Next Article in Journal
Come in from the Cold: Are Older Adults Who Live in Colder Climates at Greater Risk for Sarcopenia?
Next Article in Special Issue
Distinctive Pathophysiology Underlying Constipation in Parkinson’s Disease: Implications for Cognitive Inefficiency
Previous Article in Journal
Reliability of Synthetic Brain MRI for Assessment of Ischemic Stroke with Phantom Validation of a Relaxation Time Determination Method
Previous Article in Special Issue
Frontiers of Robotic Colonoscopy: A Comprehensive Review of Robotic Colonoscopes and Technologies
Article

Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning

by 1,2,3,4,*,†, 4,5,6,7,*,†, 4,8, 1 and 3
1
Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang 14068, Korea
2
Department of Ophthalmology, Hallym University Sacred Heart Hospital, Anyang 14068, Korea
3
Division of Biomedical Informatics, Seoul National University Biomedical Informatics (SNUBI), Seoul National University College of Medicine, Seoul 03080, Korea
4
Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon 24253, Korea
5
Department of Internal Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea
6
Institute for Liver and Digestive Diseases, Hallym University, Chuncheon 24253, Korea
7
Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon 24253, Korea
8
Department of Anesthesiology and Pain Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea
*
Authors to whom correspondence should be addressed.
These authors equally contributed as a first and corresponding author to this work.
J. Clin. Med. 2020, 9(6), 1858; https://doi.org/10.3390/jcm9061858
Received: 5 May 2020 / Revised: 31 May 2020 / Accepted: 9 June 2020 / Published: 15 June 2020
Endoscopic resection is recommended for gastric neoplasms confined to mucosa or superficial submucosa. The determination of invasion depth is based on gross morphology assessed in endoscopic images, or on endoscopic ultrasound. These methods have limited accuracy and pose an inter-observer variability. Several studies developed deep-learning (DL) algorithms classifying invasion depth of gastric cancers. Nevertheless, these algorithms are intended to be used after definite diagnosis of gastric cancers, which is not always feasible in various gastric neoplasms. This study aimed to establish a DL algorithm for accurately predicting submucosal invasion in endoscopic images of gastric neoplasms. Pre-trained convolutional neural network models were fine-tuned with 2899 white-light endoscopic images. The prediction models were subsequently validated with an external dataset of 206 images. In the internal test, the mean area under the curve discriminating submucosal invasion was 0.887 (95% confidence interval: 0.849–0.924) by DenseNet−161 network. In the external test, the mean area under the curve reached 0.887 (0.863–0.910). Clinical simulation showed that 6.7% of patients who underwent gastrectomy in the external test were accurately qualified by the established algorithm for potential endoscopic resection, avoiding unnecessary operation. The established DL algorithm proves useful for the prediction of submucosal invasion in endoscopic images of gastric neoplasms. View Full-Text
Keywords: artificial intelligence; convolutional neural networks; endoscopy; gastric neoplasms artificial intelligence; convolutional neural networks; endoscopy; gastric neoplasms
Show Figures

Figure 1

MDPI and ACS Style

Cho, B.-J.; Bang, C.S.; Lee, J.J.; Seo, C.W.; Kim, J.H. Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning. J. Clin. Med. 2020, 9, 1858. https://doi.org/10.3390/jcm9061858

AMA Style

Cho B-J, Bang CS, Lee JJ, Seo CW, Kim JH. Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning. Journal of Clinical Medicine. 2020; 9(6):1858. https://doi.org/10.3390/jcm9061858

Chicago/Turabian Style

Cho, Bum-Joo; Bang, Chang S.; Lee, Jae J.; Seo, Chang W.; Kim, Ju H. 2020. "Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning" J. Clin. Med. 9, no. 6: 1858. https://doi.org/10.3390/jcm9061858

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop