Celiac Disease Detection From Videocapsule Endoscopy Images Using Strip Principal Component Analysis

The purpose of this study was to implement principal component analysis (PCA) on videocapsule endoscopy (VE) images to develop a new computerized tool for celiac disease recognition. Three PCA algorithms were implemented for feature extraction and sparse representation. A novel strip PCA (SPCA) with nongreedy L1-norm maximization is proposed for VE image analysis. The extracted principal components were interpreted by a non-parametric k-nearest neighbor (k-NN) method for automated celiac disease classification. A benchmark dataset of 460 images (240 from celiac disease patients with small intestinal villous atrophy versus 220 control patients lacking villous atrophy) was constructed from the clinical VE series. It was found that the newly developed SPCA with nongreedy L1-norm maximization was most efficient for computerized celiac disease recognition, having a robust performance with an average recognition accuracy of 93.9 percent. Furthermore, SPCA also has a reduced computation time as compared with other methods. Therefore, it is likely that SPCA will be a helpful adjunct for the diagnosis of celiac disease.

Automated summary

This study implemented principal component analysis (PCA) on videocapsule endoscopy (VE) images to develop a new computerized tool for celiac disease recognition. The novel strip PCA (SPCA) with nongreedy L1-norm maximization was found to be the most efficient method for computerized celiac disease recognition, with an average recognition accuracy of 93.9 percent. Additionally, SPCA also reduced computation time compared to other methods, showing potential as a helpful adjunct for celiac disease diagnosis.