Accurate estimation of neuronal count and distribution is central to the understanding of the organization and layout of cortical maps in the brain, and changes in the cell population induced by brain disorders. High-throughput 3D microscopy techniques such as Knife-Edge Scanning Microscopy (KESM) are enabling whole-brain survey of neuronal distributions. Data from such techniques pose serious challenges to quantitative analysis due to the massive, growing, and sparsely labeled nature of the data. In this paper, we present a scalable, incremental learning algorithm for cell body detection that can address these issues. Our algorithm is computationally efficient (linear mapping, non-iterative) and does not require retraining (unlike gradient-based approaches) or retention of old raw data (unlike instance-based learning). We tested our algorithm on our rat brain Nissl data set, showing superior performance compared to an artificial neural network-based benchmark, and also demonstrated robust performance in a scenario where the data set is rapidly growing in size. Our algorithm is also highly parallelizable due to its incremental nature, and we demonstrated this empirically using a MapReduce-based implementation of the algorithm. We expect our scalable, incremental learning approach to be widely applicable to medical imaging domains where there is a constant flux of new data. © 2013 IEEE.
|Original language||English (US)|
|Title of host publication||The 2013 International Joint Conference on Neural Networks (IJCNN)|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|State||Published - Aug 2013|
Bibliographical noteKAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): KUSC1-016-04
Acknowledgements: This publication is based in part on work supported by Award No. KUSC1-016-04, made by King Abdullah University of Science and Technology(KAUST); NIH/NINDS grant #R01-NS54252, NSF grants #0079874,#0905041, and #1208174; and by the Breakout Labs. Computing time onAmazon EC2 was generously donated by Amazon. Chul Sung was supportedby 3Scan as an intern while conducting part of this research. We would liketo thank Bruce H. McCormick, Bernard Mesa, Louise C. Abbott, DavidMayerich, and Jaerock Kwon for their contributions in data acquisition, andSugato Basu for helpful comments on machine learning and MapReduce.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.