Three-dimensional GPU-accelerated active contours for automated localization of cells in large images - PubMed (original) (raw)
Three-dimensional GPU-accelerated active contours for automated localization of cells in large images
Mahsa Lotfollahi et al. PLoS One. 2019.
Abstract
Cell segmentation in microscopy is a challenging problem, since cells are often asymmetric and densely packed. Successful cell segmentation algorithms rely identifying seed points, and are highly sensitive to variablility in cell size. In this paper, we present an efficient and highly parallel formulation for symmetric three-dimensional contour evolution that extends previous work on fast two-dimensional snakes. We provide a formulation for optimization on 3D images, as well as a strategy for accelerating computation on consumer graphics hardware. The proposed software takes advantage of Monte-Carlo sampling schemes in order to speed up convergence and reduce thread divergence. Experimental results show that this method provides superior performance for large 2D and 3D cell localization tasks when compared to existing methods on large 3D brain images.
Conflict of interest statement
The authors have declared that no competing interests exist.
Figures
Fig 1
(a) A snakuscule is defined by two points p and q. (b) Initial configuration of multitude snakuscules congregated together at a distance 1.5R.
Fig 2
(a) A DAPI stained brain tissue slice. (b) The initial configuration and (c) final configuration of snakuscules on a zoomed region.
Fig 3
(a) A 3D snakuscule defined by two points p and q; to simplify computations 3D snakusules identifier points are considered in the same y and z levels. (b) The initial configuration consists of every two neighboring 3D contours located at a distance 1.5R apart. (c) The middle section of the 3D snakuscule with four distinct regions are shown in different colors. (d) The weight function assigns a weight to any portion of the 3D snakuscule shown in (c).
Fig 4. Energy changes of the 3D snake with and without normalization term w.r.t its radius.
Energy function with normalization term has a single local minimum when the snake fit the blob.
Fig 5. Execution time for the method implemented on CPU and GPU.
Time axis is plotted on a logarithmic scale.
Fig 6. Execution time of snakuscules (2D) on GPU with and without Monte-Carlo sampling.
Fig 7. Execution time of 3D snakuscules on GPU with and without Monte Carlo sampling.
Fig 8. Parallel implementation on GPU.
(a) Assignment of each contour to a thread block. (b) The algorithm implemented on GPU.
Fig 9
(a) A section of DAPI stained mouse hippocampus 3D image and (b) the final configuration of 3D snakuscules on the section.
Fig 10. Evaluation of different algorithms on the same DAPI stained image.
Our proposed method (3D snakuscule) provides results which matches the ground truth better than others.
Fig 11. Representing one section of different 3D datasets used for cell detection.
(a) Fluo-N3DH_CE (b) Fluo-N3DH-SIM+ (c) Mouse-Brain.
Fig 12. Quantification of the effect of Gaussian-distributed noise on localization accuracy.
Reducing SNR to 0.2 results in a drop in F-measure from 0.96 to 0.75.
Fig 13
(a) Theoretical occupancy, green, and achieved occupancy using different size images (different number of initial 3D snakuscules) with and without Monte Carlo integration, blue and red respectively. Parallel 3D snakuscules provide an achieved occupancy (purple) comparable to the theoretical limit. (b) The diagram shows execution time of the method implemented on GPU using MC integration before and after further parallelization for different number of initiated 3D snakuscules.
Similar articles
- Spline-based deforming ellipsoids for interactive 3D bioimage segmentation.
Delgado-Gonzalo R, Chenouard N, Unser M. Delgado-Gonzalo R, et al. IEEE Trans Image Process. 2013 Oct;22(10):3926-40. doi: 10.1109/TIP.2013.2264680. Epub 2013 May 22. IEEE Trans Image Process. 2013. PMID: 23708807 - Scalable and massively parallel Monte Carlo photon transport simulations for heterogeneous computing platforms.
Yu L, Nina-Paravecino F, Kaeli D, Fang Q. Yu L, et al. J Biomed Opt. 2018 Jan;23(1):1-4. doi: 10.1117/1.JBO.23.1.010504. J Biomed Opt. 2018. PMID: 29374404 Free PMC article. - An automatic segmentation algorithm for 3D cell cluster splitting using volumetric confocal images.
Indhumathi C, Cai YY, Guan YQ, Opas M. Indhumathi C, et al. J Microsc. 2011 Jul;243(1):60-76. doi: 10.1111/j.1365-2818.2010.03482.x. Epub 2011 Feb 2. J Microsc. 2011. PMID: 21288236 - A new algorithm of brain volume contours segmentation.
Wu JM, Shi PF. Wu JM, et al. J Zhejiang Univ Sci. 2003 May-Jun;4(3):294-9. doi: 10.1631/jzus.2003.0294. J Zhejiang Univ Sci. 2003. PMID: 12765282 Clinical Trial. - Graphics processing units-accelerated adaptive nonlocal means filter for denoising three-dimensional Monte Carlo photon transport simulations.
Yuan Y, Yu L, Doğan Z, Fang Q. Yuan Y, et al. J Biomed Opt. 2018 Nov;23(12):1-9. doi: 10.1117/1.JBO.23.12.121618. J Biomed Opt. 2018. PMID: 30499265 Free PMC article.
Cited by
- Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging.
Campos RL, Yoon SC, Chung S, Bhandarkar SM. Campos RL, et al. Sensors (Basel). 2023 Aug 8;23(16):7014. doi: 10.3390/s23167014. Sensors (Basel). 2023. PMID: 37631551 Free PMC article. - Whole-brain tissue mapping toolkit using large-scale highly multiplexed immunofluorescence imaging and deep neural networks.
Maric D, Jahanipour J, Li XR, Singh A, Mobiny A, Van Nguyen H, Sedlock A, Grama K, Roysam B. Maric D, et al. Nat Commun. 2021 Mar 10;12(1):1550. doi: 10.1038/s41467-021-21735-x. Nat Commun. 2021. PMID: 33692351 Free PMC article.
References
- Irshad H, Veillard A, Roux L, Racoceanu D. Methods for nuclei detection, segmentation, and classification in digital histopathology: a review—current status and future potential. IEEE reviews in biomedical engineering. 2014;7:97–114. - PubMed
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources