Unsupervised modeling of cell morphology dynamics for time-lapse microscopy

Nat Methods. 2012 May 27;9(7):711-3. doi: 10.1038/nmeth.2046.


Analysis of cellular phenotypes in large imaging data sets conventionally involves supervised statistical methods, which require user-annotated training data. This paper introduces an unsupervised learning method, based on temporally constrained combinatorial clustering, for automatic prediction of cell morphology classes in time-resolved images. We applied the unsupervised method to diverse fluorescent markers and screening data and validated accurate classification of human cell phenotypes, demonstrating fully objective data labeling in image-based systems biology.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Cell Division / physiology*
  • HeLa Cells
  • Humans
  • Image Processing, Computer-Assisted / instrumentation
  • Image Processing, Computer-Assisted / methods*
  • Microscopy, Fluorescence / instrumentation
  • Microscopy, Fluorescence / methods*
  • Models, Biological*
  • Pattern Recognition, Automated / methods*
  • RNA Interference
  • Time-Lapse Imaging / instrumentation
  • Time-Lapse Imaging / methods*