Computer Aided Diagnosis in Mammography Microcalcification Analysis

Nadin Jamal Abualroos, Norlaili Ahmad Kabir


Objectives: The project aims to resolve missed or overlooked breast cancer lesions particularly due to dense breast structure. Dense breast makes microcalcifications difficult to be detected as both normal breast tissue and microcalcification appear white on mammograms. The carry out the project, a breast phantom was fabricated, and ImageJ software was used to improve the visibility of microcalcification.

Methods: The phantom was fabricated, and the physical properties showed similarity to that of breast tissues. Calcium-Carbonate powder simulated microcalcifications. Images were acquired using CR mammography. The images acquired were post processed by ImageJ software through applying thresholding technique to help detection of subtle microcalcifications.

Results: Microcalcifications appearance enhanced by threshold technique. The resultant images showed increasing in the contrast value at ROI from 3.9, 2.2, and 4.2 to 7.2, 6.8, and 7.6 respectively.

Conclusion: The differences in contrast values were more consequential in areas of low Calcium Carbonate concentration after applying threshold technique.


Microcalcification – Mammography – Computer Aided Diagnosis – ImageJ software – breast cancer

Full Text:



Quintanilla-dominguez J, Ojeda-magaña B, Cortina-januchs MG, Ruelas R. Sharif University of Technology Image segmentation by fuzzy and possibilistic clustering algorithms for the identification of microcalcifications. Sci Iran. 2011;18(3):580-589. doi:10.1016/j.scient.2011.04.009.

Shen L, Rangayyan RM, Desautels JEL. Application of Shape-Analysis to Mammographic Calcifications. IEEE Trans Med Imaging. 1994;13(2):263-274.

Wei L, Yang Y, Nishikawa RM, Jiang Y. A study on several machine-learning methods for classification of malignant and benign clustered microcalcifications. IEEE Trans Med Imaging. 2005;24(2):371-380. doi:10.1109/TMI.2004.842457.

Li H, Liu KJR, Lo SCB. Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms. IEEE Trans Med Imaging. 1997;16(6):785-798. doi:10.1109/42.650875.

Wei L, Yang Y, Nishikawa RM. Microcalcification classification assisted by content-based image retrieval for breast cancer diagnosis ଁ. 2009;42:1126-1132. doi:10.1016/j.patcog.2008.08.028.

Jaffe MJ. Chapter 9 : Mammography.


Koukou V, Martini N, Fountos G, et al. Nuclear Instruments and Methods in Physics Research A Dual energy subtraction method for breast calci fi cation imaging. Nucl Inst Methods Phys Res A. 2017;848(December 2016):31-38. doi:10.1016/j.nima.2016.12.034.

Mansour SM, Adel L. Characterization and guided-procedures of breast suspicious microcalcifications : can MicroPure ultrasound do it ? Egypt J Radiol Nucl Med. 2012;43(3):499-505. doi:10.1016/j.ejrnm.2012.07.001.

Khan FM. Physics of Radiation Therapy Third Edition. J Am Med Assoc. 2003:1138. doi:10.1001/jama.1953.02940340098036.

MURTY RC. Effective Atomic Numbers of Heterogeneous Materials. Nature. 1965;207(4995):398-399. doi:10.1038/207398a0.

Kurudirek M. Effective atomic numbers and electron densities of some human tissues and dosimetric materials for mean energies of various radiation sources relevant to radiotherapy and medical applications. Radiat Phys Chem. 2014;102(May):139-146. doi:10.1016/j.radphyschem.2014.04.033.

Mobley E. Detecting Microcalcifications in Digital Mammograms with ImageJ.



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.