Segmenting mammographic microcalcifications using a semi-automatic procedure based on Otsu s method and morphological filters
Revista Brasileira de Engenharia Biomédica · 2013 · 29 (4) · 377-388
DOI: 10.4322/rbeb.2013.037 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista Brasileira de Engenharia Biomédica, 2013. Verfasst von Marcelo de Almeida Duarte und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref).
Abstract (Originalsprache)
Introduction
Breast cancer has the second highest world's incidence rate, according to the Brazilian National Cancer Institute (INCa). Clinical examination and mammography are the best methods for early diagnosis. Computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems are developed to improve mammographic diagnosis. Basically, CADx systems have three components: (i) segmentation, (ii) parameters extraction and selection, (iii) lesion classifi cation. The fi rst step for a CADx system is segmentation.
Methods
A microcalcifi cation segmentation method is proposed, based on morphological operators, Otsu's Method and radiologists' knowledge. Pre-processing with top-hat operators improves contrast and reduces background noise. The Otsu's method automatically selects the best grey-level threshold to segment microcalcifi cations, obtaining binary images. Following, inferior reconstruction and morphological dilatation operators are applied to reconstruct lost structure details and fi ll small fl aws in the segmented microcalcifi cations. Finally, the Canny edge detection is applied to identify microcalcifi cations contour candidates for each region-of-interest (ROI). Two experienced radiologists intervene in this semi-automatic method, fi rstly, selecting the ROI and, then, analyzing the segmentation result. The method was assessed in 1000 ROIs from 158 digital images (300 dpi, 8 bits).
Results
Considering the radiologists opinion, the rates of ROIs adequately segmented to establish a diagnosis hypothesis were 97.8% for one radiologist and 97.3% for the other. Using the Area Overlap Measure (AOM) and the 2136 microcalcifi cations delineated by an experienced radiologist as gold standards, the method achieved an average AOM of 0.640.14, being 0.560.09 for small microcalcifi cations and 0.660.13 for the large ones. Moreover, AOM was 0.640.13 for the benign and 0.640.14 for the malignant lesions with no statistical differences between them.
Conclusion
Based on these fi ndings, the proposed method could be used to develop a CADx system that could help early breast cancer detection.
Zitieren
APA
Duarte, M. D. A., Alvarenga, A. V., Azevedo, C. M., Calas, M. J. G., Infantosi, A. F. C., & Pereira, W. C. D. A. (2013). Segmenting mammographic microcalcifications using a semi-automatic procedure based on Otsu s method and morphological filters. Revista Brasileira de Engenharia Biomédica, 29(4), 377-388. https://doi.org/10.4322/rbeb.2013.037
Vancouver
Duarte MDA, Alvarenga AV, Azevedo CM, Calas MJG, Infantosi AFC, Pereira WCDA. Segmenting mammographic microcalcifications using a semi-automatic procedure based on Otsu s method and morphological filters. Revista Brasileira de Engenharia Biomédica. 2013;29(4):377-388. doi:10.4322/rbeb.2013.037
BibTeX
@article{Duarte2013,
author = {Duarte, Marcelo de Almeida and Alvarenga, André Victor and Azevedo, Carolina Maria and Calas, Maria Julia Gregório and Infantosi, Antonio Fernando Catelli and Pereira, Wagner Coelho de Albuquerque},
title = {Segmenting mammographic microcalcifications using a semi-automatic procedure based on Otsu s method and morphological filters},
journal = {Revista Brasileira de Engenharia Biomédica},
year = {2013},
volume = {29},
number = {4},
pages = {377--388},
doi = {10.4322/rbeb.2013.037}
}
EUVIMED