Automatic segmentation of histological structures in mammary gland tissue sections
Abstract
Real-time three-dimensional (3D) reconstruction of epithelial structures in human mammary gland tissue blocks mapped with selected markers would be an extremely helpful tool for breast cancer diagnosis and treatment planning. Besides its clear clinical application, this tool could also shed a great deal of light on the molecular basis of breast cancer initiation and progression. In this paper we present a framework for real-time segmentation of epithelial structures in two-dimensional (2D) images of sections of normal and neoplastic mammary gland tissue blocks. Complete 3D rendering of the tissue can then be done by surface rendering of the structures detected in consecutive sections of the blocks. Paraffin embedded or frozen tissue blocks are first sliced, and sections are stained with Hematoxylin and Eosin. The sections are then imaged using conventional bright field microscopy and their background is corrected using a phantom image. We then use the Fast-Marching algorithm to roughly extract the contours of the different morphological structures in the images. The result is then refined with the Level-Set method which converges to an accurate (sub-pixel) solution for the segmentation problem. Finally, our system stacks together the 2D results obtained in order to reconstruct a 3D representation of the entire tissuemore »
- Authors:
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE. Office of Science. Office of Advanced Scientific Research. Mathematical Information and Computational Sciences Division, Laboratory Directed Research and Development Program; US Army Medical Research Materiel Command Grants DAMD1-00-1-0306 and DAMD17-00-1-0227; California Breast Cancer Research Program Project 8WB-0150
- OSTI Identifier:
- 838539
- Report Number(s):
- LBNL-53241
R&D Project: 80FV01; TRN: US200802%%1226
- DOE Contract Number:
- AC03-76SF00098
- Resource Type:
- Journal Article
- Journal Name:
- Journal of Biomedical Optics
- Additional Journal Information:
- Journal Volume: 9; Journal Issue: 3; Other Information: Journal Publication Date: May/June 2004
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 60; 42; ALGORITHMS; DIAGNOSIS; EOSIN; HEMATOXYLIN; MAMMARY GLANDS; MICROSCOPY; NEOPLASMS; PARAFFIN; PHANTOMS; PLANNING; Breast Cancer Molecular Analysis Automatic Segmentation 3D Reconstruction Fast Marching Level Set
Citation Formats
Fernandez-Gonzalez, Rodrigo, Deschamps, Thomas, Idica, Adam K, Malladi, Ravikanth, and Ortiz de Solorzano, Carlos. Automatic segmentation of histological structures in mammary gland tissue sections. United States: N. p., 2004.
Web. doi:10.1117/1.1699011.
Fernandez-Gonzalez, Rodrigo, Deschamps, Thomas, Idica, Adam K, Malladi, Ravikanth, & Ortiz de Solorzano, Carlos. Automatic segmentation of histological structures in mammary gland tissue sections. United States. https://doi.org/10.1117/1.1699011
Fernandez-Gonzalez, Rodrigo, Deschamps, Thomas, Idica, Adam K, Malladi, Ravikanth, and Ortiz de Solorzano, Carlos. 2004.
"Automatic segmentation of histological structures in mammary gland tissue sections". United States. https://doi.org/10.1117/1.1699011. https://www.osti.gov/servlets/purl/838539.
@article{osti_838539,
title = {Automatic segmentation of histological structures in mammary gland tissue sections},
author = {Fernandez-Gonzalez, Rodrigo and Deschamps, Thomas and Idica, Adam K and Malladi, Ravikanth and Ortiz de Solorzano, Carlos},
abstractNote = {Real-time three-dimensional (3D) reconstruction of epithelial structures in human mammary gland tissue blocks mapped with selected markers would be an extremely helpful tool for breast cancer diagnosis and treatment planning. Besides its clear clinical application, this tool could also shed a great deal of light on the molecular basis of breast cancer initiation and progression. In this paper we present a framework for real-time segmentation of epithelial structures in two-dimensional (2D) images of sections of normal and neoplastic mammary gland tissue blocks. Complete 3D rendering of the tissue can then be done by surface rendering of the structures detected in consecutive sections of the blocks. Paraffin embedded or frozen tissue blocks are first sliced, and sections are stained with Hematoxylin and Eosin. The sections are then imaged using conventional bright field microscopy and their background is corrected using a phantom image. We then use the Fast-Marching algorithm to roughly extract the contours of the different morphological structures in the images. The result is then refined with the Level-Set method which converges to an accurate (sub-pixel) solution for the segmentation problem. Finally, our system stacks together the 2D results obtained in order to reconstruct a 3D representation of the entire tissue block under study. Our method is illustrated with results from the segmentation of human and mouse mammary gland tissue samples.},
doi = {10.1117/1.1699011},
url = {https://www.osti.gov/biblio/838539},
journal = {Journal of Biomedical Optics},
number = 3,
volume = 9,
place = {United States},
year = {Tue Feb 17 00:00:00 EST 2004},
month = {Tue Feb 17 00:00:00 EST 2004}
}