The development of new optical methods that enhance imaging capabilities in terms of an improvement of imaging resolution and temporal sampling are examples of developments that often require advanced algorithms. Similar to conventional radiology where one tries to image patients with lower dose CT protocols, we need to find ways to image cells with less light and lower concentrations of fluorescent stains. As we attempt to image more complex biological specimens we also need to find ways to compensate for signal attenuation.
In all of these examples it is necessary to find algorithmic solutions that enhance the capability of existing hardware platforms or enable new imaging protocols. Here we need to make use of the knowledge of the underlying physical system and combine this with state-of-the-art machine learning methods.
Particular Areas of Interest:
- Assessment of image quality
- Quantitative label free imaging
- De-noising methods
- De-convolution methods
- Multi-spectral imaging
- â€¢ M. J. Gerdes, C. J. Sevinsky, A. Sood, S. Adak, M. Bello, A. Can, S. Dinn, R. J. Filkins, M. Larsen, Q. Li, M. C. Montalto, J. Rittscher, J. E. Rothman, Z. Pang, B. D. Sarachan, M. L. Seel, A. Seppo, J. Zhang, and F. Ginty, High-Order Multiplexed Fluorescence Imaging for Quantitative, in Situ Subcellular Analysis of Cancer Tissue, PNAS, 2013 [pubmed]
- C. C. Bilgin, J. Rittscher, B. Filkins, A. Can, Digitally Adjusting Chromogenic Dye Proportions in Pathology Images, Journal of Microscopy, 2011 [pubmed]
- D. Gao, D. Padfield, J. Rittscher, R. McKay, Automated Training Data Generation for Microscopy Focus Classification, International Conference on Medical Image Computing and Computer Assisted Intervention, Beijing, 2010 [pubmed]
- D. Padfield, J. Rittscher, and B. Roysam, Defocus and Low CNR Detection for Cell Tracking Applica- tions, 3rd MICCAI Workshop on Microscopic Image Analysis with Applications in Biology, New York, NY, September, 2008 [miaab]