Objectives/Hypothesis
To develop a deep‐learning‐based automatic diagnosis system for identifying nasopharyngeal carcinoma (NPC) from noncancer (inflammation and hyperplasia), using both white light imaging (WLI) and narrow‐band imaging (NBI) nasopharyngoscopy images.
Study Design
Retrospective study.
Methods
A total of 4,783 nasopharyngoscopy images (2,898 WLI and 1,885 NBI) of 671 patients were collected and a novel deep convolutional neural network (DCNN) framework was developed named Siamese deep convolutional neural network (S‐DCNN), which can simultaneously utilize WLI and NBI images to improve the classification performance. To verify the effectiveness of combining the above‐mentioned two modal images for prediction, we compared the proposed S‐DCNN with two baseline models, namely DCNN‐1 (only considering WLI images) and DCNN‐2 (only considering NBI images).
Results
In the threefold cross‐validation, an overall accuracy and area under the curve of the three DCNNs achieved 94.9% (95% confidence interval [CI] 93.3%–96.5%) and 0.986 (95% CI 0.982–0.992), 87.0% (95% CI 84.2%–89.7%) and 0.930 (95% CI 0.906–0.961), and 92.8% (95% CI 90.4%–95.3%) and 0.971 (95% CI 0.953–0.992), respectively. The accuracy of S‐DCNN is significantly improved compared with DCNN‐1 (P‐value <.001) and DCNN‐2 (P‐value = .008).
Conclusion
Using the deep‐learning technology to automatically diagnose NPC under nasopharyngoscopy can provide valuable reference for NPC screening. Superior performance can be obtained by simultaneously utilizing the multimodal features of NBI image and WLI image of the same patient.
Level of Evidence
3 Laryngoscope, 132:999–1007, 2022
Background: This research aimed at investigating the safety and efficacy of autologous esophageal mucosa (AEM) with polyglycolic acid (PGA) transplantation and temporary stent implantation (TSI) in preventing esophageal stenosis (ES) after early esophageal cancer (EC) surgery.Methods: Between April 2019 and October 2020, patients scheduled for circumferential endoscopic submucosal dissection (ESD) were prospectively recruited. After ESD, autologous esophageal mucosal patches (MPs) were constructed on the absorbable PGA felt. Then, the felt was structured onto a covered metal mesh stent (CMMS) and attached to the ulcer surface. The stents were removed 6-8 weeks after the operation. The occurrence of ES and adverse events was observed and analyzed.Results: Data from 25 patients were analyzed. In total, 14 patients (56%) had no stenosis during an average follow-up of 10.2 months, and 11 patients (44%) suffered strictures at a mean interval of 63.73 days after the ESD procedure. Stent migration occurred in 2 patients. No other complications, including perforations, bleeding, or wound infections, occurred. The median of endoscopic balloon dilatation (EBD) sessions was 2.16 (range, 0-14). There showed a higher post-ESD stricture rate in patients with lesions located in the middle-lower esophagus (P<0.05). More transplanted MPs may reduce the occurrence of ES.Conclusions: AEM with PGA transplantation and TSI is a safe and effective approach of preventing ES and improving the life quality after circumferential ESD.
Background:
To observe and preliminarily evaluate the efficacy and safety of endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) in the treatment of non-ampullary duodenal lesions (NADLs).
Methods:
This retrospective observational study included 84 patients who underwent endoscopic resection (ER) with non-ampullary duodenal lesions, between March 2010 and November 2020, at the Cancer Hospital of the Chinese Academy of Medical Sciences (Beijing, China). Data on patient demographics, therapeutic outcomes, and follow-up results were analyzed.
Results:
There were 44 patients undergoing EMR, and 40 patients accepting ESD. The overall en bloc resection rate was 98.8% (83/84). For the neoplastic lesions, the overall en bloc resection rate and curative rate were 98.5% (67/68) and 89.7% (61/68), respectively. The procedure-related bleeding and perforation rates were 2.4% and 10.7%, respectively. Univariate analysis results indicated that the main correlation factor of non-curative pathologic resection was tumor size (p = 0.004) and resection size (
P
< 0.01). There showed a higher curative rate in patients with tumors less than 25 mm in diameter. Multivariate logistic regression analyses determined that the tumor size (OR 0.935; 95% CI 0.878-0.995;
P
= 0.035) was associated with non-curative resection. No recurrences were observed in patients who had undergone a complete ER during a follow-up period of 42.8 months (range, 3-127 months).
Conclusion:
Endoscopic resection is an effective, safe, and feasible treatment for non-ampullary duodenal lesions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.