1. How to submit my research paper? What’s the process of publication of my paper?
The journal receives submitted manuscripts via email only. Please submit your research paper in .doc or .pdf format to the submission email: ijsps@ejournal.net.
2. Can I submit an abstract?
The journal publishes full research papers. So only full paper submission should be considered for possible publication...[Read More]

A Method for Automatic Extraction of Parotid Lesions in CT Images with Feature-Based Segmentation and Active Contour

Tung-Ying Wu 1, Sheng-Fuu Lin 1, Pa-Chun Wang 1, and Yong-Cheng Wang 2
1. National Chiao Tung University, Department of Electrical Engineering, Hsinchu, Taiwan (ROC). Industrial Technique Research Institute, Center of Measurement and Standard, Hsinchu, Taiwan (ROC).
2. Cathay General Hospital, Taipei, Taiwan (ROC)
Abstract—In this paper, we propose a method that can be used to automatically segment and delineate the suspected lesion regions of parotid glands for computer-aided diagnosis and treatment planning on clinical applications. Because the suspected lesions are unpredictable, it needs to be found by distinguishing the local features of soft tissues. The proposed method starts from image sub-band decomposition and the gathered coefficients are utilized to derived local feature descriptors. The pixels of soft tissue regions can de segmented based on the corresponding local features and the pathological regions can be localized. In order to improve the accuracy of segmentation, the active contour method is then involved based on the segmentation results as the initial conditions. The active contour method is more sensitive to the gradient variation such that the initial conditions based on prior segmentation can help converge to the weak boundaries between pathological tissues and normal tissues. In this paper, the effective method that can improve medical automation is described, and the results are compared with the contour directly found by clinical experts. As a result, the experiment of H&N CT images with parotid lesions shows that the accuracy can approach over 94%.

Index Terms—parotid, computer-aided diagnosis, computer tomography, active contour

Cite: Tung-Ying Wu, Sheng-Fuu Lin, Pa-Chun Wang, and Yong-Cheng Wang, "A Method for Automatic Extraction of Parotid Lesions in CT Images with Feature-Based Segmentation and Active Contour," International Journal of Signal Processing Systems, Vol. 1, No. 2, pp. 225-231, December 2013. doi: 10.12720/ijsps.1.2.225-231

Copyright © 2012-2015 International Journal of Signal Processing Systems, All Rights Reserved