Global Strategy of Active Machine Learning for Complex Systems: Embryogenesis Application on Cell Division Detection

The intrinsic complexity of biological systems creates huge amounts of unlabeled experimental data. The exploitation of such data can be achieved by performing active machine learning accompanied by a high-level symbolic expert who defines categories and their best boundaries using as little data as possible. We present a global strategy for designing active machine learning methods suited for the observation and analysis of complex systems, such as embryonic development. We developed a procedure that uses all available knowledge, whether gathered manually or automatically, and is able to readjust when new data is provided. We show that it is a powerful method for the investigation of the morphogenetic features of embryogenesis and specifically mitosis detection. It will make possible to properly reconstruct the in vivo cell morphodynamics, a main challenge of the post-genomic era.

[1]  M V Boland,et al.  Automated recognition of patterns characteristic of subcellular structures in fluorescence microscopy images. , 1998, Cytometry.

[2]  Milan Sonka,et al.  Mitotic cell recognition with hidden Markov models , 2004, Medical Imaging: Image-Guided Procedures.

[3]  Xiaobo Zhou,et al.  Automated segmentation, classification, and tracking of cancer cell nuclei in time-lapse microscopy , 2006, IEEE Transactions on Biomedical Engineering.

[4]  Jacques Demongeot,et al.  Tree Representation for Image Matching and Object Recognition , 1999, DGCI.

[5]  Vladimir Vapnik,et al.  Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics) , 1982 .

[6]  C. Kimmel,et al.  Stages of embryonic development of the zebrafish , 1995, Developmental dynamics : an official publication of the American Association of Anatomists.

[7]  R Malladi,et al.  Subjective surfaces: a method for completing missing boundaries. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Xiaobo Zhou,et al.  High content cellular imaging for drug development , 2006 .

[9]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[10]  Meng Wang,et al.  Context based mixture model for cell phase identification in automated fluorescence microscopy , 2007, BMC Bioinformatics.

[11]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Xiaobo Zhou,et al.  Informatics challenges of high-throughput microscopy , 2006, IEEE Signal Processing Magazine.

[13]  Meng Wang,et al.  Novel cell segmentation and online SVM for cell cycle phase identification in automated microscopy , 2008, Bioinform..

[14]  V. Vapnik Estimation of Dependences Based on Empirical Data , 2006 .

[15]  Scott E. Fraser,et al.  Digitizing life at the level of the cell: high-performance laser-scanning microscopy and image analysis for in toto imaging of development , 2003, Mechanisms of Development.

[16]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[17]  Jacques Demongeot,et al.  Efficient Algorithms to Implement the Confinement Tree , 2000, DGCI.

[18]  Robert F. Murphy,et al.  A graphical model approach to automated classification of protein subcellular location patterns in multi-cell images , 2006, BMC Bioinformatics.

[19]  J. Demongeot,et al.  Understanding Physiological and Degenerative Natural Vision Mechanisms to Define Contrast and Contour Operators , 2009, PloS one.

[20]  Jacques Demongeot,et al.  Tree Representation and Implicit Tree Matching for a Coarse to Fine Image Matching Algorithm , 1999, MICCAI.

[21]  K. Mikula,et al.  Embryogenesis Image Segmentation by the Generalized Subjective Surfaces Method using the Finite Volume Technique , .

[22]  E. Davidson,et al.  Later embryogenesis: regulatory circuitry in morphogenetic fields. , 1993, Development.

[23]  HarroldMary Jean,et al.  Active learning for automatic classification of software behavior , 2004 .

[24]  Xiaobo Zhou,et al.  An Effective System for Optical Microscopy Cell Image Segmentation, Tracking and Cell Phase Identification , 2006, 2006 International Conference on Image Processing.

[25]  Houqiang Li,et al.  Automated segmentation and tracking of cells in time-lapse microscopy using watershed and mean shift , 2005, 2005 International Symposium on Intelligent Signal Processing and Communication Systems.

[26]  F. Veronesi,et al.  Cells tracking in a live zebrafish embryo , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  James M. Rehg,et al.  Active learning for automatic classification of software behavior , 2004, ISSTA '04.

[28]  Ayhan Demiriz,et al.  Semi-Supervised Support Vector Machines , 1998, NIPS.

[29]  J. Sethian,et al.  Subjective surfaces: a geometric model for boundary completion , 2000 .

[30]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[31]  James A. Sethian,et al.  Level Set Methods and Fast Marching Methods: Evolving Interfaces in Computational Geometry, Fluid , 2012 .