Toward consistent cell segmentation: quality assessment of cell segments via appearance and geometry features

Andrew Brinker; Annika Fredrikson; Xiaofan Zhang; Richard Sourvenir; Shaoting Zhang

doi:10.1117/12.2082329

Translator Disclaimer

19 March 2015 Toward consistent cell segmentation: quality assessment of cell segments via appearance and geometry features

Andrew Brinker, Annika Fredrikson, Xiaofan Zhang, Richard Sourvenir, Shaoting Zhang

Author Affiliations +

Proceedings Volume 9420, Medical Imaging 2015: Digital Pathology; 94200O (2015) https://doi.org/10.1117/12.2082329
Event: SPIE Medical Imaging, 2015, Orlando, Florida, United States

Abstract

Computer-Aided Diagnosis (CAD) systems based on histopathological images rely on quality low-level image processing, including cell segmentation. Many methods for cell segmentation lack in generality and struggle with the wide variety of cell appearance and inter-cell structure present in histopathological images. We present a computationally efficient system to classify segmentation results as the first step toward automatic segment correction. This general method can applied to existing or future cell segmentation methods to provide corrections for low-quality results. Specifically, with a small collection of easy-to-compute features, we can identify incorrect segments with a high degree of accuracy, which then can be used to determine the needed corrections based on the type of segmentation failure present.

Citation Download Citation

Andrew Brinker, Annika Fredrikson, Xiaofan Zhang, Richard Sourvenir, and Shaoting Zhang "Toward consistent cell segmentation: quality assessment of cell segments via appearance and geometry features", Proc. SPIE 9420, Medical Imaging 2015: Digital Pathology, 94200O (19 March 2015); https://doi.org/10.1117/12.2082329

ACCESS THE FULL ARTICLE