Big data in Neurosurgery - Intelligent Support for Brain Tumor Consilium

Karol Kozak, Karol Kozak

2015

Abstract

A brain tumor occurs when abnormal cells form within the brain. Medical imaging plays a central role in the diagnosis of brain tumors. When a brain tumor is diagnosed, a medical team will be formed (consilium) to assess the treatment options presented by the leading surgeon to the patient and his/her family. Using historical evidence-based healthcare data and information directly extracted from images to categorize them may support to increase decision for treatment of patient with brain tumor. Due to its complexity, cancer care is increasingly being dependent on multidisciplinary tumor consilium. That is why it is very important to avoid emotional and quick decisions done by members of consilium. Few studies have investigated how best to organize and run consilium in order to facilitates important decision about patient therapy. We developed and evaluated a multiparametric approach designed to improve the consilium ability to reach treatment decisions. In particular the use of discriminative classification methods such as support vector machines and the use of local brain image meta-data were empirically shown to be important building blocks as support for therapy assign. For efficient classification we used fast SVM classifier with new kernel method.

References

  1. (2011) Digital imaging and communications in medicine (DICOM) part 7: Message exchange. Section 9.1.2. National Electrical Manufacturers Association.
  2. (2011) Digital Imaging and Communications in Medicine (DICOM), Part 5: Data Structures and Encoding, Section 6.2 http://medical.nema.org/ Dicom/ 2011/11_05pu.pdf
  3. Cristianini, N. and J. Shawe-taylor, (2000). An introduction to Support Vector Machines. 200.11/year
  4. Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning. 213. 94
  5. Grauman, K. and Darrell, T. (2005). The pyramid match kernel: Discriminative classification with sets of image features. ICCV, 2.
  6. Kincade, K. (1998). Data mining: digging for healthcare gold. Insurance & Technology, 23(2), IM2-IM7
  7. Lazebnik, L., Schmid, C. and Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR.
  8. Milley, A. (2000). Healthcare and data mining. Health Management Technology, 21(8), 44-47
  9. National Cancer Institute. Definition of Tumor Board Review, (2012).
  10. Cancer http://www.cancer.gov/dictionary?cdrid=322893.
  11. Odone, A., Barla, F. , Verri, A. (2005) Building kernels from binary strings for image matching. IEEE T. Image Processing, 14(2):169-180.
  12. Subhransu, Z. M., Berg, A. C. Malik, J. (2008) Classification using Intersection Kernel Support Vector Machines is Efficient. IEEE Computer Vision and Pattern Recognition.
  13. Vapnik, V.N. (1995). The Nature of Statistical Learning theory, Springer Verlag, New York.
Download


Paper Citation


in Harvard Style

Kozak K. (2015). Big data in Neurosurgery - Intelligent Support for Brain Tumor Consilium . In Proceedings of the Fourth International Conference on Telecommunications and Remote Sensing - Volume 1: ICTRS, ISBN 978-989-758-152-6, pages 69-75. DOI: 10.5220/0005889600690075


in Bibtex Style

@conference{ictrs15,
author={Karol Kozak},
title={Big data in Neurosurgery - Intelligent Support for Brain Tumor Consilium},
booktitle={Proceedings of the Fourth International Conference on Telecommunications and Remote Sensing - Volume 1: ICTRS,},
year={2015},
pages={69-75},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005889600690075},
isbn={978-989-758-152-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Telecommunications and Remote Sensing - Volume 1: ICTRS,
TI - Big data in Neurosurgery - Intelligent Support for Brain Tumor Consilium
SN - 978-989-758-152-6
AU - Kozak K.
PY - 2015
SP - 69
EP - 75
DO - 10.5220/0005889600690075