Segmentation of Pectoral Muscle in Mammogram Images Using Gaussian Mixture Model-Expectation Maximization

Segmentation of Pectoral Muscle in Mammogram Images Using Gaussian Mixture Model-Expectation Maximization

Ichrak Khoulqi (Faculty of Sciences and Technics, Sultan Moulay Slimane University, Morocco), Najlae Idrissi (Faculty of Sciences and Technics, Sultan Moulay Slimane University, Morocco) and Muhammad Sarfraz (Kuwait University, Kuwait)
DOI: 10.4018/978-1-7998-4444-0.ch009
OnDemand PDF Download:
No Current Special Offers


Breast cancer is one of the significant issues in medical sciences today. Specifically, women are suffering most worldwide. Early diagnosis can result to control the growth of the tumor. However, there is a need of high precision of diagnosis for right treatment. This chapter contributes toward an achievement of a computer-aided diagnosis (CAD) system. It deals with mammographic images and enhances their quality. Then, the enhanced images are segmented for pectoral muscle (PM) in the Medio-Lateral-Oblique (MLO) view of the mammographic images. The segmentation approach uses the tool of Gaussian Mixture Model-Expectation Maximization (GMM-EM). A standard database of Mini-MIAS with 322 images has been utilized for the implementation and experimentation of the proposed technique. The metrics of structural similarity measure and DICE coefficient have been utilized to verify the quality of segmentation based on the ground truth. The proposed technique is quite robust and accurate, it supersedes various existing techniques when compared in the same context.
Chapter Preview


In the context of pectoral muscle (PM) segmentation from breast tissues, several studies have been carried out in the literature. For the automatic segmentation of the PM, Guo, et al (2020) proposed a study which is based on boundary identification and shape prediction. Their work identifies the PM region in MLO view mammograms.

The authors in (Khoulqi & Idrissi, 2019; 2020) believe that computer-aided diagnosis (CAD) systems are beneficial for breast cancer detection as it improves the diagnosis accuracy. They have presented some contribution towards the development of a breast CAD system. This work is based on split and merge methodology. Their algorithm used a technique of voting.

Mammography can be utilized for measuring breast density (BD) which is helpful to diagnose breast cancer. For very commonly clinical routines, the radiologists evaluate images using Breast Imaging Reporting and Data System (BIRADS) (Wikipedia, March 29, 2020) assessment. Since this method has human intervention and hence has some kind of variability. Therefore, to relieve the burden of medical experts like radiologists and to have a first aid opinion, there is a need to find out some robust and automated approach to measure BD and hence to extract PM which is a challenging task.

Complete Chapter List

Search this Book: