Pop Out Many Small Structures from a Very Large Microscopic Image

TitlePop Out Many Small Structures from a Very Large Microscopic Image
Publication TypeConference Paper
Year of Publication2011
AuthorsBernardis, E., & Yu S. X.
Published inMedical Image Analysis
KeywordsDigital Pathology, Segmentation, spectral graph partitioning

In medical research, many applications require counting and measuring small regions in a large image. Segmenting these images poses a dilemma in terms of segmentation granularity due to fine structures and segmentation complexity due to large image sizes. We propose a constrained spectral graph partitioning framework to address the former while also reducing the segmentation complexity associated with the latter. The final segmentation is obtained from a set of patch segmentations, independently derived but subject to stitching constraints between neighboring patches. Individual segmentation is based on local pairwise cues designed to pop out all cells simultaneously from their common background, while the constraints are derived from mutual agreement analysis on patch segmentations from a previous round of segmentation. Our results show that we successfully extract many small regions in a variety of images.


This research was funded by NSF CAREER IIS-0644204 and a Clare Boothe
Luce Professorship to Stella X. Yu.

ICSI Research Group