A robust method for segmenting pectoral muscle in mediolateral oblique (MLO) mammograms
Accurately detecting and removing pectoral muscle areas depicting on mediolateral oblique (MLO) view mammograms are an important step to develop a computer-aided detection scheme to assess global mammographic density or tissue patterns. This study aims to develop and test a new fully automated, accurate and robust method for segmenting pectoral muscle in MLO mammograms.
The new method includes the following steps. First, a small rectangular region in the top-left corner of the MLO mammogram which may contain pectoral muscle is captured and enhanced by the fractional differential method. Next, an improved iterative threshold method is applied to segment a rough binary boundary of the pectoral muscle in the small region. Then, a rough contour is fitted with the least squares method on the basis of points of the rough boundary. Last, the fitting contour is subjected to local active contour evolution to obtain the final pectoral muscle segmentation line. The method has been tested on 720 MLO mammograms.
The segmentation results generated using the new scheme were evaluated by two expert mammographic radiologists using a 5-scale rating system. More than 65% were rated above scale 3. When assessing the segmentation results generated using Hough transform, morphologic thresholding methods and Unet-based model, less than 20%, 35% and 47% of segmentation results were rated above scale 3 by two radiologists, respectively. Quantitative data analysis results show that the Dice coefficient of 0.986 ± 0.005 is obtained. In addition, the mean rate of errors and Hausdorff distance between the contours detected by automated and manual segmentation are FP = 1.71 ± 3.82%, FN = 5.20 ± 3.94% and 2.75 ± 1.39 mm separately.
The proposed method can be used to segment the pectoral muscle in MLO mammograms with higher accuracy and robustness.
KeywordsComputer-aided diagnosis Pectoral muscle Automated segmentation Mediolateral oblique mammograms
This work was supported by the National Institutes of Health [Grant Numbers R01 CA160205, CA197150].
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animal performed by any of the authors.
- 4.Bandyopadhyay SK, IndraKantaMaitra (2015) Fully automated computer aided diagnosis (CAD) system of human breast cancer using digital mammogramGoogle Scholar
- 5.Vaidehi K, Subashini TS (2015) Automatic classification of CC view and MLO view in digital mammograms. In: Kamalakannan C, Suresh L, Dash S, Panigrahi B (eds) Power electronics and renewable energy systems, vol 326. Springer, New DelhiGoogle Scholar
- 10.Georgsson F (2001) Algorithms and techniques for computer aided mammo-graphic screening. Daily MailGoogle Scholar
- 14.Rodriguez-Ruiz A, Teuwen J, Chung K, Karssemeijer N, Chevalier M, Gubern-Mérida A (2018) Pectoral muscle segmentation in breast tomosynthesis with deep learning. In: Computer-aided diagnosisGoogle Scholar
- 15.Chen D, Chen YQ, Xue D, Pan F (2012) Adaptive image enhancement based on fractional differential mask. In: CCDC, vol 229, pp 1043–1047Google Scholar
- 17.Wuthrich M, Trimpe S, Kappler D, Schaal S (2015) A new perspective and extension of the Gaussian filter. Comput Sci 35(14)Google Scholar
- 18.Anh VV, Mcvinish R (2003) Fractional differential equations driven by Lévy noise. Int J Stoch Anal 16(2):97–119Google Scholar
- 19.Yi-Fei PU (2007) Application of fractional differential approach to digital image processing. J Sichuan Univ 39(3):124–132Google Scholar
- 24.Variable, R. (2013). Heaviside step function. BelowGoogle Scholar
- 27.Yezzi A, Tsai A, Willsky A (2002) A fully global approach to image segmentation via coupled curve evolution equations. Academic Press Inc., New YorkGoogle Scholar
- 31.Och FJ, Ney H (2003) A systematic comparison of various statistical alignment models. MIT Press, CambridgeGoogle Scholar