Abstract
Calcium imaging is one of the most important tools in neurophysiology as it enables the observation of neuronal activity for hundreds of cells in parallel and at single-cell resolution. In order to use the data gained with calcium imaging, it is necessary to extract individual cells and their activity from the recordings. We present DISCo, a novel approach for the cell segmentation in calcium imaging videos. We use temporal information from the recordings in a computationally efficient way by computing correlations between pixels and combine it with shape-based information to identify active as well as non-active cells. We first learn to predict whether two pixels belong to the same cell; this information is summarized in an undirected, edge-weighted graph which we then partition. Evaluating our method on the Neurofinder public benchmark shows that DISCo outperforms all existing models trained on these datasets.
E. Kirschbaum—This work was done while E.K. was at 1.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
We used the U-Net implementation provided in Inferno 0.3.0 with depth five, see https://github.com/inferno-pytorch/inferno.
- 3.
Leaderboard of the Neurofinder challenge at http://neurofinder.codeneuro.org. Accessed: 2020-03-05. We do not discuss the submissions Mask R-CNN and human-label since we have no information on the used models and training procedures.
References
Bailoni, A., Pape, C., Wolf, S., Beier, T., Kreshuk, A., Hamprecht, F.A.: A generalized framework for agglomerative clustering of signed graphs applied to instance segmentation. arXiv preprint (2019)
CodeNeuro: neurofinder public benchmark (2016). http://neurofinder.codeneuro.org. Accessed 05 Mar 2020
Denk, W., Strickler, J.H., Webb, W.W.: Two-photon laser scanning fluorescence microscopy. Science 248, 73–76 (1990)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26, 297–302 (1945)
Diego, F., Hamprecht, F.A.: Learning multi-level sparse representations. In: NIPS (2013)
Diego, F., Hamprecht, F.A.: Sparse space-time deconvolution for calcium image analysis. In: NIPS (2014)
Diego, F., Reichinnek, S., Both, M., Hamprecht, F.A.: Automated identification of neuronal activity from calcium imaging by sparse dictionary learning. In: IEEE International Symposium on Biomedical Imaging (ISBI) (2013)
Flusberg, B.A., et al.: High-speed, miniaturized fluorescence microscopy in freely moving mice. Nat. Methods (2008)
Friedrich, J., Zhou, P., Paninski, L.: Fast online deconvolution of calcium imaging data. PLoS Comput. Biol. 13, e1005423 (2017)
Gao, S.: Conv2D (2016). https://github.com/iamshang1/Projects/tree/master/Advanced_ML/Neuron_Detection. Accessed 19 Jul 2019
Giovannucci, A., et al.: Caiman an open source tool for scalable calcium imaging data analysis. eLife 8, e38173 (2019)
Giovannucci, A., et al.: Onacid: online analysis of calcium imaging data in real time. In: NIPS (2017)
Helmchen, F., Denk, W.: Deep tissue two-photon microscopy. Nat. Methods (2005)
Kaifosh, P., Zaremba, J.D., Danielson, N.B., Losonczy, A.: SIMA: python software for analysis of dynamic fluorescence imaging data. Front. Neuroinform. 8, 80 (2014)
Keuper, M., Levinkov, E., Bonneel, N., Lavoué, G., Brox, T., Andres, B.: Efficient decomposition of image and mesh graphs by lifted multicuts. In: IEEE International Conference on Computer Vision (ICCV), Proceedings (2015)
Kirschbaum, E., et al.: LeMoNADe: learned motif and neuronal assembly detection in calcium imaging videos. In: International Conference on Learning Representations (ICLR), Proceedings (2018)
Klibisz, A., Rose, D., Eicholtz, M., Blundon, J., Zakharenko, S.: Fast, simple calcium imaging segmentation with fully convolutional networks. In: International Workshop on Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA and ML-CDS), held in conjunction with MICCAI (2017)
Levinkov, E., Kirillov, A., Andres, B.: A comparative study of local search algorithms for correlation clustering. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 103–114. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66709-6_9
Nikolić, D., Mureşan, R.C., Feng, W., Singer, W.: Scaled correlation analysis: a better way to compute a cross-correlogram. Eur. J. Neurosci. 35, 742–762 (2012)
Pachitariu, M., Packer, A.M., Pettit, N., Dalgleish, H., Hausser, M., Sahani, M.: Extracting regions of interest from biological images with convolutional sparse block coding. In: NIPS (2013)
Pachitariu, M., et al.: Suite2p: beyond 10,000 neurons with standard two-photon microscopy. bioRxiv preprint (2017)
Pearson, K.: Notes on regression and inheritance in the case of two parents. Proc. Roy. Soc. Lond. 58, 240–242 (1895)
Petersen, A., Simon, N., Witten, D.: Scalpel: extracting neurons from calcium imaging data. Ann. Appl. Stat. 12, 2430 (2018)
Pnevmatikakis, E.A., et al.: A structured matrix factorization framework for large scale calcium imaging data analysis. arXiv preprint (2014)
Pnevmatikakis, E.A., Paninski, L.: Sparse nonnegative deconvolution for compressive calcium imaging: algorithms and phase transitions. In: NIPS (2013)
Pnevmatikakis, E.A., et al.: Simultaneous denoising, deconvolution, and demixing of calcium imaging data. Neuron 89, 285–299 (2016)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Soltanian-Zadeh, S., Sahingur, K., Blau, S., Gong, Y., Farsiu, S.: Fast and robust active neuron segmentation in two-photon calcium imaging using spatiotemporal deep learning. Proc. Natl. Acad. Sci. 116, 8554–8563 (2019)
Sørensen, T.J.: A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons. Biol. Skar 5, 1–34 (1948)
Spaen, Q., Asín-Achá, R., Chettih, S.N., Minderer, M., Harvey, C., Hochbaum, D.S.: HNCcorr: a novel combinatorial approach for cell identification in calcium-imaging movies. eNeuro (2019)
Székely, G.J., Rizzo, M.L., Bakirov, N.K.: Measuring and testing dependence by correlation of distances. Ann. Stat. 35, 2769–2794 (2007)
Wolf, S., et al.: The mutex watershed: efficient, parameter-free image partitioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 571–587. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_34
Acknowledgements
We gratefully acknowledge partial financial support by DFG SFB 1134 Functional Ensembles and DFG HA 4364/9-1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kirschbaum, E., Bailoni, A., Hamprecht, F.A. (2020). DISCo: Deep Learning, Instance Segmentation, and Correlations for Cell Segmentation in Calcium Imaging. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12265. Springer, Cham. https://doi.org/10.1007/978-3-030-59722-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-59722-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59721-4
Online ISBN: 978-3-030-59722-1
eBook Packages: Computer ScienceComputer Science (R0)