Presentation 2017-03-14
Analysis of temporal change of astrocyte morphology under hypoxial adaptation using higher-order image features
Tomohiro Nishino, Sosuke Tanaka, Masahiro Nitta, Takuma Sugashi, Kazuto Masamoto, Yoichi Miyawaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Astrocytes play an important role in controlling oxygen and nutrition from the blood to neurons. Although the shape of astrocytes is known to change under pathological conditions such as hypoxia, it is unclear how it dynamically changes after the onset of the pathological conditions. Our previous studies proposed an approach using deep convolutional neural network (DCNN) to describe morphological changes of astrocytes and demonstrated that DCNN-extracted image features are effective to discriminate astrocytes for pre- and post-hypoxia adaptation. In this study, we further extend this approach to analysis of dynamical changes of astrocyte shapes over the time course of hypoxia adaptation. We measured the same astrocyte images from one mouse using the two-photon microscope at multiple days after hypoxia induction, and performed classification analysis to predict whether given astrocyte images are measured during pre- or post-hypoxia adaptation using DCNN-extracted image features. Results showed that prediction accuracy gradually increased while the number of image features necessary for pre-/post-adaptation prediction decreased as hypoxia adaptation progressed. Further analyses revealed that the predictive image features only partially agreed between different stages of hypoxia adaptation. These results suggest that DCNN-extracted image features are effective to capture dynamical and continuous changes of astrocyte morphology during hypoxia adaptation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Astrocyte / Deep convolutional neural network / Hypoxial adaptation / Higher-order image feature / Cellular morphology / Two-photon microscopy / Support vector machine / Machine learning
Paper # NC2016-91
Date of Issue 2017-03-06 (NC)

Conference Information
Committee MBE / NC
Conference Date 2017/3/13(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kikai-Shinko-Kaikan Bldg.
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yutaka Fukuoka(Kogakuin Univ.) / Shigeo Sato(Tohoku Univ.)
Vice Chair Kazuki Nakajima(Univ. of Toyama) / Masafumi Hagiwara(Keio Univ.)
Secretary Kazuki Nakajima(Kogakuin Univ.) / Masafumi Hagiwara(Toyama Pref. Univ.)
Assistant Ryota Horie(Shibaura Inst. of Tech.) / Kim Juhyon(Univ. of Toyama) / Hisanao Akima(Tohoku Univ.) / Yoshihisa Shinozawa(Keio Univ.)

Paper Information
Registration To Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis of temporal change of astrocyte morphology under hypoxial adaptation using higher-order image features
Sub Title (in English)
Keyword(1) Astrocyte
Keyword(2) Deep convolutional neural network
Keyword(3) Hypoxial adaptation
Keyword(4) Higher-order image feature
Keyword(5) Cellular morphology
Keyword(6) Two-photon microscopy
Keyword(7) Support vector machine
Keyword(8) Machine learning
1st Author's Name Tomohiro Nishino
1st Author's Affiliation The University of Electro-Communications(UEC Tokyo)
2nd Author's Name Sosuke Tanaka
2nd Author's Affiliation The University of Electro-Communications(UEC Tokyo)
3rd Author's Name Masahiro Nitta
3rd Author's Affiliation The University of Electro-Communications(UEC Tokyo)
4th Author's Name Takuma Sugashi
4th Author's Affiliation The University of Electro-Communications(UEC Tokyo)
5th Author's Name Kazuto Masamoto
5th Author's Affiliation The University of Electro-Communications(UEC Tokyo)
6th Author's Name Yoichi Miyawaki
6th Author's Affiliation The University of Electro-Communications(UEC Tokyo)
Date 2017-03-14
Paper # NC2016-91
Volume (vol) vol.116
Number (no) NC-521
Page pp.pp.159-164(NC),
#Pages 6
Date of Issue 2017-03-06 (NC)