Background and Aims
EUS is considered one of the most sensitive modalities for pancreatic cancer detection,
but it is highly operator-dependent and the learning curve is steep. In this study,
we constructed a system named BP MASTER (pancreaticobiliary master) for EUS training
and quality control.
Methods
The standard procedure of pancreatic EUS was divided into 6 stations. We developed
a station classification model and a pancreas/abdominal aorta/portal confluence segmentation
model with 19,486 images and 2207 images, respectively. Then, we used 1920 images
and 700 images for classification and segmentation internal validation, respectively.
To test station recognition we used 396 videos clips. An independent data set containing
180 images was applied for comparing the performance between models and EUS experts.
Seven hundred sixty-eight images from 2 other hospitals were used for external validation.
A crossover study was conducted to test the system effect on reducing difficulty in
ultrasonographics interpretation among trainees.
Results
The models achieved 94.2% accuracy in station classification and .836 dice in segmentation
at internal validation. At external validation, the models achieved 82.4% accuracy
in station classification and .715 dice in segmentation. For the video test, the station
classification model achieved a per-frame accuracy of 86.2%. Compared with EUS experts,
the models achieved 90.0% accuracy in classification and .77 and .813 dice in blood
vessel and pancreas segmentation, which is comparable with that of experts. In the
crossover study, trainee station recognition accuracy improved from 67.2% to 78.4%
(95% confidence interval, .058-1.663; P < .01).
Conclusions
The BP MASTER system has the potential to play an important role in shortening the
pancreatic EUS learning curve and improving EUS quality control in the future.
Graphical abstract
Graphical Abstract
Abbreviations:
BP MASTER (pancreaticobiliary master), DCNN (deep convolutional neural network), GPU (graphics processing unit), IoU (intersection over union)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
- Screening for pancreatic cancer: updated evidence report and systematic review for the US Preventive Services Task Force.JAMA. 2019; 322: 445-454
- Management of patients with increased risk for familial pancreatic cancer: updated recommendations from the International Cancer of the Pancreas Screening (CAPS) Consortium.Gut. 2020; 69: 7-17
- Frequent detection of pancreatic lesions in asymptomatic high-risk individuals.Gastroenterology. 2012; 142: 796-804
- A multicentre comparative prospective blinded analysis of EUS and MRI for screening of pancreatic cancer in high-risk individuals.Gut. 2016; 65: 1505-1513
- Training in EUS and ERCP: standardizing methods to assess competence.Gastrointest Endosc. 2018; 87: 1371-1382
- Standard imaging techniques of endoscopic ultrasound-guided fine-needle aspiration using a curved linear array echoendoscope.Dig Endosc. 2007; 19: S180-S205
- Curved linear array EUS technique in the pancreas and biliary tree: focusing on the stations.Gastrointest Endosc. 2009; 69: S84-S89
- Training in endoscopy: endoscopic ultrasound.Clin Endosc. 2017; 50: 340-344
- Deep learning in neural networks: an overview.Neural Netw. 2015; 61: 85-117
- Randomised controlled trial of WISENSE, a real-time quality improving system for monitoring blind spots during esophagogastroduodenoscopy.Gut. 2019; 68: 2161-2169
- Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study.Lancet Gastroenterol Hepatol. Epub 2020 Jan 22;
- Quantitative contrast-enhanced harmonic EUS in differential diagnosis of focal pancreatic masses (with videos).Gastrointest Endosc. 2015; 82: 59-69
- Usefulness of deep learning analysis for the diagnosis of malignancy in intraductal papillary mucinous neoplasms of the pancreas.Clin Translat Gastroenterol. 2019; 10: 1-8
- How I do a diagnostic EUS.Endoscopy. 2019; 51: 973-975
- How to perform EUS in the pancreaticobiliary area.Min Med. 2014; 105: 371-389
- Normal linear echoanatomy.Techn Gastrointest Endosc. 2000; 3: 124-135
- Transfer learning for visual categorization: a survey.IEEE Trans Neural Netw Learn Syst. 2014; 26: 1019-1034
Abadi M, Barham P, Chen J, et al. Tensorflow: a system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16). Available at: https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf. Accessed July 13, 2020.
- The dropout learning algorithm.Artific Intell. 2014; 210: 78-122
- Automatic early stopping using cross validation: quantifying the criteria.Neural Netw. 1998; 11: 761-767
- Classification and regression by random forest.R News. 2002; 2: 18-22
- A prospective multicenter study evaluating learning curves and competence in endoscopic ultrasound and endoscopic retrograde cholangiopancreatography among advanced endoscopy trainees: the Rapid Assessment of Trainee Endoscopy Skills study.Clin Gastroenterol Hepatol. 2017; 15: 1758
- Competence in endoscopic ultrasound and endoscopic retrograde cholangiopancreatography, from training through independent practice.Gastroenterology. 2018; 155: 1483-1494
- Training in endoscopic ultrasonography: an Asian perspective.Digestive Endoscopy. 2017; 29: 512-516
- Variation in aptitude of trainees in endoscopic ultrasonography, based on cumulative sum analysis.Clin Gastroenterol Hepatol. 2015; 13: 1318-1325
- Setting minimum standards for training in EUS and ERCP: results from a prospective multicenter study evaluating learning curves and competence among advanced endoscopy trainees.Gastrointest Endosc. 2019; 89: 1160-1168.e9
Article info
Publication history
Published online: May 06, 2020
Accepted:
April 18,
2020
Received:
March 10,
2020
Footnotes
DISCLOSURE: The following author disclosed financial relationships: S. Hu: Research staff member of Wuhan EndoAngel Medical Technology Company. All other authors disclosed no financial relationships. Research support for this study was provided in part by the Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision (grant no. 2018BCC337) and the Hubei Province Major Science and Technology Innovation Project (grant no. 2018-916-000-008).
Identification
Copyright
© 2020 by the American Society for Gastrointestinal Endoscopy
ScienceDirect
Access this article on ScienceDirectLinked Article
- ErratumGastrointestinal EndoscopyVol. 93Issue 3
- PreviewIn the article, “Deep learning–based pancreas segmentation and station recognition system in EUS: development and validation of a useful training tool (with video),” which was published in the October 2020 issue (Gastrointest Endosc 2020;92:874-85), the following authors contributed equally to the article:
- Full-Text
- Preview
