Features for Discriminating Normal Cases in Mass Screening for Gastric Cancer with Double Contrast X-ray Images of Stomach
DOI:
https://doi.org/10.14738/jbemi.16.781Keywords:
Computer-aided Diagnosis, Gastric Cancer, Double Contrast X-ray Image of Stomach, Medical Image ProcessingAbstract
In a mass screening for gastric cancer, diagnosticians read many stomach X-ray pictures at a time. To decrease the number of reading the pictures in the mass screening, the proposed method discriminates normal cases in stomach X-ray images using the proposed features. In the normal cases, folds on the stomach wall appear in parallel in the images. Considering this characteristic, the proposed method measures parallelism of the folds in the images. Experimental results of the discriminations for 88 images where 13 abnormal cases are included have shown that the proposed features are well effective for recognizing normal cases.References
. Y. Kita (1996), 'Elastic-model driven analysis of several views of a deformable cylindrical object', IEEE Trans. Pattern Anal. Mach. Intel., 18(12), 1150-1162.
. Y. Mekada, J. Hasegawa, J. Toriwaki, S. Nawano, and K. Miyagawa (1998), 'Automated extraction of cancer lesions from double contrast X-ray images of stomach', Proc. 1st International Workshop on Computer Aided Diagnosis, 407-412.
. J. Hasegawa, T. Tsutsui, and J. Toriwaki (1991), 'Automated Extraction of Cancer Lesions with Convergent Fold Patterns in Double Contrast X-ray Images of the Stomach', Systems and Computers in Japan, 22(7), 51-62.
. J. Hasegawa and J. Toriwaki (1992), 'A new filter for feature extraction of line pattern texture with application to cancer detection', Proc. 11th IAPR Int. Conf. on Pattern Recognition, 352-355.
. Y. Yoshinaga, H. Kobatake, and S. Fukushima (1999), 'The detection and feature extraction method of curvilinear convex regions with weak contrast using a gradient distribution method', Proc. IEEE ICIP 99, 715-719.
. K. Abe, T. Nobuoka, and M. Minami (2011), 'Computer-Aided Diagnosis of Mass Screenings for Gastric Cancer Using Double Contrast X-ray Images', Proc. IEEE Pacific Rim Conf. on Communications, Computers and Signal Processing, 708-713.
. M. Kass, A. Witkin, and D. Terzopoulos (1988), 'Snakes: Active contour models', Int. J. Computer Vision, 1(3), 321-331.
. S. Fukushima, H. Uwai, and K. Yoshimoto (2000), 'Optimization-Based Recognition the Gastric Region from a Double-Contrast Radiogram', IEICE Trans. (Japanese Edition), J83-D-II(1), 154-164.
. R. A. Schowengerdt (1983), 'Techniques for Image Processing and Classfication in Remote Sensing', ACADEMIC PRESS, 72-83.
. M. J. Canty (2014), 'Image Analysis, Classification and Change Detection in Remote Sensing', CRC Press, 329-332.
. Y. Yoshinaga and H. Kobatake (2000), 'The line detection method with robustness against contrast and width variation applied in gradient vector field', Systems and Computers in Japan, 31(3), 49-58.
. M. Stone (1974), 'Cross-Validatory Choice and Assessment of Statistical Predictions', J. of the Royal Statistical Society, Series B (Methodological), 36(2), 111-147.
. NV. Chawla, KW. Bowyer, LO. Hall, and WP. Kegelmeyear (2002), 'SMOTE: Synthetic Minority Over-sampling Technique', J. of Artificial Intelligence Research 16, 321-357.
