Abstract
Background and Aims: Endoscopic ultrasonography (EUS) is a useful diagnostic modality for evaluating gastric mesenchymal tumors; however, differentiating gastrointestinal stromal tumors (GISTs) from benign mesenchymal tumors such as leiomyomas and schwannomas remains challenging. For this reason, we developed a convolutional neural network computer-aided diagnosis (CNN-CAD) system that can analyze gastric mesenchymal tumors on EUS images. Methods: A total of 905 EUS images of gastric mesenchymal tumors (pathologically confirmed GIST, leiomyoma, and schwannoma) were used as a training dataset. Validation was performed using 212 EUS images of gastric mesenchymal tumors. This test dataset was interpreted by three experienced and three junior endoscopists. Results: The sensitivity, specificity, and accuracy of the CNN-CAD system for differentiating GISTs from non-GIST tumors were 83.0%, 75.5%, and 79.2%, respectively. Its diagnostic specificity and accuracy were significantly higher than those of two experienced and one junior endoscopists. In the further sequential analysis to differentiate leiomyoma from schwannoma in non-GIST tumors, the final diagnostic accuracy of the CNN-CAD system was 75.5%, which was significantly higher than that of two experienced and one junior endoscopists. Conclusions: Our CNN-CAD system showed high accuracy in diagnosing gastric mesenchymal tumors on EUS images. It may complement the current clinical practices in the EUS diagnosis of gastric mesenchymal tumors.
Highlights
Mesenchymal tumors of the stomach are mostly incidentally observed during routine esophagogastroduodenoscopy examinations, especially as part of the national gastric cancer screening programs in Korea; they appear as hard, elevated subepithelial lesions [1]
The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of the convolutional neural network computer-aided diagnosis (CNN-CAD) system to differentiate gastrointestinal stromal tumors (GISTs) from non-GIST tumors were 79.0%, 78.0%, 76.3%, 80.5%, and 78.5%, respectively
The sensitivity, specificity, PPV, NPV, and accuracy of the convolutional neural network (CNN)-CAD system to differentiate leiomyomas from schwannomas were 89.3%, 80.6%, 82.1%, 88.4%, and 85.0%, respectively
Summary
Mesenchymal tumors of the stomach are mostly incidentally observed during routine esophagogastroduodenoscopy examinations, especially as part of the national gastric cancer screening programs in Korea; they appear as hard, elevated subepithelial lesions [1]. Endoscopic ultrasonography (EUS) is a useful diagnostic modality for evaluating gastric mesenchymal tumors; differentiating gastrointestinal stromal tumors (GISTs) from benign mesenchymal tumors such as leiomyomas and schwannomas remains challenging. For this reason, we developed a convolutional neural network computer-aided diagnosis (CNN-CAD) system that can analyze gastric mesenchymal tumors on EUS images. In the further sequential analysis to differentiate leiomyoma from schwannoma in non-GIST tumors, the final diagnostic accuracy of the CNN-CAD system was 75.5%, which was significantly higher than that of two experienced and one junior endoscopists. It may complement the current clinical practices in the EUS diagnosis of gastric mesenchymal tumors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
