Segmentation of breast cancer histopathology tissue micro-arrays for computer-aided diagnosis in pathology

Abstract:

Computer-Aided Diagnosis (CAD) systems for pathologists can act as an intelligent digital assistant supporting automated grading and morphometric-based discovery of tissue features that are important in cancer diagnosis and patient prognosis. Automated image segmentation is an essential component of computer-based grading in CAD. 

• We describe a novel tissue segmentation algorithm using local feature-based multiphase active contours in a globally convex formulation [1, 2]. By decomposing the image into intensity and chromaticity channels we utilize multiple feature based fitting terms to drive the active contour evolution for effective stromal-epithelial separation. Experimental results using the Stanford Tissue MicroArray (TMA) database shows promising stromal/epithelial superpixel segmentation.

• Applying and testing deep learning models [3].

"Histopathology - ἱστόπάθολογί - Histo-tissue, patho-disease" 

More Results:

               TBA  - Please see our poster at Figshare!

References:

[1] V. B. S. Prasath, F. Bunyak, P. Dale, S. R. Frazier, K. Palaniappan. Segmentation of breast cancer tissue microarrays for computer-aided diagnosis in pathology. First IEEE Healthcare Technology Conference: Translational Engineering in Health & Medicine (IEEE HIC 2012), Houston, TX, USA.

[2] V. B. S. Prasath, F. Bunyak, P. Dale, S. R. Frazier, K. Palaniappan. Stromal-epithelial separation for breast cancer tissue microarrays histopathology. Poster at the Missouri Life Sciences Week 2014. figshare: 10.6084/m9.figshare.997514.

In preparation:

[3] V. B. S. Prasath et al. Segmentation of tissue microarrays for stromal-epithelial separation in pathology. In preparation, 2025.

Back to Histopathology Projects Main Page. Back to Research Page.