrectomy.

INTRODUCTION: Accurate tumor localization and resection margin acquisition are essential in gastric cancer surgery. Preoperative placement of marking clips in laparoscopic gastrectomy as well as intraoperative gastroscopy can be used for gastric cancer surgery. However, these procedures are not available at all institutions. We conducted a prospective clinical trial to investigate the diagnostic performance of near-infrared fluorescent clips (ZEOCLIP FS) in laparoscopic gastrectomy. MATERIALS AND METHODS: Patients with gastric cancer or neuroendocrine tumor in whom laparoscopic distal, pylorus-preserving, or proximal gastrectomy was planned were enrolled (n = 20) in this study. Fluorescent clips were placed proximal and/or distal to the tumor via gastroscopy on the day before surgery. During surgery, the clips were detected using a fluorescent laparoscope, and suturing was performed where fluorescence was detected. The clip locations were then confirmed via gastroscopy, and the stomach was transected. The primary endpoint was the detection rate of the marking clips using fluorescence, and the secondary endpoints were complications and distance between the clips and stitches. RESULTS: Among the 20 patients enrolled, distal and pylorus-preserving gastrectomies were performed in 18 and 2 patients, respectively. All clips were detected in 15 patients, indicating a detection rate of 75.0% (90% confidence interval: 54.4%-89.6%). Furthermore, no complications related to the clips were observed. The median distance between the clips and stitches was 5 (range, 0-10) mm. CONCLUSIONS: We report the feasibility and safety of preoperative placement and intraoperative detection of near-infrared fluorescent marking clips in laparoscopic gastrectomy.

Clinical outcomes of endoscopic resection for the treatment of intermediate- or high-risk gastric small gastrointestinal stromal tumors: a multicenter retrospective study.

BACKGROUND AND AIMS: Many studies of gastric gastrointestinal stromal tumors (g-GISTs) following endoscopic resection (ER) have typically focused on tumor size, with most tumors at low risk of aggressiveness after risk stratification. There have been few systematic studies on the oncologic outcomes of intermediate- or high-risk g-GISTs after ER. METHODS: From January 2014 to January 2020, we retrospectively collected patients considered at intermediate- or high-risk of g-GISTs according to the modified NIH consensus classification system. The primary outcome was overall survival (OS). RESULTS: Six hundred and seventy nine (679) consecutive patients were diagnosed with g-GISTs and treated by ER between January 2014 and January 2020 in three hospitals in Shanghai, China. 43 patients (20 males and 23 females) were confirmed at intermediate-or high-risk. The mean size of tumors was 2.23 ± 1.01 cm. The median follow-up period was 62.02 ± 15.34 months, with a range of 28 to 105 months. There were no recurrences or metastases, even among patients having R1 resections. The 5-year OS rate was 97.4% (42/43). CONCLUSION: ER for intermediate- or high-risk gastric small GISTs is a feasible and safe method, which allows for a wait-and-see approach before determining the necessity for imatinib adjuvant or surgical treatment. This approach to g-GISTs does require that patients undergo close follow-up.

High-flow nasal cannula oxygen reduced hypoxemia in patients undergoing gastroscopy under general anesthesia at ultra-high altitude: a randomized controlled trial.

BACKGROUND: Hypoxemia can occur in people at ultra-high altitude (above 3500 m) even at rest, and patients undergoing gastroscopy under general anesthesia have higher risk of hypoxemia. Supplementary oxygen via standard nasal cannula (SNC) is the standard of care for most patients who undergo gastroscopy under general anesthesia, which provides oxygen flow up to 15 L/min. High-flow nasal cannula (HFNC) could deliver oxygen at a rate up to 60 L/min, which is recommended by the American Society of Anesthesiologists Practice Guidelines. We speculated that the benefit with HFNC is more prominent in high-altitude areas, and aimed to compare the incidence of hypoxemia during gastroscopy under general anesthesia at ultra-high altitude with oxygen supply via either HFNC or SNC. METHODS: The trial was registered at at Chinese Clinical Trial Registry (ChiCTR2100045513; date of registration on 18/04/2021). Adult patients undergoing gastroscopy with anesthesia (estimated duration of anesthesia at ≥ 15 min) were randomized at a 1:1 ratio to receive HFNC oxygen or SNC oxygen. The primary outcome was hypoxemia (SpO2 < 90% for any duration). Secondary outcomes included severe hypoxemia (SpO2 < 75% for any duration or SpO2 < 90% but ≥ 75% for ≥ 60 s) and hypotension, as defined by reduction of mean arterial blood pressure by ≥ 25% from the baseline. RESULTS: A total of 262 patients were enrolled: 129 in the HFNC group and 133 in the SNC group. All patients received the designated intervention. Student's t-test, Mann-Whitney U test and χ2 test were employed in the study. The rate of hypoxemia was 9.3% (12/129) in the HFNC group versus 36.8% (49/133) in the SNC group [risk ratio (95% confidence interval): 0.25(0.14-0.45); P < 0.001). The HFNC group also had lower rate of severe hypoxemia [0.0% (0/129) versus 11.3% (15/133); risk ratio (95% confidence interval): 0.03(0.00-0.55); P < 0.001, respectively]. The rate of hypotension did not differ between the 2 groups [22.5% (29/129) in HFNC group versus 21.1% (28/133) in SNC group; risk ratio (95% confidence interval): 1.07(0.67-1.69) ; P = 0.779]. CONCLUSION: HFNC oxygen reduced the incidence of hypoxemia during anesthesia in adult patients undergoing gastroscopy at ultra-high altitude.