Computer-Aided Identification of the Pectoral Muscle in Digitized Mammograms

Abstract

Mammograms are X-ray images of human breast which are normally used to detect breast cancer. The presence of pectoral muscle in mammograms may disturb the detection of breast cancer as the pectoral muscle and mammographic parenchyma appear similar. So, the suppression or exclusion of the pectoral muscle from the mammograms is demanded for computer-aided analysis which requires the identification of the pectoral muscle. The main objective of this study is to propose an automated method to efficiently identify the pectoral muscle in medio-lateral oblique-view mammograms. This method uses a proposed graph cut-based image segmentation technique for identifying the pectoral muscle edge. The identified pectoral muscle edge is found to be ragged. Hence, the pectoral muscle is smoothly represented using Bezier curve which uses the control points obtained from the pectoral muscle edge. The proposed work was tested on a public dataset of medio-lateral oblique-view mammograms obtained from mammographic image analysis society database, and its performance was compared with the state-of-the-art methods reported in the literature. The mean false positive and false negative rates of the proposed method over randomly chosen 84 mammograms were calculated, respectively, as 0.64% and 5.58%. Also, with respect to the number of results with small error, the proposed method out performs existing methods. These results indicate that the proposed method can be used to accurately identify the pectoral muscle on medio-lateral oblique view mammograms.

Appendix

The merge criterion can be expanded as two conditions as

$${\text{IRM}}{\left( {R_{1} ,R_{{\text{2}}} } \right)} \leqslant {\text{IRA}}{\left( {R_{1} } \right)} + \frac{{2 \times N_{R} }}{{{\left| {R_{{\text{1}}} } \right|}}}$$

(16a)

$${\text{IRM}}{\left( {R_{{\text{1}}} {\text{,}}R_{{\text{2}}} } \right)} \leqslant {\text{IRA}}{\left( {R_{2} } \right)} + \frac{{2 \times N_{R} }}{{{\left| {R_{{\text{2}}} } \right|}}}$$

(16b)

$${\text{IRM}}{\left( {R_{1} ,R_{{\text{2}}} } \right)} \times {\left| {R_{{\text{1}}} } \right|} \leqslant {\text{IRA}}{\left( {R_{{\text{1}}} } \right)} \times {\left| {R_{{\text{1}}} } \right|} + 2 \times N_{r} $$

(17a)

$${\text{IRM}}{\left( {R_{1} ,R_{2} } \right)} \times {\left| {R_{{\text{2}}} } \right|} \leqslant {\text{IRA}}{\left( {R_{2} } \right)} \times {\left| {R_{{\text{2}}} } \right|} + 2 \times N_{R} $$

(17b)

Let $K = 2 \times N_{R}$. Now, Eqs. 17a and 17b can be written as

$${\left( {{\text{IRM}}{\left( {R_{1} ,R_{2} } \right)} - {\text{IRA}}{\left( {R_{1} } \right)}} \right)} \times {\left| {R_{1} } \right|} \leqslant K$$

(18a)

$${\left( {{\text{IRM}}{\left( {R_{1} ,R_{2} } \right)} - {\text{IRA}}{\left( {R_{2} } \right)}} \right)} \times {\left| {R_{2} } \right|} \leqslant K$$

(18b)

For the merge criterion to be true, any one of these conditions in Eqs. 18a and 18b must be satisfied. If the two regions, R ₁ and R ₂, are homogeneous, then the non-homogeneity measures ${\text{IRM}}{\left( {R_{1} ,\,R_{2} } \right)} - {\text{IRA}}{\left( {R_{i} } \right)},\,i \in {\left\{ {1,2} \right\}}$ become small; hence, any one of these conditions is more likely to be satisfied. However, if the regions are not homogeneous, then the non-homogeneity measure values become high and also, the values are further enhanced by the multiplicative factor, the size of the region; hence, both these conditions are not satisfied.