TY - GEN
T1 - Learning Spatially-correlated Temporal Dictionaries for Calcium Imaging
AU - Mishne, Gal
AU - Charles, Adam S.
N1 - Funding Information:
∗G.M. is supported by the NIBIB and the NINDS, of the NIH, Award R01EB026936. 1Spatial profiles are sometimes termed Regions of Interest (ROIs), however we prefer the terminology “profile” as it more accurately reflects that
Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - Calcium imaging has become a fundamental neural imaging technique, aiming to recover the individual activity of hundreds of neurons in a cortical region. Current methods (mostly matrix factorization) are aimed at detecting neurons in the field-of-view and then inferring the corresponding time-traces. In this paper, we reverse the modeling and instead aim to minimize the spatial inference, while focusing on finding the set of temporal traces present in the data. We reframe the problem in a dictionary learning setting, where the dictionary contains the time-traces and the sparse coefficient are spatial maps. We adapt dictionary learning to calcium imaging by introducing constraints on the norms and correlations of the time-traces, and incorporating a hierarchical spatial filtering model that correlates the time-trace usage over the field-of-view. We demonstrate on synthetic and real data that our solution has advantages regarding initialization, implicitly inferring number of neurons and simultaneously detecting different neuronal types.
AB - Calcium imaging has become a fundamental neural imaging technique, aiming to recover the individual activity of hundreds of neurons in a cortical region. Current methods (mostly matrix factorization) are aimed at detecting neurons in the field-of-view and then inferring the corresponding time-traces. In this paper, we reverse the modeling and instead aim to minimize the spatial inference, while focusing on finding the set of temporal traces present in the data. We reframe the problem in a dictionary learning setting, where the dictionary contains the time-traces and the sparse coefficient are spatial maps. We adapt dictionary learning to calcium imaging by introducing constraints on the norms and correlations of the time-traces, and incorporating a hierarchical spatial filtering model that correlates the time-trace usage over the field-of-view. We demonstrate on synthetic and real data that our solution has advantages regarding initialization, implicitly inferring number of neurons and simultaneously detecting different neuronal types.
KW - Calcium imaging
KW - Dictionary learning
KW - Re-weighted l
KW - Sparse coding
KW - Two-photon microscopy
UR - http://www.scopus.com/inward/record.url?scp=85069000269&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85069000269&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2019.8683375
DO - 10.1109/ICASSP.2019.8683375
M3 - Conference contribution
AN - SCOPUS:85069000269
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1065
EP - 1069
BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Y2 - 12 May 2019 through 17 May 2019
ER -