Work

Semi-automatic neuron segmentation in electron microscopy images via sparse labeling

Year: 2013

Type: conference-paper

Abstract: We introduce a novel method for utilizing user input to sparsely label membranes in electron microscopy images. Using gridlines as guides, the user marks where the guides cross the membrane to generate a sparsely labeled image. We use a best path algorithm to connect each of the sparse membrane labels. The resulting segmentation has a significantly better Rand error than automatic methods while requiring as little as 2% of the image to be labeled.

Source: IEEE International Symposium on Biomedical Imaging (ISBI)

DOI: 10.1109/isbi.2013.6556771

Authors: Cory Jones, Ting Liu, Mark Ellisman, Tolga Tasdizen

Institutions: University of Utah, University of California San Diego

Language: English

Topic: Cell Image Analysis Techniques

Subfield: Biophysics

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: green

Funders: National Institute of General Medical Sciences, National Institute of Neurological Disorders and Stroke

Awards: Support of and Extensions to the Cell Image Library, SLASH: SCALABLE LARGE ANALYTIC SEGMENTATION HYBRID, IVEM and Image Analysis Resource