An efficient computational framework for the analysis of whole slide images: Application to follicular lymphoma immunohistochemistry

Follicular Lymphoma (FL) is one of the most common non-Hodgkin Lymphoma in the United States. Diagnosis and grading of FL is based on the review of histopathological tissue sections under a microscope and is influenced by human factors such as fatigue and reader bias. Computer-aided image analysis tools can help improve the accuracy of diagnosis and grading and act as another tool at the pathologist's disposal. Our group has been developing algorithms for identifying follicles in immunohistochemical images. These algorithms have been tested and validated on small images extracted from whole slide images. However, the use of these algorithms for analyzing the entire whole slide image requires significant changes to the processing methodology since the images are relatively large (on the order of 100k × 100k pixels). In this paper we discuss the challenges involved in analyzing whole slide images and propose potential computational methodologies for addressing these challenges. We discuss the use of parallel computing tools on commodity clusters and compare performance of the serial and parallel implementations of our approach.

[1]  B. Nathwani,et al.  A clinical evaluation of the International Lymphoma Study Group Classification of non-Hodgkin's lymphoma: a report of the Non-Hodgkin's Lymphoma Classification Project , 1997 .

[2]  Christophe Lenglet,et al.  ODF reconstruction in q-ball imaging with solid angle consideration , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[3]  Luc Vincent,et al.  Morphological grayscale reconstruction in image analysis: applications and efficient algorithms , 1993, IEEE Trans. Image Process..

[4]  M. M. Maza.  Proceedings of the 2007 international workshop on Parallel symbolic computation , 2007, ISSAC 2007.

[5]  Kim L. Boyer,et al.  Computer-aided evaluation of neuroblastoma on whole-slide histology images: Classifying grade of neuroblastic differentiation , 2009, Pattern Recognit..

[6]  Jeremy Kepner,et al.  'pMATLAB Parallel MATLAB Library' , 2007, Int. J. High Perform. Comput. Appl..

[7]  Sudhakar Yalamanchili.  High performance computing for engineering applications , 1995 .

[8]  Georg Peters,et al.  Some refinements of rough k-means clustering , 2006, Pattern Recognit..

[9]  Yulei Jiang,et al.  Computer-aided Detection of Prostate Cancer on Tissue Sections , 2009, Applied immunohistochemistry & molecular morphology : AIMM.

[10]  Siddharth Samsi,et al.  Survey of Parallel MATLAB Techniques and Applications to Signal and Image Processing , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[11]  Metin Nafi Gürcan,et al.  Detection of Follicles From IHC-Stained Slides of Follicular Lymphoma Using Iterative Watershed , 2010, IEEE Transactions on Biomedical Engineering.

[12]  B N Nathwani,et al.  Subclassification of follicular lymphomas by computerized microscopy. , 1987, Human pathology.

[13]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Jason Duell,et al.  Productivity and performance using partitioned global address space languages , 2007, PASCO '07.

[15]  Vijay Gadepally,et al.  MATLAB for Signal Processing on Multiprocessors and Multicores , 2010, IEEE Signal Processing Magazine.

[16]  George Lee,et al.  Computer-aided prognosis: Predicting patient and disease outcome via multi-modal image analysis , 2010, 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[17]  Heang-Ping Chan,et al.  Computer-aided detection of breast cancer. , 2004, Radiology.

[18]  Joel H. Saltz,et al.  Stroma classification for neuroblastoma on graphics processors , 2009, Int. J. Data Min. Bioinform..

[19]  Anna Korzynska,et al.  Segmentation of Stained Lymphoma Tissue Section Images , 2010 .

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

[21]  Joel H. Saltz,et al.  Histopathological Image Analysis Using Model-Based Intermediate Representations and Color Texture: Follicular Lymphoma Grading , 2009, J. Signal Process. Syst..

[22]  G. Pinkus,et al.  Cell proliferation in non-Hodgkin's lymphomas. Digital image analysis of Ki-67 antibody staining. , 1989, The American journal of pathology.

[23]  Constantine Katsinis,et al.  Automated identification of microstructures on histology slides , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[24]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[25]  Xiuzhen Huang,et al.  K-Means Clustering Algorithms: Implementation and Comparison , 2007, Second International Multi-Symposiums on Computer and Computational Sciences (IMSCCS 2007).

[26]  Jun Kong,et al.  Efficient processing of pathological images using the grid: computer-aided prognosis of neuroblastoma , 2007, CLADE '07.

[27]  Meichun Hsu,et al.  Clustering billions of data points using GPUs , 2009, UCHPC-MAW '09.

[28]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[29]  Constantinos S. Pattichis,et al.  Computer-aided detection of breast cancer nuclei , 1997, IEEE Transactions on Information Technology in Biomedicine.

[30]  Alan Edelman,et al.  Parallel MATLAB: Doing it Right , 2005, Proceedings of the IEEE.

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

[32]  Jun Kong,et al.  Computerized microscopic image analysis of follicular lymphoma , 2008, SPIE Medical Imaging.

[33]  Jun Kong,et al.  Computerized Pathological Image Analysis For Neuroblastoma Prognosis , 2007, AMIA.

[34]  Kendall Preston,et al.  Continuous class pattern recognition for pathology, with applications to non-hodgkin's follicular lymphomas , 1996, Pattern Recognit..

[35]  A. Krishnamurthy,et al.  Developing a Computational Science IDE for HPC Systems , 2007, Third International Workshop on Software Engineering for High Performance Computing Applications (SE-HPC '07).

[36]  Forum Mpi.  MPI: A Message-Passing Interface , 1994 .

[37]  Nittaya Kerdprasop,et al.  Parallelization of K-means clustering on multi-core processors , 2010 .

[38]  Anant Madabhushi,et al.  Automated gland and nuclei segmentation for grading of prostate and breast cancer histopathology , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[39]  Anders Hast,et al.  Proceedings of the combined workshops on UnConventional high performance computing workshop plus memory access workshop , 2009 .

[40]  Michael Granitzer,et al.  Accelerating K-Means on the Graphics Processor via CUDA , 2009, 2009 First International Conference on Intensive Applications and Services.

[41]  D. Hossfeld.  E.S. Jaffe, N.L. Harris, H. Stein, J.W. Vardiman (eds). World Health Organization Classification of Tumours: Pathology and Genetics of Tumours of Haematopoietic and Lymphoid Tissues , 2002 .

[42]  Gaurav Sharma,et al.  MATLAB®: A Language for Parallel Computing , 2009, International Journal of Parallel Programming.

[43]  Nikhil Garge,et al.  ParaKMeans: Implementation of a parallelized K-means algorithm suitable for general laboratory use , 2008, BMC Bioinformatics.

[44]  Junshui Ma,et al.  Improved Prediction of Prostate Cancer Recurrence Based on an Automated Tissue Image Analysis System , 2004 .

[45]  Kilian Stoffel,et al.  Parallel k/h-Means Clustering for Large Data Sets , 1999, Euro-Par.