Morphological analysis of mammary biopsy images

Author

Marroquin, E.M. ; Santamaria, E. ; Jove, X. ; Socoró, J.C.

Author_Institution

Dept. of Commun. & Signal Theory, Univ. Ramon Llull, Barcelona, Spain

Volume

2

fYear

1996

fDate

13-16 May 1996

Firstpage

1067

Abstract

The authors present an automatic system to analyse a cell nucleus in a given biopsy of mammary tissue which is cancerous. Identification and characterization of the cell nucleus provides enough information to diagnose a high or low grade cancer. This is a high interest differentiation for the pathologist to apply the correct therapy. Performing these measures by human observation is a hard, imprecise and subjective task. The algorithm they present processes the image in order to identify the cell nucleus over the rest of the tissue. Images are enhanced and segmented using morphological transformations. An ultimate erosion is used in two steps to separate cell nuclei in contact. It is based in a combination of symmetrical ultimate erosion with directional ultimate erosion

Keywords

biological techniques; cellular biophysics; feature extraction; image classification; image segmentation; mathematical morphology; medical image processing; optical microscopy; automatic system; cancer diagnosis; cancerous mammary tissue; cell nucleus analysis; cell nucleus characterization; cell nucleus identification; directional ultimate erosion; high resolution optical microscopy; image enhancement; image processing; image segmentation; mammary biopsy images; morphological analysis; morphological transformations; pathologist; symmetrical ultimate erosion; therapy; Biomedical measurements; Biopsy; Cancer; Humans; Image analysis; Nuclear measurements; Optical microscopy; Shape measurement; Signal analysis; Uniform resource locators;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 1996. MELECON '96., 8th Mediterranean

Conference_Location

Bari

Print_ISBN

0-7803-3109-5

Type

conf

DOI

10.1109/MELCON.1996.551392

Filename

551392