↓ Skip to main content

Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks

Overview of attention for article published in Abdominal Radiology, August 2017
Altmetric Badge

Mentioned by

twitter
2 tweeters
facebook
1 Facebook page

Citations

dimensions_citation
8 Dimensions

Readers on

mendeley
21 Mendeley
Title
Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks
Published in
Abdominal Radiology, August 2017
DOI 10.1007/s00261-017-1294-1
Pubmed ID
Authors

Phillip M. Cheng, Tapas K. Tejura, Khoa N. Tran, Gilbert Whang

Abstract

The purpose of this pilot study is to determine whether a deep convolutional neural network can be trained with limited image data to detect high-grade small bowel obstruction patterns on supine abdominal radiographs. Grayscale images from 3663 clinical supine abdominal radiographs were categorized into obstructive and non-obstructive categories independently by three abdominal radiologists, and the majority classification was used as ground truth; 74 images were found to be consistent with small bowel obstruction. Images were rescaled and randomized, with 2210 images constituting the training set (39 with small bowel obstruction) and 1453 images constituting the test set (35 with small bowel obstruction). Weight parameters for the final classification layer of the Inception v3 convolutional neural network, previously trained on the 2014 Large Scale Visual Recognition Challenge dataset, were retrained on the training set. After training, the neural network achieved an AUC of 0.84 on the test set (95% CI 0.78-0.89). At the maximum Youden index (sensitivity + specificity-1), the sensitivity of the system for small bowel obstruction is 83.8%, with a specificity of 68.1%. The results demonstrate that transfer learning with convolutional neural networks, even with limited training data, may be used to train a detector for high-grade small bowel obstruction gas patterns on supine radiographs.

Twitter Demographics

The data shown below were collected from the profiles of 2 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 21 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 21 100%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 9 43%
Researcher 5 24%
Unspecified 3 14%
Student > Master 2 10%
Professor > Associate Professor 1 5%
Other 1 5%
Readers by discipline Count As %
Medicine and Dentistry 12 57%
Unspecified 3 14%
Computer Science 3 14%
Veterinary Science and Veterinary Medicine 1 5%
Neuroscience 1 5%
Other 1 5%