TY - JOUR
T1 - Framework for hyperspectral image processing and quantification for cancer detection during animal tumor surgery
AU - Lu, Guolan
AU - Wang, Dongsheng
AU - Qin, Xulei
AU - Halig, Luma
AU - Muller, Susan
AU - Zhang, Hongzheng
AU - Chen, Amy
AU - Pogue, Brian W.
AU - Chen, Zhuo Georgia
AU - Fei, Baowei
N1 - Publisher Copyright:
© 2015 Society of Photo-Optical Instrumentation Engineers (SPIE).
PY - 2015/12/1
Y1 - 2015/12/1
N2 - Hyperspectral imaging (HSI) is an imaging modality that holds strong potential for rapid cancer detection during image-guided surgery. But the data from HSI often needs to be processed appropriately in order to extract the maximum useful information that differentiates cancer from normal tissue. We proposed a framework for hyperspectral image processing and quantification, which includes a set of steps including image preprocessing, glare removal, feature extraction, and ultimately image classification. The framework has been tested on images from mice with head and neck cancer, using spectra from 450-to 900-nm wavelength. The image analysis computed Fourier coefficients, normalized reflectance, mean, and spectral derivatives for improved accuracy. The experimental results demonstrated the feasibility of the hyperspectral image processing and quantification framework for cancer detection during animal tumor surgery, in a challenging setting where sensitivity can be low due to a modest number of features present, but potential for fast image classification can be high. This HSI approach may have potential application in tumor margin assessment during image-guided surgery, where speed of assessment may be the dominant factor.
AB - Hyperspectral imaging (HSI) is an imaging modality that holds strong potential for rapid cancer detection during image-guided surgery. But the data from HSI often needs to be processed appropriately in order to extract the maximum useful information that differentiates cancer from normal tissue. We proposed a framework for hyperspectral image processing and quantification, which includes a set of steps including image preprocessing, glare removal, feature extraction, and ultimately image classification. The framework has been tested on images from mice with head and neck cancer, using spectra from 450-to 900-nm wavelength. The image analysis computed Fourier coefficients, normalized reflectance, mean, and spectral derivatives for improved accuracy. The experimental results demonstrated the feasibility of the hyperspectral image processing and quantification framework for cancer detection during animal tumor surgery, in a challenging setting where sensitivity can be low due to a modest number of features present, but potential for fast image classification can be high. This HSI approach may have potential application in tumor margin assessment during image-guided surgery, where speed of assessment may be the dominant factor.
KW - cancer surgery
KW - feature extraction
KW - feature selection
KW - glare removal
KW - hyperspectral imaging
KW - image registration
KW - intra-operative cancer detection
KW - mutual information
UR - http://www.scopus.com/inward/record.url?scp=84954162928&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84954162928&partnerID=8YFLogxK
U2 - 10.1117/1.JBO.20.12.126012
DO - 10.1117/1.JBO.20.12.126012
M3 - Article
C2 - 26720879
AN - SCOPUS:84954162928
SN - 1083-3668
VL - 20
JO - Journal of biomedical optics
JF - Journal of biomedical optics
IS - 12
M1 - 126012
ER -