Share Email Print
cover

Proceedings Paper

Automatic classification of fluorescence and optical diffusion spectroscopy data in neuro-oncology
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The complexity of the biological tissue spectroscopic analysis due to the overlap of biological molecules’ absorption spectra, multiple scattering effect, as well as measurement geometry in vivo has caused the relevance of this work. In the neurooncology the problem of tumor boundaries delineation is especially acute and requires the development of new methods of intraoperative diagnosis. Methods of optical spectroscopy allow detecting various diagnostically significant parameters non-invasively. 5-ALA induced protoporphyrin IX is frequently used as fluorescent tumor marker in neurooncology. At the same time analysis of the concentration and the oxygenation level of haemoglobin and significant changes of light scattering in tumor tissues have a high diagnostic value. This paper presents an original method for the simultaneous registration of backward diffuse reflectance and fluorescence spectra, which allows defining all the parameters listed above simultaneously. The clinical studies involving 47 patients with intracranial glial tumors of II-IV Grades were carried out in N.N. Burdenko National Medical Research Center of Neurosurgery. To register the spectral dependences the spectroscopic system LESA- 01-BIOSPEC was used with specially developed w-shaped diagnostic fiber optic probe. The original algorithm of combined spectroscopic signal processing was developed. We have created a software and hardware, which allowed (as compared with the methods currently used in neurosurgical practice) to increase the sensitivity of intraoperative demarcation of intracranial tumors from 78% to 96%, specificity of 60% to 82%. The result of analysis of different techniques of automatic classification shows that in our case the most appropriate is the k Nearest Neighbors algorithm with cubic metrics.

Paper Details

Date Published: 12 April 2018
PDF: 7 pages
Proc. SPIE 10582, Laser Florence 2017: Advances in Laser Medicine, 105820E (12 April 2018); doi: 10.1117/12.2315633
Show Author Affiliations
T. A. Savelieva, A.M. Prokhorov General Physics Institute (Russian Federation)
National Research Nuclear Univ. MEPhI (Russian Federation)
V. B. Loshchenov, A.M. Prokhorov General Physics Institute (Russian Federation)
National Research Nuclear Univ. MEPhI (Russian Federation)
S. A. Goryajnov, N.N. Burdenko National Medical Research Ctr. for Neurosurgery (Russian Federation)
A. A. Potapov, N.N. Burdenko National Medical Research Ctr. for Neurosurgery (Russian Federation)


Published in SPIE Proceedings Vol. 10582:
Laser Florence 2017: Advances in Laser Medicine
Leonardo Longo, Editor(s)

© SPIE. Terms of Use
Back to Top