Automated Segmentation of HeLa Nuclear Envelope from Electron Microscopy Images
Karabağ, C. 
ORCID: 0000-0003-4424-0471, Jones, M., Peddie, C. J. , Weston, A. E., Collinson, L. M. & Reyes-Aldasoro, C. C. ORCID: 0000-0002-9466-2018 (2018).
Automated Segmentation of HeLa Nuclear Envelope from Electron Microscopy Images.
Poster presented at the British Association for Cancer Research Conference, 19 Nov 2018.
Abstract
This work describes an algorithm to segment the nuclear envelope (NE) of HeLa cancer cells from Electron Microscopy images. The algorithm is unsupervised, fully automatic, fast and processes one image in less than 10 seconds. Comparison with hand segmented ground truth reported Jaccard values 94% - 98% and Hausdorff distance 4-13 pixels and the algorithm outperformed segmentation with active contours. Code and data are freely available at https://github.com/reyesaldasoro/Hela-Cell-Segmentation and http://dx.doi.org/10.6019/EMPIAR-10094.
| Publication Type: | Conference or Workshop Item (Poster) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Departments: | School of Science & Technology School of Science & Technology > Department of Computer Science School of Science & Technology > Department of Computer Science > giCentre |
| SWORD Depositor: |
Metadata
MetadataActions (login required)
Admin Login