Background and Aims
Magnetically controlled capsule endoscopy (MCE) has become an efficient diagnostic
modality for gastric diseases. We developed a novel automatic gastric lesion detection
system to assist in diagnosis and reduce inter-physician variations. This study aimed
to evaluate the diagnostic capability of the computer-aided detection system for MCE
images.
Methods
We developed a novel automatic gastric lesion detection system based on a convolutional
neural network (CNN) and faster region-based convolutional neural network (RCNN).
A total of 1,023,955 MCE images from 797 patients were used to train and test the
system. These images were divided into 7 categories (erosion, polyp, ulcer, submucosal
tumor, xanthoma, normal mucosa, and invalid images). The primary endpoint was the
sensitivity of the system.
Results
The system detected gastric focal lesions with 96.2% sensitivity (95% confidence interval
[CI], 95.7%-96.5%), 76.2% specificity (95% CI, 75.97%-76.3%), 16.0% positive predictive
value (95% CI, 15.7%-16.3%), 99.7% negative predictive value (95% CI, 99.74%-99.79%),
and 77.1% accuracy (95% CI, 76.9%-77.3%) (sensitivity was 99.3% for erosions; 96.5%
for polyps; 89.3% for ulcers; 87.2% for submucosal tumors; 90.6% for xanthomas; 67.8%
for normal; and 96.1% for invalid images). Analysis of the receiver operating characteristic
curve showed that the area under the curve for all positive images was 0.84. Image
processing time was 44 milliseconds per image for the system and 0.38 ± 0.29 seconds
per image for clinicians (P < .001). The kappa value of 2 times repeated reads was 1.
Conclusions
The CNN faster-RCNN-based diagnostic program system showed good performance in diagnosing
gastric focal lesions in MCE images.
Abbreviations:
AI (artificial intelligence), AUC (area under curve), CAD (computer-aided diagnosis), CI (confidence intervals), CNN (convolutional neural networks), MCE (magnetically controlled capsule endoscopy), NPV (negative predictive value), PPV (positive predictive value), RCNN (region-based convolutional neural network)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Gastrointestinal EndoscopyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Feasibility and safety of magnetic-controlled capsule endoscopy system in examination of human stomach: a pilot study in healthy volunteers.J Interv Gastroenterol. 2012; 2: 155-160
- Accuracy of magnetically controlled capsule endoscopy, compared with conventional gastroscopy, in detection of gastric diseases.Clin Gastroenterol Hepatol. 2016; 14: 1266-1273.e1
- Screening for gastric cancer with magnetically controlled capsule gastroscopy in asymptomatic individuals.Gastrointest Endosc. 2018; 88: 466-474.e1
- Efficacy and effectiveness of colonoscopy: how do we bridge the gap.Gastrointest Endosc Clin N Am. 2010; 20: 673-684
- Deep learning.Nature. 2015; 521: 436-444
- A survey on deep learning in medical image analysis.Med Image Anal. 2017; 42: 60-88
- Polyp detection and radius measurement in small intestine using video capsule endoscopy.(7th International Conference on Biomedical Engineering and Informatics, Dalian)2014: 237-241
- Abnormal image detection in endoscopy videos using a filter bank and local binary patterns.Neurocomputing. 2014; 144: 70-91
- Automatic small bowel tumor diagnosis by using multi-scale wavelet-based analysis in wireless capsule endoscopy images.Biomed Eng Online. 2012; 11: 3
- Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning.IEEE Trans Med Imaging. 2016; 35: 1285-1298
- Detecting cancer metastases on gigapixel pathology images.arXiv. 2017; 1703: 02442v2
- Dermatologist-level classification of skin cancer with deep neural networks.Nature. 2017; 542: 115-118
- Gastroenterologist-level identification of small-bowel diseases and normal variants by capsule endoscopy using a deep-learning model.Gastroenterology. 2019; 157: 1044-1054.e5
- Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy.Gut. 2019; 68: 2161-2169
- Standardized examination procedure of magnetically controlled capsule endoscopy.VideoGIE. 2019; 4: 239-243
- Upper gastrointestinal endoscopy: can we cut the cord.Lancet Gastroenterol Hepatol. 2019; 4: 749-751
- Magnetic-controlled capsule endoscopy vs. gastroscopy for gastric diseases: a two-center self-controlled comparative trial.Endoscopy. 2015; 47: 525-528
- Application of convolutional neural networks in the diagnosis of helicobacter pylori infection based on endoscopic images.EBioMedicine. 2017; 25: 106-111
- Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images.Gastric Cancer. 2018; 21: 653-660
- Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy.Gastrointest Endosc. 2019; 89: 806-815.e1
- A lesion-based convolutional neural network improves endoscopic detection and depth prediction of early gastric cancer.J Clin Med. 2019; 8: 1310
- Deep-learning based detection of gastric precancerous conditions.Gut. 2020; 69: 4-6
- Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study.Lancet Oncol. 2019; 20: 1645-1654
- A smart capsule system for automated detection of intestinal bleeding using HSL color recognition.PLoS One. 2016; 11e0166488
- Exploring deep learning and transfer learning for colonic polyp classification.Comput Math Methods Med. 2016; 2016: 6584725
- Quantitative analysis of patients with celiac disease by video capsule endoscopy: a deep learning method.Comput Biol Med. 2017; 85: 1-6
- An automatic gastrointestinal polyp detection system in video endoscopy using fusion of color wavelet and convolutional neural network features.Int J Biomed Imaging. 2017; 2017: 9545920
- Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system.J Biomed Res. 2017; 31: 419-427
Article info
Publication history
Published online: May 26, 2020
Accepted:
May 1,
2020
Received:
February 9,
2020
Footnotes
If you would like to chat with an author of this article, you may contact Dr Liao at [email protected] or Dr Li at [email protected]
DISCLOSURE: All authors disclosed no financial relationships.
Identification
Copyright
© 2021 by the American Society for Gastrointestinal Endoscopy
