Seed Point Detection of Multiple Cancers Based on Empirical Domain Knowledge and K-means in Ultrasound Breast Image

Authors:
Lock-Jo Koo;Min-Suk Ko;Hee-Won Jo;Sang-Chul Park;Gi-Nam Wang
Affiliations:
Department of Industrial Engineering, Ajou University, Suwon, Kyunggido, Korea 442-749;Department of Industrial Engineering, Ajou University, Suwon, Kyunggido, Korea 442-749;Department of Industrial Engineering, Ajou University, Suwon, Kyunggido, Korea 442-749;Department of Industrial Engineering, Ajou University, Suwon, Kyunggido, Korea 442-749;Department of Industrial Engineering, Ajou University, Suwon, Kyunggido, Korea 442-749
Venue:
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Year:
2009

Citing 3
Cited 0

Scale-Space and Edge Detection Using Anisotropic Diffusion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Two-dimensional signal and image processing

Two-dimensional signal and image processing
Better breast cancer detection

IEEE Spectrum

Quantified Score

Hi-index	0.00

Visualization

Abstract

The objective of this paper is to remove noises of image based on the heuristic noises filter and to automatically detect seed points of tumor region by using K-MEANS in breast ultrasound. The proposed method is to use 4 different kinds of process. First process is the pixel value which indicates the light and shade of image is acquired as matrix type. Second process is an image preprocessing phase that is aimed to maximize a contrast of image and to prevent a leak of personal information. The next process is the heuristic noise filter which is based on the opinion of medical specialist and it is applied to remove noises. The last process is to detect a seed point automatically by applying K-MEANS algorithm. As a result, the noise is effectively eliminated in all images and an automated detection is possible by determining seed points on each tumor.