Signal, image, and data analysis

NIH Biosketch

Modern sensing devices produce a wealth of data about the world we live in, ranging from digital microscopy images of sub-cellular patterns and diagnostic images of tissues, to satellite imagery and detailed telescope images of our universe. Numerous applications in science and technology depend on quantitative information extraction and pattern recognition from datasets that are large in dimension in comparison to the number of samples available. One of the most important (in many cases still unsolved) problems is that of classification, that is of `telling one from another'. Examples include being able to distinguish between benign and malignant tumors from medical images, between 'normal' and 'abnormal' physiological signals, identify people from images of faces or fingerprints, identify biological/chemical threats from resonant spectra etc. The high-dimensional nature of the measurements in relation to the number of samples available often makes these problems challenging. In particular, such problems are typically beyond the human brain's ability to parse. Our laboratory focuses on developing solutions for a variety of signal, image, and data analysis for health science-related and other applications in science and technology. Below you will find a description of several ongoing projects in our laboratory.

Transport-based morphometry of signals and images:

We have developed a new signal transformation framework based on the mathematics of optimal transport and related ideas. Preliminary results have shown that the signal transformation framework can significantly augment the classification performance in detection problems (e.g. cancer detection from histopathology images, face identification, etc) in comparison to state of the art methods. The new signal transformation framework is generative, and thus allows for modeling and visualization of intensity variations in a signal (image) database. The approach can be used to `visualize' any decision (classifier) boundary computed in transform space. It is completely automated, does not require the determination or existance of corresponding landmarks, and consitutes a signal transform with analysis and synthesis operations well defined. Click here for more information.


  • S Kolouri, GK Rohde, Transport-based single frame super resolution of very low resolution face images. IEEE CVPR 2015, accepted.
  • S. Basu, S. Kolouri, GK Rohde, Detecting and visualizing cell phenotype differences from microscopy images using transport-based morphometry. PNAS 111 (9), 3448-3453, 2014. pdf , publisher , software
  • W. Wang, D. Slepcev, J. A. Ozolek, S. Basu, G. K. Rohde, A linear optimal transportation framework for quantifying and visualizing variations in sets of images. International Journal of Computer Vision, vol. 101(2), pp. 254-269, 2013. Journal site , pdf .
  • S. Kolouri, GK Rohde, Quantifying and visualizing variations in sets of images using continuous linear optimal transport. Accepted to SPIE Medical Imaging 2014, San Diego, California, US.

Cancer detection based on cell morphology

We are developing new ways to quantify cell morphology for the purposes of cancer diagnosis and prognosis from histopathology and other imaging modalities. The approach is based on segmenting individual cells (or subcellular structures) for each patient, and comparing the morphology of the segmented structures against the morphology of similar cells in a labaled database. Our approaches are based on the optimal transport framework, described above, and we have shown that cell morphology (imaged using standard approaches) contains enough information for performing accurate diagnosis in a variety of malignancies including liver, thyroid, breast, and lung cancers. In addition, we have shown that the transport-based methods we are developing can significantly outperform traditional descriptive feature based methods which are currently the state of the art. Click here for more information.


  • AB Tosun, A Yergiev, S Kolouri, J Silverman, GK Rohde, Detection of malignant mesothelioma using nuclear structure of mesothelial cells in effusion cytology specimens, Cytometry A, in press, 2014.
  • JA Ozolek, AB Tosun, W Wang, C Chen, S Basu, H Huang, GK Rohde. Accurate diagnosis of thyroid follicular lesions from nuclear morphology using supervised learning. Medical Image Analysis. 18(5), 772-780, 2014. link
  • H Huang, AB Tosun, J Guo, C Chen, W Wang, JA Ozolek, GK Rohde, Cancer diagnosis by nuclear morphometry using spatial information. Pattern Recognition Letters. 42, 115-121, 2014. (pdf)
  • A. B. Tosun, A. Yergiyev, S. Kolouri, J. F. Silverman, G. K. Rohde. Novel computer-aided diagnosis of Mesothelioma using nuclear structure of mesothelial cells in effusion cytology specimens. Accepted to SPIE Medical Imaging 2014, San Diego, California, US.
  • W. Wang, J. A. Ozolek, D. Slepcev, A. B. Lee, C. Chen, G. K. Rohde, An optimal transportation approach for nuclear structure-based pathology, IEEE Transactions on Medical Imaging, 30, pp. 621-631, 2011. (pdf)
  • W. Wang, J. A. Ozolek, G.K. Rohde, Detection and classification of thyroid follicular lesions based on nuclear structure from histopathology images. Cytometry 77A, pp. 485-494, 2010. (reprint)

Image-based cytometry and cell modeling

Modern imaging techniques are able to measure information regarding cellular processes with increasing accuracy, and specificity. Numerous applications in health sciences (drug discovery, genetic screens, diagnosis, prognosis, etc.) can be benefited by image data analysis techniques capable of deriving relevant biological information from such datasets. We are developing new approaches for mining information contained in cell image databases, and utilizing it to model important cellular processes. The approach draws upon our contributions to deformation and transport-based morphometry, as well as other parametric and non parametric extensions. Our efforts are summarized in the CellOrganizer project webpage.


