Automated Microtubule Path Tracking on Gliding Assay Using Hidden Markov Model — ASN Events
  1. Schedule
  2. High Performance & Supercomputing in Bioinformatics & Bioimaging
  3. Automated Microtubule Path Tracking on Gliding Assay Using Hidden Markov Model

Automated Microtubule Path Tracking on Gliding Assay Using Hidden Markov Model (#27)

Bulibuli Mahemuti 1 , Yuexing Han 1 2 , Daisuke Inoue 3 , Akira Kakugo 3 4 , Akihiko Konagaya 1
  1. Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan
  2. School of Computer Engineering and Science, Shanghai University, Shanghai , China
  3. Faculty of Science, Hokkaido University, Sapporo, Japan
  4. Graduate School of Chemical Sciences and Engineering, Hokkaido University, Sapporo, Japan

Object tracking is an important issue in bio-imaging and necessary to elucidate the dynamics of molecules from video data. In microtubule gliding assays, object tracking becomes non-trivial due to the occurrences of compound objects such as crossing and snuggling of microtubules as well as sudden appearance and disappearance of microtubules. In order to solve these issues, in our study, we discuss the newly created object tracking methodology using a Hidden Markov model. The microtubule Hidden Markov model enables us to estimate a plausible tracking paths efficiently by means of decomposing hidden states of compound objects. These microtubule tracking paths can enhance our understanding of the dynamics of microtubule movement. Our future work will focus on further improving the microtubule recognition accuracy.