Personal tools

You are here: Home / Research / Biomedical Image Analysis / Professor Alison Noble / Microscopy Image Analysis

Microscopy Image Analysis

Microscopy image analysis research

Today's cellular microscopy systems are fully digital and generate volumes of data (BigData).  Summarising the useful information content of such images can be very challenging to do manually, both due to the volume of data (time) and the variable quality of typical microscopy data. Thus there is a growing interest from the biology community in working with image analysis experts to develop robust tools to automate tracking and analysis of microscopy image sequences to measure for instance, key spatial and temporal parameters associated with mitosis, cell population statistics of high-throughput screens, in order to develop better understanding biological processes, and to provide tools for clinical decision-making and target discovery.

The Biomedical Image Analysis laboratory (Alison Noble)  in collaboration with the Visual Geometry Group (Andrew Zisserman) and Skoltech (Victor Lempitsky) is developing a programme of research investigating novel applications of machine learning to microscopy image analysis tasks such as counting cells and segmentation. Other work is looking at quantification issues of fluorescent confocal microscopy images and how image analysis can help overcome them.

Microscopy image analysis team: Alison Noble and Andrew Zisserman (PIs), Carlos Arteta, Haiyue Ye, Thomas Nketia.

  • Collaborators: Victor Lempitsky (Skoltech, Russia), Boris Vojnovik and Paul Barber (Oncology), Bass Hassan, Claudia Buehnemann (IMM); Xin Lu (Oxford Ludwig Institute).
  • Funding: EPSRC.

Representative Publications:

C Arteta,  V Lempitsky, JA Noble, A Zisserman
Learning to Detect Partially Overlapping Instances.
Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013). June 25-27, 2013, Portland, USA. To appear.

C Arteta, V Lempitsky, JA Noble, A Zisserman.
Learning Non-overlapping Extremal Regions To Detect Cells
Proceedings of the Medical Imaging and Computer Assisted Interventions (MICCAI), 1-5 October 2012, Nice, France.

G Flaccavento, V Lempitsky, I Pope, PR Barber, A Zisserman, JA Noble, B Vojnovic. Learning to Count Cells: applications to lens-free imaging of large fields.
Proc. International Workshop on Microscopic image analysis with applications in Biology – Heidelberg, 2011.

C Buehnemann, H Yu, S Li, HA Branford White, JA Noble, AB Hassan.
Unbiased digital image based quantification of IGF pathway signaling responses in Ewing’s sarcoma of bone.
Proc. International Workshop on Microscopic image analysis with applications in Biology – Heidelberg, 2011.

S Li, JG Wakefield, JA Noble. 
Automated segmentation and alignment of mitotic nuclei for kymograph visualization.

Proc. IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI), pp 622-625, 30 March-2 April, 2011.

E Santos Filho, JA Noble, M Poli, T Griffiths, G Emerson, and D Wells.A method for semi-automatic grading of human blastocyst microscope images.Human Reproduction. Sept 2012;27(9):2641-8. doi: 10.1093/humrep/des219. Epub 2012 Jun 26.

E. Santos Filho, J. A. Noble, and D. Wells.
A review on automatic analysis of human embryo microscope images.
The Open Biomedical Engineering Journal, 4:170-177, 2010.
 

LMA Beaumont, J Wakefield, JA Noble
Spatio-temporal Bayesian cell population tracking and analysis with lineage contruction
Proceedings of the IEEE International Symposium on Biomedical Imaging 2008.

Flaccavento, G., Folkard, M., Noble, J.A., Prise, K.M., Vojnovic, B.,
Substrate evaluation for a microbeam endstation using unstained cell imaging
Applied Radiation and Isotopes 67 (2009), pp. 460-463.