DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Automatic detection of small bowel tumors in wireless capsule endoscopy images using ensemble learning

Journal Article · · Medical Physics
DOI: https://doi.org/10.1002/mp.13709 · OSTI ID:1573850
 [1];  [1];  [2];  [3];  [4];  [1]
  1. CMEMS‐UMinho Research Unit University of Minho Guimarães Portugal
  2. School of Health Polytechnic Institute of Castelo Branco Castelo Branco Portugal
  3. ALGORITMI Research Center University of Minho Campus of Gualtar 4710‐057 Braga Portugal
  4. Gastroenterology Department of the Hospital of Braga Braga Portugal, ICVS/3B’s Associate Laboratory University of Minho Braga Portugal

Purpose Wireless Capsule Endoscopy (WCE) is a minimally invasive diagnosis tool for lesion detection in the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the significant amount of acquired data leads to difficulties in the diagnosis by the physicians; which can be eased with computer assistance. This paper addresses a method for the automatic detection of tumors in WCE by using a two‐step based procedure: region of interest selection and classification. Methods The first step aims to separate abnormal from normal tissue by using automatic segmentation based on a Gaussian Mixture Model (GMM). A modified version of the Anderson method for convergence acceleration of the expectation–maximization (EM) algorithm is proposed. The proposed features for both segmentation and classification are based on the CIELab color space, as a way of bypassing lightness variations, where the L component is discarded. Tissue variability among subjects, light inhomogeneities and even intensity differences among different devices can be overcome by using simultaneously features from both regions. In the second step, an ensemble system with partition of the training data with a new training scheme is proposed. At this stage, the gating network is trained after the experts have been trained decoupling the joint maximization of both modules. The partition module is also used at the test step, leading the incoming data to the most likely expert allowing incremental adaptation by preserving data diversity. Results This algorithm outperforms others based on texture features selected from Wavelets and Curvelets transforms, classified by a regular support vector machine (SVM) in more than 5%. Conclusions This work shows that simpler features can outperform more elaborate ones if appropriately designed. In the current case, luminance was discarded to cope with saturated tissue, facilitating the color perception. Ensemble systems remain an open research field. In the current case, changes in both topology and training strategy have led to significant performance improvements. A system with this level of performance can be used in current clinical practice.

Sponsoring Organization:
USDOE
OSTI ID:
1573850
Journal Information:
Medical Physics, Journal Name: Medical Physics Journal Issue: 1 Vol. 47; ISSN 0094-2405
Publisher:
Wiley Blackwell (John Wiley & Sons)Copyright Statement
Country of Publication:
United States
Language:
English

References (21)

Convergence results for the EM approach to mixtures of experts architectures journal January 1995
CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames journal February 2003
Texture and color based image segmentation and pathology detection in capsule endoscopy videos journal January 2014
Detection of small bowel tumor based on multi-scale curvelet analysis and fractal technology in capsule endoscopy journal March 2016
A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler journal June 2013
The usage of soft-computing methodologies in interpreting capsule endoscopy journal June 2007
Achieving total enteroscopy with capsule endoscopy in all patients: are we stretching the limits of technology? journal January 2009
Small bowel malignancy journal January 2004
A model of deformable rings for interpretation of wireless capsule endoscopic videos journal April 2009
Ensemble of online sequential extreme learning machine journal August 2009
Wireless capsule endoscopy journal May 2000
Total enteroscopy with a nonsurgical steerable double-balloon method journal February 2001
Efficient implementation of GLCM based texture feature computation using CUDA platform
  • Parvez, Asad; Phadke, Anuradha C.
  • 2017 International Conference on Trends in Electronics and Informatics (ICOEI), 2017 International Conference on Trends in Electronics and Informatics (ICEI) https://doi.org/10.1109/ICOEI.2017.8300935
conference May 2017
An efficient implementation of GLCM algorithm in FPGA conference December 2018
Computer-aided tumor detection in endoscopic video using color wavelet features journal September 2003
Skin Color Measurements in Terms of CIELAB Color Space Values journal October 1992
Anderson Acceleration for Fixed-Point Iterations journal January 2011
Automatic small bowel tumor diagnosis by using multi-scale wavelet-based analysis in wireless capsule endoscopy images journal January 2012
Small bowel capsule endoscopy: Where are we after almost 15 years of use? journal January 2015
The Usefulness of Capsule Endoscopy for Small Bowel Tumors journal January 2016
Detection of small bowel tumor in wireless capsule endoscopy images using an adaptive neuro-fuzzy inference system journal January 2017