Computed Automatic 3D Segmentation Methods in Computed Tomography Laser Mammography

A., JALALIAN and A.R., RAMLI and B., KARASFI and M. I., SARIPAN and N., BAHRI and R., MAHMUD and S. A/P., SUPPIAH and S., MASHOHOR (2015) Computed Automatic 3D Segmentation Methods in Computed Tomography Laser Mammography. In: Third International Conference on Advances in Computing, Electronics and Communication - ACEC 2015, 10-11 October, 2015, Zurich, Switzerland.

20151023_093556.pdf - Published Version

Download (555kB) | Preview
Official URL:


The use of computer assisted diagnosis systems (CADs) has been recognized to improve sensitivity and specificity of diagnostic in radiology research. Accurate segmentation of clinical imaging is a critical step in the CAD systems which affect the efficiency of subsequence stages such as feature extraction and classification. In this paper we propose a 3-dimensional (3D) segmentation method to extract volume of interests (VOIs) in computed tomography laser mammography (CTLM). Three automatic segmentation techniques consist of Color quantization (CQ), K-Mean (Kmean) and Fuzzy C-Means (FCM) clustering have been implemented as a proposed method in a 3D structure. The evaluations were performed by comparison of segmented images and ground truth. The ground truth are extracted using windows/level technique on the original CTLM images. The Jaccard and Dice coefficients in addition volumetric overlap error are employed to quantify the accuracy of segmentation methods. According to the outcomes, the 3D Fuzzy C-Means clustering presents reasonable results compared to other methods.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Computed Tomography Laser Mammography; Computer Aided Diagnosis; Segmentation; Breast Cancer
Depositing User: Mr. John Steve
Date Deposited: 20 Apr 2019 11:36
Last Modified: 20 Apr 2019 11:36

Actions (login required)

View Item View Item