Skip to Main content Skip to Navigation
Journal articles

Automatic detection of microcalcification based on morphological operations and structural similarity indices

Abstract : In this paper, a new method for automatic detection of microcalcifications in digitized mammograms is proposed. Based on mathematical morphology theory to deal with the problem of low contrast between microcalcifications and their surrounding pixels, it uses various structuring elements of different sizes to reduce the sensibility to microcalcification diversity sizes. The obtained morphological results are converted to a suspicion map based on an image quality assessment metric called structural similarity index (SSIM). This continuous map is, then, locally analyzed using superpixels to automatically estimate threshold values and finally detect potential microcalcification areas. The proposed method was evaluated using the publicly-available INBreast dataset. Experimental results show the benefits gained in terms of improving microcalcification detection performances compared to state-of-the-art methods.
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-02563861
Contributor : Pierre-Henri Conze <>
Submitted on : Tuesday, May 5, 2020 - 4:16:10 PM
Last modification on : Thursday, April 15, 2021 - 12:06:01 PM

Identifiers

Citation

Asma Touil, Karim Kalti, Pierre-Henri Conze, Basel Solaiman, Mohamed Ali Mahjoub. Automatic detection of microcalcification based on morphological operations and structural similarity indices. Biocybernetics and Biomedical Engineering, 2020, 40 (3), pp.1155-1173. ⟨10.1016/j.bbe.2020.05.002⟩. ⟨hal-02563861⟩

Share

Metrics

Record views

93