Automated Reconstruction of Dendritic and Axonal Trees by Global Optimization with Geometric Priors
- 690 Downloads
We present a novel probabilistic approach to fully automated delineation of tree structures in noisy 2D images and 3D image stacks. Unlike earlier methods that rely mostly on local evidence, ours builds a set of candidate trees over many different subsets of points likely to belong to the optimal tree and then chooses the best one according to a global objective function that combines image evidence with geometric priors. Since the best tree does not necessarily span all the points, the algorithm is able to eliminate false detections while retaining the correct tree topology. Manually annotated brightfield micrographs, retinal scans and the DIADEM challenge datasets are used to evaluate the performance of our method. We used the DIADEM metric to quantitatively evaluate the topological accuracy of the reconstructions and showed that the use of the geometric regularization yields a substantial improvement.
KeywordsDIADEM Tree reconstruction Global optimization Minimum arborescence k-MST Ant colony optimization
This work was supported in part by the Swiss National Science Foundation and in part by the MicroNano ERC project. Christian Blum also acknowledges support from the Ramón y Cajal program of the Spanish Government.
We would like to thank Felix Schürmann for his advice and for giving us access to the brightfield dataset and corresponding ground-truth.
- Ascoli, G. A., Svoboda, K., & Liu Y. (2010). Digital reconstruction of axonal and dendritic morphology DIADEM challenge. http://diademchallenge.org/.
- Blum, C., & Blesa M. (2005). Combining ant colony optimization with dynamic programming for solving the K-cardinality tree problem. In Computational intelligence and bioinspired systems. Lecture notes in computer science (Vol. 3512, pp. 25–33).Google Scholar
- Fan, D. (2006). Bayesian inference of vascular structure from retinal images. Ph.D. thesis, Dept. of Computer Science, U. of Warwick, Coventry, UK.Google Scholar
- Felzenszwalb, P., & McAllester, D. (2006). A min-cover approach for finding salient curves. In Conference on computer vision and pattern recognition (pp. 61–74).Google Scholar
- Fischler, M., & Heller, A. (1998). Automated techniques for road network modeling. In DARPA image understanding workshop (pp. 501–516).Google Scholar
- Frangi, A. F., Niessen, W. J., Vincken, K. L., & Viergever, M. A. (1998). Multiscale vessel enhancement filtering. Lecture Notes in Computer Science, 1496, 130–137.Google Scholar
- Garg, N. (1996). A 3-approximation for the minimum tree spanning K vertices. In IEEE symposium on foundations of computer science (Vol. 27, pp. 302–309). Washington, DC, USA: IEEE Computer Society.Google Scholar
- Gonzalez, G., Aguet, F., Fleuret, F., Unser, M., & Fua, P. (2009). Steerable features for statistical 3D dendrite detection. In Conference on medical image computing and computer assisted intervention (Vol. 12, pp. 625–32).Google Scholar
- Gonzalez, G., Fleuret, F., & Fua, P. (2008). Automated delineation of dendritic networks in noisy image stacks. In European conference on computer vision. Lecture notes in computer science (Vol. 5305, pp. 214–227). Berlin/Heidelberg: Springer.Google Scholar
- Huang, K., & Yan, M. (2006). Robust optic disk detection in retinal images using vessel structure and radon transform. In SPIE (Vol. 6144).Google Scholar
- Law, M., & Chung, A. (2008). Three dimensional curvilinear structure detection using optimally oriented flux. In European conference on computer vision (pp. 368–382).Google Scholar
- Leordeanu, M., Hebert, M., & Sukthankar, R. (2007). Beyond local appearance: Category recognition from pairwise interactions of simple features. In Conference on computer vision and pattern recognition (pp. 1 –8).Google Scholar
- Platt, J. (2000). Advances in large margin classifiers. Chap probabilistic outputs for SVMs and comparisons to regularized likelihood methods. Cambridge, MA: MIT Press.Google Scholar
- Santamaría-Pang, A., Colbert, C. M., Saggau, P., & Kakadiaris, I. (2007). Automatic centerline extraction of irregular tubular structures using probability volumes from multiphoton imaging. In Conference on medical image computing and computer assisted intervention (pp. 486–494).Google Scholar
- Schoelkopf, B., Burges, C., & Smola, A. (1999). Advances in Kernel methods. In Support vector learning. Cambridge, MA: MIT Press.Google Scholar
- Sun, K., Sang, N., & Zhang, T. (2007). Marked point process for vascular tree extraction on angiogram. In Conference on computer vision and pattern recognition (pp. 467–478).Google Scholar
- Xie, J., Zhao, T., Lee, T., Myers, G., & Peng, H. (2010). Automatic neuron tracing in volumetric microscopy images with anisotropic path searching. In Conference on medical image computing and computer assisted intervention.Google Scholar
- Yedidya, T., & Hartley, R. (2008). Tracking of blood vessels in retinal images using Kalman filter. In Digital image computing: Techniques and applications (pp. 52–58).Google Scholar