Nerve fibers identification based on molecular hyperspectral imaging technology

• Published in: 2012 IEEE International Conference on Computer Science and Automation Engineering Vol. 3; pp. 15 - 17
• Main Authors: Qingli Li, Yiting Wang, Hongying Liu, Zenggan Chen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2012
• Subjects: biomedical imaging; Biomedical optical imaging; Hyperspectral imaging; Microscopy; Nerve fibers; Optical imaging; spectral angle mapper; spectral imaging
• ISBN: 1467300888; 9781467300889
• DOI: 10.1109/CSAE.2012.6272897

To identify the nerve fibers more effectively, a molecular hyperspectral imaging system is used to capture the molecular hyperpsectral images of nerve sections. This new type of imaging system has the advantage of having no moving parts and the spectra can be scanned at very high speed. Then a spectral angle mapper algorithm for automatic nerve fibers identification is presented. To evaluate the performance of the new method, both the molecular hyperspectral images (before staining) and the traditional microscope image (after staining) were captured and compared. The experiment results demonstrate that the new method can utilizes both spectral and spatial information of nerves and identify the nerve fibers more accurately.