Title: Edge detection and feature extraction of gastrointestinal radiographs using adaptive differential filter and level set method

Authors: Nobumichi Nagano; Takami Matsuo

Addresses: Department of Architecture and Mechatronics, Oita University, 700 Dannonaru, Oita, Japan. ' Department of Architecture and Mechatronics, Oita University, 700 Dannonaru, Oita, Japan

Abstract: To improve the detectability of the gastric lesions in the X-ray examinations, the computer image processing methods of radiographs of gastric cancer lesions are discussed. We propose an adaptive differential filter to the edge detection. Moreover, the level set method is adopted to the segmentation. To verify the effectiveness of the proposed method, the numerical examples are carried out, using the case radiograph of the gastric intestines medical picture database produced by National Kyushu Cancer Center. The numerical results show that the number of iterations in the level set method can be reduced using the binary image obtained by the adaptive differential filter.

Keywords: adaptive differential filters; computer-aided diagnosis; edge detection; segmentation; feature extraction; gastrointestinal radiographs; radiography; medical imaging; gastric lesions; X-rays; image processing; gastric cancer; cancer lesions; level set method.

DOI: 10.1504/IJAMECHS.2011.043376

International Journal of Advanced Mechatronic Systems, 2011 Vol.3 No.4, pp.279 - 287

Published online: 18 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article