TY - JOUR
T1 - Automatic summarization of changes in biological image sequences using algorithmic information theory
AU - Cohen, Andrew R.
AU - Bjornsson, Christopher S.
AU - Temple, Sally
AU - Banker, Gary
AU - Roysam, Badrinath
N1 - Funding Information:
This work was performed while A. Cohen was with the Department of Electrical, Computer and Systems Engineering, at the Rensselaer Polytechnic Institute. A preliminary version of this work appeared as a part of a conference proceeding [65]. Various portions of this research were supported by the Center for Subsurface Sensing and Imaging Systems under the Engineering Research Centers Program of the US National Science Foundation (EEC-9986821) and by Rensselaer Polytechnic Institute. The authors would like to thank Dr. William Shain at the Wadsworth Center and Dr. S.J. Kim at Seoul National University for the neuroprosthetics data, Yousef Al-Kofahi and Omar Al-Kofahi for help with tracking data, Susan Goderie for her help with the imaging of neural progenitor cells and advice, Dr. Stefanie Kaech at Oregon Health and Sciences University for time-lapse neuronal data, Hussein Sharafeddin for suggestions on the display of ATG, and Professor Richard Radke for insightful comments on the role of quantization in algorithmic information theory and automatic feature selection.
PY - 2009
Y1 - 2009
N2 - An algorithmic information-theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG). Time courses of object states are compared using an adaptive information distance measure, aided by a closed-form multidimensional quantization. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. The summary is the clustering result and feature subset that maximize the gap statistic. This approach was validated on four bioimaging applications: 1) It was applied to a synthetic data set containing two populations of cells differing in the rate of growth, for which it correctly identified the two populations and the single feature out of 23 that separated them; 2) it was applied to 59 movies of three types of neuroprosthetic devices being inserted in the brain tissue at three speeds each, for which it correctly identified insertion speed as the primary factor affecting tissue strain; 3) when applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain; and 4) when analyzing intracellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification.
AB - An algorithmic information-theoretic method is presented for object-level summarization of meaningful changes in image sequences. Object extraction and tracking data are represented as an attributed tracking graph (ATG). Time courses of object states are compared using an adaptive information distance measure, aided by a closed-form multidimensional quantization. The notion of meaningful summarization is captured by using the gap statistic to estimate the randomness deficiency from algorithmic statistics. The summary is the clustering result and feature subset that maximize the gap statistic. This approach was validated on four bioimaging applications: 1) It was applied to a synthetic data set containing two populations of cells differing in the rate of growth, for which it correctly identified the two populations and the single feature out of 23 that separated them; 2) it was applied to 59 movies of three types of neuroprosthetic devices being inserted in the brain tissue at three speeds each, for which it correctly identified insertion speed as the primary factor affecting tissue strain; 3) when applied to movies of cultured neural progenitor cells, it correctly distinguished neurons from progenitors without requiring the use of a fixative stain; and 4) when analyzing intracellular molecular transport in cultured neurons undergoing axon specification, it automatically confirmed the role of kinesins in axon specification.
KW - Algorithmic information theory
KW - Algorithmic statistics
KW - Clustering distance
KW - Image sequence analysis
UR - http://www.scopus.com/inward/record.url?scp=67650438358&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=67650438358&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2008.162
DO - 10.1109/TPAMI.2008.162
M3 - Article
C2 - 19542574
AN - SCOPUS:67650438358
SN - 0162-8828
VL - 31
SP - 1386
EP - 1403
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 8
ER -