Automatic detection of small bowel tumors in wireless capsule endoscopy images using ensemble learning
- CMEMS‐UMinho Research Unit University of Minho Guimarães Portugal
- School of Health Polytechnic Institute of Castelo Branco Castelo Branco Portugal
- ALGORITMI Research Center University of Minho Campus of Gualtar 4710‐057 Braga Portugal
- 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
Similar Records
Feature‐shared adaptive‐boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images
Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem