Nuclei segmentation and feature extraction for disease stage classification in Glioma histopathology images

Abstract:

In the field of histopathology, many studies on evaluation methods for tissue images have been reported for quantitative analysis. In particular, disease stage evaluation for Glioblastoma multiforme (GBM), which is one of brain tumors and its prognosis is quite worse samples is enormous, and this gives much burden to pathologists because they have to evaluate them manually. In addition, the criteria of evaluation heavily depend on each pathologist’s experience and feelings. Computational pathology using computer vision techniques are required to standardize the disease stage evaluation. In the following works, we evaluate:

  • Different nuclei segmentation methods,

  • The performance of various feature descriptors for disease stage of Glioma and nuclei segmentation.

Disease Stage Classification and Significant of Features [1]

Nuclei Segmentation Methods [2]

(More results coming soon)

References:


[1] K. Fukuma, H. Kawanaka, V. B. S. Prasath, B. J. Aronow, H. Takase. Feature extraction and disease stage classification for glioma histopathology images. IEEE 17th International Conference on e-Health Networking, Applications and Services (Healthcom), Boston, USA. Proc. IEEE, pp. 598-599, Oct 2015.


[2] V. B. S. Prasath, K. Fukuma, B. J. Aronow, H. Kawanaka. Cell nuclei segmentation in glioma histopathology images with color decomposition based active contours. IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM), Washington, DC, USA. Proc. IEEE. pp. 1734-1736, Nov 2015. Poster available at figshare: 10.6084/m9.figshare.1588805


[3] K. Fukuma, V. B. S. Prasath, H. Kawanaka, B. J. Aronow, H. Takase. A study on feature extraction and disease stage classification for glioma pathology images. IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Vancouver, Canada. Proc. IEEE, pp. 2150-2156, Aug 2016.


[4] K. Fukuma, V. B. S. Prasath, H. Kawanaka, B. J. Aronow, H. Takase. A study on nuclei segmentation, feature extraction and disease stage classification for human brain histopathological images. International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES), York, UK, Sep 2016. Procedia Computer Science, 96, pp. 1202-1020, Sep 2016.


In preparation:


Nuclei segmentation and feature extraction for disease stage classification in Glioblastoma Multiforme.


Automatic nuclei segmentation in glioma histopathology with adaptive filtering based entropy thresholding.


Back to research page. Back to the homepage.