Superpixel-based segmentation of muscle fibers in multi-channel microscopy
Background Confetti fluorescence and other multi-color genetic labelling strategies are useful for observing stem cell regeneration and for other problems of cell lineage tracing. One difficulty of such strategies is segmenting the cell boundaries, which is a very different problem from segmenting...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2017
|
| Online Access: | http://hdl.handle.net/1721.1/106208 https://orcid.org/0000-0003-4698-6488 |
| _version_ | 1826206883012149248 |
|---|---|
| author | So, Peter T. C. Heemskerk, Johannes Antonius Tucker-Kellogg, Lisa Nguyen, Binh P. |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering So, Peter T. C. Heemskerk, Johannes Antonius Tucker-Kellogg, Lisa Nguyen, Binh P. |
| author_sort | So, Peter T. C. |
| collection | MIT |
| description | Background
Confetti fluorescence and other multi-color genetic labelling strategies are useful for observing stem cell regeneration and for other problems of cell lineage tracing. One difficulty of such strategies is segmenting the cell boundaries, which is a very different problem from segmenting color images from the real world. This paper addresses the difficulties and presents a superpixel-based framework for segmentation of regenerated muscle fibers in mice.
Results
We propose to integrate an edge detector into a superpixel algorithm and customize the method for multi-channel images. The enhanced superpixel method outperforms the original and another advanced superpixel algorithm in terms of both boundary recall and under-segmentation error. Our framework was applied to cross-section and lateral section images of regenerated muscle fibers from confetti-fluorescent mice. Compared with “ground-truth” segmentations, our framework yielded median Dice similarity coefficients of 0.92 and higher.
Conclusion
Our segmentation framework is flexible and provides very good segmentations of multi-color muscle fibers. We anticipate our methods will be useful for segmenting a variety of tissues in confetti fluorecent mice and in mice with similar multi-color labels. |
| first_indexed | 2024-09-23T13:39:44Z |
| format | Article |
| id | mit-1721.1/106208 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:39:44Z |
| publishDate | 2017 |
| publisher | BioMed Central |
| record_format | dspace |
| spelling | mit-1721.1/1062082022-09-28T15:23:31Z Superpixel-based segmentation of muscle fibers in multi-channel microscopy So, Peter T. C. Heemskerk, Johannes Antonius Tucker-Kellogg, Lisa Nguyen, Binh P. Massachusetts Institute of Technology. Department of Mechanical Engineering Massachusetts Institute of Technology. Research Laboratory of Electronics Singapore-MIT Alliance in Research and Technology (SMART) Singapore-MIT Alliance in Research and Technology (SMART) So, Peter T. C. Heemskerk, Johannes Antonius Tucker-Kellogg, Lisa Nguyen, Binh P. Background Confetti fluorescence and other multi-color genetic labelling strategies are useful for observing stem cell regeneration and for other problems of cell lineage tracing. One difficulty of such strategies is segmenting the cell boundaries, which is a very different problem from segmenting color images from the real world. This paper addresses the difficulties and presents a superpixel-based framework for segmentation of regenerated muscle fibers in mice. Results We propose to integrate an edge detector into a superpixel algorithm and customize the method for multi-channel images. The enhanced superpixel method outperforms the original and another advanced superpixel algorithm in terms of both boundary recall and under-segmentation error. Our framework was applied to cross-section and lateral section images of regenerated muscle fibers from confetti-fluorescent mice. Compared with “ground-truth” segmentations, our framework yielded median Dice similarity coefficients of 0.92 and higher. Conclusion Our segmentation framework is flexible and provides very good segmentations of multi-color muscle fibers. We anticipate our methods will be useful for segmenting a variety of tissues in confetti fluorecent mice and in mice with similar multi-color labels. National University of Singapore (Duke-NUS SRP Phase 2 Research Block Grant) Singapore. National Research Foundation (CREATE programme) Singapore-MIT Alliance for Research and Technology (SMART) 2017-01-05T18:59:24Z 2017-01-05T18:59:24Z 2016-12 2016-12-06T05:51:05Z Article http://purl.org/eprint/type/JournalArticle 1752-0509 http://hdl.handle.net/1721.1/106208 Nguyen, Binh P., Hans Heemskerk, Peter T. C. So, and Lisa Tucker-Kellogg. “Superpixel-Based Segmentation of Muscle Fibers in Multi-Channel Microscopy.” BMC Systems Biology 10, no. S5 (December 2016): 39–50. https://orcid.org/0000-0003-4698-6488 en http://dx.doi.org/10.1186/s12918-016-0372-2 BMC Systems Biology Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf BioMed Central BioMed Central |
| spellingShingle | So, Peter T. C. Heemskerk, Johannes Antonius Tucker-Kellogg, Lisa Nguyen, Binh P. Superpixel-based segmentation of muscle fibers in multi-channel microscopy |
| title | Superpixel-based segmentation of muscle fibers in multi-channel microscopy |
| title_full | Superpixel-based segmentation of muscle fibers in multi-channel microscopy |
| title_fullStr | Superpixel-based segmentation of muscle fibers in multi-channel microscopy |
| title_full_unstemmed | Superpixel-based segmentation of muscle fibers in multi-channel microscopy |
| title_short | Superpixel-based segmentation of muscle fibers in multi-channel microscopy |
| title_sort | superpixel based segmentation of muscle fibers in multi channel microscopy |
| url | http://hdl.handle.net/1721.1/106208 https://orcid.org/0000-0003-4698-6488 |
| work_keys_str_mv | AT sopetertc superpixelbasedsegmentationofmusclefibersinmultichannelmicroscopy AT heemskerkjohannesantonius superpixelbasedsegmentationofmusclefibersinmultichannelmicroscopy AT tuckerkellogglisa superpixelbasedsegmentationofmusclefibersinmultichannelmicroscopy AT nguyenbinhp superpixelbasedsegmentationofmusclefibersinmultichannelmicroscopy |