On Using Image Processing Techniques for Evaluation of Mammography Acquisition Errors

• Maira B. H. Moran UFF
• Aura Conci UFF
• Salete de J.F. Rêgo UFF
• Cristina A. P. Fontes UFF
• Marcelo D. Brito Faria UERJ
• Luciana Freitas Bastos UERJ
• Gilson A. Giraldi LNCC

DOI: https://doi.org/10.5753/sbcas.2019.6271

Abstract

Mammography is an extremely important examination considering the high incidence of breast-related diseases, since it helps to detect several abnormalities. Errors in the acquisition can mask potential problems. The objective of this study is to apply image processing techniques for automated detection of some very common errors. Craniocaudal (CC) and mediolateral oblique (MLO) mammograms views were evaluated considering aspects as: (1) breast symmetric positioning, (2) adequate nipples profiling and centering, and (3) properly pectoral muscle location. The image processing techniques used are based on: skeletonization, Hough transform and thresholding. The achieved results are impressive especially in the determination of the nipple position.

References

Bassett, L., Hirbawi, I., DeBruhl, N., and Hayes, M. (1993). Mammographic positioning: evaluation from the view box. Radiology, 188(3):803–806. http://dx.doi.org/10.1148/radiology.188.3.8351351

INCA (2018). Mammograms for radiologists.

Li, Y., Poulos, A., McLean, D., and Rickard, M. (2010). A review of methods of clinical image quality evaluation in mammography. European journal of Radiology, 74(3):e122–e131. http://dx.doi.org/10.1016/j.ejrad.2009.04.069
March, M. et al. (2013). Making the diagnosis: A practical guide to breast imaging.

Méndez, A. J., Tahoces, P. G., Lado, M. J., Souto, M., Correa, J., and Vidal, J. J. (1996). Automatic detection of breast border and nipple in digital mammograms. Computer methods and programs in biomedicine, 49(3):253–262. http://dx.doi.org/10.1016/0169-2607(96)01724-5

Popli, M. B., Teotia, R., Narang, M., and Krishna, H. (2014). Breast positioning during mammography: mistakes to be avoided. Breast Cancer: Basic and Clinical Research, 8:BCBCR–S17617. http://dx.doi.org/10.4137/BCBCR.S17617

Silva, L., Saade, D., Sequeiros, G., Silva, A., Paiva, A., Bravo, R., and Conci, A. (2014). A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, 4(1):92–100. http://dx.doi.org/10.1166/jmihi.2014.1226

Sonka, M., Hlavac, V., and Boyle, R. (2014). Image processing, analysis, and machine vision. Cengage Learning.