  • S. Basu, S. Kolouri, GK Rohde, Detecting and visualizing cell phenotype differences from microscopy images using transport-based morphometry. Accepted for publication, PNAS, 2014.
  • S. Basu, C. Liu, GK Rohde, Extraction of individual filaments from 2D confocal microscopy images of flat cells. Submitted, 2013.
  • S. Basu, K. N. Dahl, G. K. Rohde, Localizing and extracting filament distributions from microscopy images, Journal of Microscopy, vol. 250(1), pp 57-67, 2013. PMC3638952. web , software .
  • J. Li, A. Shariff, G.K. Rohde, R. F. Murphy, Estimating and comparing microtubule distributions from fluorescence microscopy images of different human cell lines. PLoS ONE 7(11): e50292. doi:10.1371/journal.pone.0050292, 2012. (html)
  • A. Shariff, R. F. Murphy, G. K. Rohde, A generative model of microtubule distributions, and indirect estimation of its parameters from fluorescence microscopy images. Cytometry 77A, pp. 457-466, 2010. (reprint)
  • G.K. Rohde, A.J.S. Ribeiro, K.N. Dahl, R.F. Murphy, Deformation-based nuclear morphometry: Capturing nuclear shape variation in HeLa cells. Cytometry, vol 73A, pp. 341-350, 2008. (pdf)

Automated image segmentation

Before different structures (subcellular organelles, cells, tissues, organs) can be quantified these often must be accurately segmented from a variety of images. We are developing methods for segmenting biomedical structures from image data based on a supervised learning strategy. The idea is to utilize a few sample expert annotated images to automatically train a program to repeat the same task on other images. With our software, a researcher interested in segmenting structures from novel imaging modalities can, with little effort, design a finely tuned segmentation method to automatically segment any quantity of image data. Our method fuses elements related to pixel classification, region optimization, and front evolution methods. The method has been used to segment tissues from histopathology images, nuclei from fluorescence and histopathology images, yeast cells from microscopy images, brain tissues from MRI images, and others. In addition, we are also developing methods for the extraction of linear filaments from microscopy images.


  • C. Cheng, W. Wang, J. A. Ozolek, G. K. Rohde, A flexible and robust approach for segmenting cell nuclei from 2D microscopy images using supervised learning and template matching, Cytometry A, 83(5), pp. 495-507, 2013. Journal site , pdf , software .
  • J. Guo, H. Huang, C. Chen, G.K. Rohde, Optimized nonlinear discriminant analysis (ONDA) for supervised pixel classification, IEEE Sig. Proc. Letters, 30:1155-1158, 2013. (pdf) , supplement
  • S. Basu, C. Liu, GK Rohde, Extraction of individual filaments from 2D confocal microscopy images of flat cells. Submitted, 2013.
  • S. Basu, K. N. Dahl, G. K. Rohde, Localizing and extracting filament distributions from microscopy images, Journal of Microscopy, vol. 250(1), pp 57-67, 2013. PMC3638952. web , software .
  • C. Chen, J. A. Ozolek, W. Wang, G. K. Rohde, A general system for automatic biomedical image segmentation using intensity neighborhoods, International Journal of Biomedical Imaging, Volume 2011, Article ID 606857. (link)
  • C. Chen, J. A. Ozolek, W. Wang, G.K. Rohde, A pixel classification system for segmenting biomedical images intensity neighborhoods and dimension reduction, Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI), 2011, p. 1649-1652. (pdf)

Image registration, motion correction, and interpolation:

We have developed a series of algorithms for image registration for quantitative applications in biomedicine. Our multimodal nonrigid registration methods have been used for template-based image segmentation, population analysis, motion correction, distortion correction, and other applications. The methods work well with multi-modal data, since they are based on mutual information optimization. We have also investigated interpolation artifacts, and their effect on image registration itself, as well as their effect on quantitative estimates produced based on registered data. In the papers below we offer several precautions that may be taken to minimize such artifacts.


  • G.K. Rohde, A. Aldroubi, B.M. Dawant, The adaptive bases algorithm for intensity based nonrigid image registration. Special issue on image registration. IEEE Transactions on Medical Imaging, vol. 22, pp. 1470-1479, 2003. (pdf)
  • G. K. Rohde, A. Aldroubi, D. M. Healy, Jr., Interpolation Artifacts in Sub-Pixel Image Registration. IEEE Transactions on Image Processing 18(2), pp. 333-345, 2009. (preprint)
  • G.K. Rohde, A.S. Barnett, P.J. Basser, C. Pierpaoli, Estimating intensity variance due to noise in registered images: applications to DT-MRI. Neuroimage, vol. 26, pp. 673-684, 2005. (pdf)
  • G.K. Rohde, B.M. Dawant, S.-F Lin, Correction of motion artifact in cardiac optical mapping using image registration. IEEE Transactions on Biomedical Engineering, vol. 52, pp. 338-341, 2005. (pdf)
  • G.K. Rohde, A.S. Barnet, P.J. Basser, S. Marenco, C. Pierpaoli, Comprehensive approach for motion and distortion correction in diffusion weighted MRI. Magnetic Resonance in Medicine, vol. 51, pp. 103-114, 2004. (pdf)
  • G.K. Rohde, D.M. Healy, Jr., C.A. Berenstein, A. Aldroubi, D. Rockmore, Stochastic analysis of geometric image processing using B-splines, Proceedings of IEEE ICASSP, pp. 1017-1020, 2006. (pdf)
  • G.K. Rohde, S. Pajevic, C. Pierpaoli, P.J. Basser. A comprehensive approach for multi-channel image registration. Second International Workshop on Biomedical Image registration (WBIR03), Philadelphia, Pennsylvania. June 2003. Pp. 214-223. (pdf)