Background Visual inspection, lesion detection, and differentiation between malignant and benign features are key aspects of an endoscopist’s role. The use of machine learning for the recognition and differentiation of images has been increasingly adopted in clinical practice. This study aimed to establish convolutional neural network (CNN) models to automatically classify gastric neoplasms based on endoscopic images.
Methods Endoscopic white-light images of pathologically confirmed gastric lesions were collected and classified into five categories: advanced gastric cancer, early gastric cancer, high grade dysplasia, low grade dysplasia, and non-neoplasm. Three pretrained CNN models were fine-tuned using a training dataset. The classifying performance of the models was evaluated using a test dataset and a prospective validation dataset.
Results A total of 5017 images were collected from 1269 patients, among which 812 images from 212 patients were used as the test dataset. An additional 200 images from 200 patients were collected and used for prospective validation. For the five-category classification, the weighted average accuracy of the Inception-Resnet-v2 model reached 84.6 %. The mean area under the curve (AUC) of the model for differentiating gastric cancer and neoplasm was 0.877 and 0.927, respectively. In prospective validation, the Inception-Resnet-v2 model showed lower performance compared with the endoscopist with the best performance (five-category accuracy 76.4 % vs. 87.6 %; cancer 76.0 % vs. 97.5 %; neoplasm 73.5 % vs. 96.5 %; P < 0.001). However, there was no statistical difference between the Inception-Resnet-v2 model and the endoscopist with the worst performance in the differentiation of gastric cancer (accuracy 76.0 % vs. 82.0 %) and neoplasm (AUC 0.776 vs. 0.865).
Conclusion The evaluated deep-learning models have the potential for clinical application in classifying gastric cancer or neoplasm on endoscopic white-light images.
Background and Aims
Catheter‐based endobiliary radiofrequency ablation (RFA) is an endoscopic local treatment for patients with malignant biliary stricture (MBS). However, excessive heating of the bile duct by the current RFA system can induce serious complications. Recently, a new RFA system with automatic temperature control was developed. In the present study, we examined the safety of the new RFA system in patients undergoing endobiliary RFA for extrahepatic MBS.
Methods
This prospective, multicenter study enrolled patients with unresectable or inoperable extrahepatic (> 2 cm from the hilum) MBS. Endobiliary RFA was performed using a newly developed RFA catheter (ELRA™, STARmed, Goyang, Korea) at a setting of 7 or 10 W for 120 s and with a target temperature of 80°C. A self‐expandable metallic stent was inserted after endobiliary RFA. The rate of procedure‐related adverse events was assessed.
Results
The 30 patients were enrolled in this study. Cholangiocarcinoma was diagnosed in 19 patients, pancreatic cancer was found in 9, and gallbladder cancers were recorded in 2. The mean stricture length was 22.1 ± 6.6 mm. Post‐procedural adverse events occurred in three patients (10.0%; 2 mild pancreatitis and 1 cholangitis) without hemobilia and bile duct perforation. The pancreatitis and cholangitis resolved with conservative treatment. The cumulative duration of stent patency and survival were 236 and 383 days, respectively.
Conclusions
Automatic temperature‐controlled endobiliary RFA using a newly developed catheter was safely applied in patents with extrahepatic MBS. Further prospective studies are needed to confirm the efficacy of endobiliary RFA for MBS.
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.