Mapping stain distribution in pathology slides using whole slide imaging

Background: Whole slide imaging (WSI) offers a novel approach to digitize and review pathology slides, but the voluminous data generated by this technology demand new computational methods for image analysis. Materials and Methods: In this study, we report a method that recognizes stains in WSI data and uses kernel density estimator to calculate the stain density across the digitized pathology slides. The validation study was conducted using a rat model of acute cardiac allograft rejection and another rat model of heart ischemia/reperfusion injury. Immunohistochemistry (IHC) was conducted to label ED1 + macrophages in the tissue sections and the stained slides were digitized by a whole slide scanner. The whole slide images were tessellated to enable parallel processing. Pixel-wise stain classification was conducted to classify the IHC stains from those of the background and the density distribution of the identified IHC stains was then calculated by the kernel density estimator. Results: The regression analysis showed a correlation coefficient of 0.8961 between the number of IHC stains counted by our stain recognition algorithm and that by the manual counting, suggesting that our stain recognition algorithm was in good agreement with the manual counting. The density distribution of the IHC stains showed a consistent pattern with those of the cellular magnetic resonance (MR) images that detected macrophages labeled by ultrasmall superparamagnetic iron-oxide or micron-sized iron-oxide particles. Conclusions: Our method provides a new imaging modality to facilitate clinical diagnosis. It also provides a way to validate/correlate cellular MRI data used for tracking immune-cell infiltration in cardiac transplant rejection and cardiac ischemic injury.

[1]  Wei Wang,et al.  Detection and classification of thyroid follicular lesions based on nuclear structure from histopathology images , 2010, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[2]  Borivoj Vojnovic,et al.  An image analysis‐based approach for automated counting of cancer cell nuclei in tissue sections , 2003, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[3]  Drazen Jukic,et al.  Evaluation of 2 whole-slide imaging applications in dermatopathology. , 2008, Human pathology.

[4]  Padraig Cunningham,et al.  Ensemble based system for whole-slide prostate cancer probability mapping using color texture features , 2011, Comput. Medical Imaging Graph..

[5]  Donald S. Williams,et al.  Detection of single mammalian cells by high-resolution magnetic resonance imaging. , 1999, Biophysical journal.

[6]  Kristine A. Erps,et al.  Overview of telepathology, virtual microscopy, and whole slide imaging: prospects for the future. , 2009, Human pathology.

[7]  Todd H. Stokes,et al.  Pathology imaging informatics for quantitative analysis of whole-slide images , 2013, Journal of the American Medical Informatics Association : JAMIA.

[8]  Edward R. Dougherty,et al.  An introduction to morphological image processing , 1992 .

[9]  Robert F Murphy,et al.  Deformation‐based nuclear morphometry: Capturing nuclear shape variation in HeLa cells , 2008, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[10]  Michael D Feldman,et al.  Beyond morphology: whole slide imaging, computer-aided detection, and other techniques. , 2008, Archives of pathology & laboratory medicine.

[11]  José M. F. Moura,et al.  Automatic Detection of Regional Heart Rejection in USPIO-Enhanced MRI , 2008, IEEE Transactions on Medical Imaging.

[12]  Dirk P. Kroese,et al.  Kernel density estimation via diffusion , 2010, 1011.2602.

[13]  A. Huisman,et al.  Automatic Nuclei Segmentation in H&E Stained Breast Cancer Histopathology Images , 2013, PloS one.

[14]  J. Saltz,et al.  Image Analysis for Neuroblastoma Classification: Segmentation of Cell Nuclei , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Laoighse Mulrane,et al.  Automated image analysis in histopathology: a valuable tool in medical diagnostics , 2008, Expert review of molecular diagnostics.

[16]  Metin Nafi Gürcan,et al.  An efficient computational framework for the analysis of whole slide images: Application to follicular lymphoma immunohistochemistry , 2012, J. Comput. Sci..

[17]  G. Kayser,et al.  AI (artificial intelligence) in histopathology--from image analysis to automated diagnosis. , 2010, Folia histochemica et cytobiologica.

[18]  B. Roysam,et al.  Digital Transplantation Pathology: Combining Whole Slide Imaging, Multiplex Staining and Automated Image Analysis , 2012, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[19]  Qing Ye,et al.  In situ labeling of immune cells with iron oxide particles: an approach to detect organ rejection by cellular MRI. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[20]  David C Wilbur,et al.  Ovarian frozen section diagnosis: use of whole-slide imaging shows excellent correlation between virtual slide and original interpretations in a large series of cases. , 2010, Archives of pathology & laboratory medicine.

[21]  M. Rosenblatt.  Remarks on Some Nonparametric Estimates of a Density Function , 1956 .

[22]  Philip S. Yu,et al.  Top 10 algorithms in data mining , 2007, Knowledge and Information Systems.

[23]  Hanan Samet,et al.  A general approach to connected-component labeling for arbitrary image representations , 1992, JACM.

[24]  Mari Mino-Kenudson,et al.  Whole-slide imaging digital pathology as a platform for teleconsultation: a pilot study using paired subspecialist correlations. , 2009, Archives of pathology & laboratory medicine.

[25]  Bartley P. Griffith,et al.  Macrophage Accumulation Associated With Rat Cardiac Allograft Rejection Detected by Magnetic Resonance Imaging With Ultrasmall Superparamagnetic Iron Oxide Particles , 2001, Circulation.

[26]  Yukako Yagi,et al.  Primary histologic diagnosis using automated whole slide imaging: a validation study , 2006, BMC clinical pathology.

[27]  Jun Kong,et al.  Computer-aided prognosis of neuroblastoma on whole-slide images: Classification of stromal development , 2009, Pattern Recognit..

[28]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[29]  Chandan Chakraborty,et al.  Statistical Analysis of Textural Features for Improved Classification of Oral Histopathological Images , 2012, Journal of Medical Systems.