Benchmarking of Image Registration Methods for Differently Stained Histological Slides

Image registration is a common task for many biomedical analysis applications. The present work focuses on the benchmarking of registration methods on differently stained histological slides. This is a challenging task due to the differences in the appearance model, the repetitive texture of the details and the large image size, between other issues. Our benchmarking data is composed of 616 image pairs at two different scales - average image diagonal 2.4k and 5k pixels. We compare eleven fully automatic registration methods covering the widely used similarity measures (and optimization strategies with both linear and elastic transformation). For each method, the best parameter configuration is found and subsequently applied to all the image pairs. The performance of the algorithms is evaluated from several perspectives - the registrations (in)accuracy on manually annotated landmarks, the method robustness and its processing computation time.

[1]  Carlos Ortiz-de-Solorzano,et al.  Consistent and Elastic Registration of Histological Sections Using Vector-Spline Regularization , 2006, CVAMIA.

[2]  Jan Kybic,et al.  Automatic simultaneous segmentation and fast registration of histological images , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[3]  Haiying Liu,et al.  A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations , 2001, MICCAI.

[4]  Johannes E. Schindelin,et al.  TrakEM2 Software for Neural Circuit Reconstruction , 2012, PloS one.

[5]  Oscar Déniz-Suárez,et al.  Multi-stained whole slide image alignment in digital pathology , 2015, Medical Imaging.

[6]  A. Madabhushi,et al.  Histopathological Image Analysis: A Review , 2009, IEEE Reviews in Biomedical Engineering.

[7]  Carlos Ortiz-de-Solorzano,et al.  Registration of multiple stained histological sections , 2013, 2013 IEEE 10th International Symposium on Biomedical Imaging.

[8]  Ben Glocker,et al.  Deformable medical image registration: setting the state of the art with discrete methods. , 2011, Annual review of biomedical engineering.

[9]  M. Miller,et al.  Large Deformation Diffeomorphic Metric Mapping Registration of Reconstructed 3D Histological Section Images and in vivo MR Images , 2009, Front. Hum. Neurosci..

[10]  R. Castillo,et al.  A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets , 2009, Physics in medicine and biology.

[11]  Derek R. Magee,et al.  3D reconstruction of multiple stained histology images , 2013, Journal of pathology informatics.

[12]  Arno Klein,et al.  Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration , 2009, NeuroImage.

[13]  Jean-Christophe Olivo-Marin,et al.  Multi-staining registration of large histology images , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[14]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[15]  Brian B. Avants,et al.  Evaluation of Registration Methods on Thoracic CT: The EMPIRE10 Challenge , 2011, IEEE Transactions on Medical Imaging.

[16]  Sébastien Ourselin,et al.  Fast free-form deformation using graphics processing units , 2010, Comput. Methods Programs Biomed..

[17]  Jan Kybic,et al.  Fast registration of segmented images by normal sampling , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[18]  Gerald Q. Maguire,et al.  Comparison and evaluation of retrospective intermodality brain image registration techniques. , 1997, Journal of computer assisted tomography.

[19]  Nikos Paragios,et al.  Deformable Medical Image Registration: A Survey , 2013, IEEE Transactions on Medical Imaging.

[20]  Ching-Wei Wang,et al.  Robust image registration of biological microscopic images , 2014, Scientific Reports.

[21]  Ying Wei,et al.  Non-rigid image registration evaluation using common evaluation databases , 2009 .

[22]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..

[23]  Simon K. Warfield,et al.  Efficient multi-modal dense field non-rigid registration: alignment of histological and section images , 2005, Medical Image Anal..

[24]  G. Metzger,et al.  Development of Multigene Expression Signature Maps at the Protein Level from Digitized Immunohistochemistry Slides , 2012, PloS one.