Pathological image compression for big data image analysis: Application to hotspot detection in breast cancer

In this paper, we propose a pathological image compression framework to address the needs of Big Data image analysis in digital pathology. Big Data image analytics require analysis of large databases of high-resolution images using distributed storage and computing resources along with transmission of large amounts of data between the storage and computing nodes that can create a major processing bottleneck. The proposed image compression framework is based on the JPEG2000 Interactive Protocol and aims to minimize the amount of data transfer between the storage and computing nodes as well as to considerably reduce the computational demands of the decompression engine. The proposed framework was integrated into hotspot detection from images of breast biopsies, yielding considerable reduction of data and computing requirements.

[1]  Johannes Gerdes,et al.  Production of a mouse monoclonal antibody reactive with a human nuclear antigen associated with cell proliferation , 1983, International journal of cancer.

[2]  James A. Sethian,et al.  Level Set Methods and Fast Marching Methods: Evolving Interfaces in Computational Geometry, Fluid , 2012 .

[3]  M. Khalid Khan,et al.  Hotspot detection in pancreatic neuroendocrine tumors: density approximation by α-shape maps , 2016, SPIE Medical Imaging.

[4]  M. Khalid Khan,et al.  Entropy based quantification of Ki-67 positive cell images and its evaluation by a reader study , 2013, Medical Imaging.

[5]  Amit Ashok,et al.  Task-specific information for imaging system analysis. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[6]  André Huisman,et al.  Creation of a fully digital pathology slide archive by high-volume tissue slide scanning. , 2010, Human pathology.

[7]  K. Gelmon,et al.  Ki67 in breast cancer: prognostic and predictive potential. , 2010, The Lancet. Oncology.

[8]  Marco Saerens,et al.  Clustering methods applied in the detection of Ki67 hot‐spots in whole tumor slide images: An efficient way to characterize heterogeneous tissue‐based biomarkers , 2012, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[9]  H.H. Barrett,et al.  Model observers for assessment of image quality , 1993, 2002 IEEE Nuclear Science Symposium Conference Record.

[10]  J. Gerdes,et al.  The cell proliferation-associated antigen of antibody Ki-67: a very large, ubiquitous nuclear protein with numerous repeated elements, representing a new kind of cell cycle-maintaining proteins , 1993, The Journal of cell biology.

[11]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2002, The Kluwer International Series in Engineering and Computer Science.

[12]  M. Khalid Khan,et al.  Hot spot detection for breast cancer in Ki-67 stained slides: image dependent filtering approach , 2014, Medical Imaging.

[13]  Xiaoping Zhou,et al.  Perceptual clustering for automatic hotspot detection from Ki‐67‐stained neuroendocrine tumour images , 2014, Journal of microscopy.

[14]  Michael W. Marcellin,et al.  Image compression based on task-specific information , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[15]  Jack Cuzick,et al.  Assessment of Ki67 in breast cancer: recommendations from the International Ki67 in Breast Cancer working group. , 2011, Journal of the National Cancer Institute.

[16]  Touradj Ebrahimi,et al.  The JPEG 2000 still image compression standard , 2001, IEEE Signal Process. Mag..

[17]  C. L. Philip Chen,et al.  Data-intensive applications, challenges, techniques and technologies: A survey on Big Data , 2014, Inf. Sci..