Interactive Cell Segmentation Based on Correction Propagation

Abstract

Automatic cell segmentation can hardly be flawless due to the complexity of image data particularly when time-lapse experiments last for a long time without biomarkers. To address this issue, we propose an interactive cell segmentation method that actively selects uncertain regions and requests human validation on them. Once erroneous segmentation is detected and subsequently corrected, the information is propagated over affinity graphs in order to fix analogous errors. We present a systematical method for correction propagation based on active and semi-supervised learning. Experimental results performed on three types of cell populations validate that our interactive cell segmentation quickly reaches high quality results with minimal human interventions, and thus is significantly more efficient than alternative methods.

Meeting Name

2014 IEEE 11th International Symposium on Biomedical Imaging (2014: Apr. 29-May 2, Beijing, China)

Department(s)

Computer Science

Keywords and Phrases

Cell Culture; Cell Proliferation; Cells; Cytology; Medical Imaging; Supervised Learning; Cell Populations; Cell Segmentation; High Quality; Human Intervention; Image Data; Semi-Supervised Learning; Image Segmentation; Active Learning; Correction Propagation; Interactive Correction

International Standard Book Number (ISBN)

978-1467319591

International Standard Serial Number (ISSN)

1945-7928; 1945-8452

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2014 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jul 2014

Link to Full Text

Share

 
COinS