Detection of lobular carcinoma in situ(LCIS) by image analysis

Author

Kim, Sujin ; Choi, Hyun-Joo ; Kim, Desok ; Joo, Hee Jae

Author_Institution

Div. of Biomed. Inf., Univ. of Kentucky, Lexington, KY, USA

fYear

2011

fDate

12-15 Nov. 2011

Firstpage

623

Lastpage

624

Abstract

In this study, we aimed to develop a quantitative image analysis method that may enhance the detection of the lobular carcinoma in-situ (LCIS) in breast cancer specimens. Glandular areas were segmented by using mathematical morphology from 5X histologic images of breast cancer cases (n=213). Computational features such as shape, intensity, and texture were extracted from glandular areas. Segmented glandular areas of LCIS were significantly larger, thicker, lower and less variant in intensity, compared to normal areas (Mann-Whitney test, p<;0.01). Our models based on data mining algorithms detected LCIS frames at the accuracy rate close to 99%. Our proposed methods may be well incorporated into a further development of computer aided detection (CAD) software for the screening of whole slide images to locate the LCIS areas.

Keywords

CAD; biological tissues; cancer; data mining; image segmentation; image texture; mathematical morphology; medical image processing; CAD; Mann-Whitney testing; breast cancer specimens; computer aided detection; data mining algorithms; histologic images; image segmentation; lobular carcinoma detection; mathematical morphology; quantitative image analysis method; slide images; texture; Breast cancer; Feature extraction; Glands; Image analysis; Image segmentation; Pathology; Breast Cancer; Computer Aided Detection; Image Analysis; Lobular Carcinoma In-situ (LCIS); Pattern Recognition; Whole Slide Images;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics and Biomedicine Workshops (BIBMW), 2011 IEEE International Conference on

Conference_Location

Atlanta, GA

Print_ISBN

978-1-4577-1612-6

Type

conf

DOI

10.1109/BIBMW.2011.6112440

Filename

6112440