For a complete list of publications please visit this link.
2019 |
|
Elisabeth J. M. Baltussen; Henricus J. C. M. Sterenborg; Theo J. M. Ruers; Behdad Dashtbozorg Optimizing algorithm development for tissue classification in colorectal cancer based on diffuse reflectance spectra Journal Article Biomed. Opt. Express, 10 (12), pp. 6096–6113, 2019. Abstract | Links | BibTeX | Tags: Diffuse reflectance; Diffuse reflectance spectroscopy; Feature extraction; Hyperspectral imaging; Light scattering; Photon diffusion @article{Baltussen:19, title = {Optimizing algorithm development for tissue classification in colorectal cancer based on diffuse reflectance spectra}, author = {Elisabeth J. M. Baltussen and Henricus J. C. M. Sterenborg and Theo J. M. Ruers and Behdad Dashtbozorg}, url = {http://www.osapublishing.org/boe/abstract.cfm?URI=boe-10-12-6096}, doi = {10.1364/BOE.10.006096}, year = {2019}, date = {2019-12-01}, journal = {Biomed. Opt. Express}, volume = {10}, number = {12}, pages = {6096--6113}, publisher = {OSA}, abstract = {Diffuse reflectance spectroscopy can be used in colorectal cancer surgery for tissue classification. The main challenge in the classification task is to separate healthy colorectal wall from tumor tissue. In this study, four normalization techniques, four feature extraction methods and five classifiers are applied to nine datasets, to obtain the optimal method to separate spectra measured on healthy colorectal wall from spectra measured on tumor tissue. All results are compared to the use of the entire non-normalized spectra. It is found that the most optimal classification approach is to apply a feature extraction method on non-normalized spectra combined with support vector machine or neural network classifier.}, keywords = {Diffuse reflectance; Diffuse reflectance spectroscopy; Feature extraction; Hyperspectral imaging; Light scattering; Photon diffusion}, pubstate = {published}, tppubtype = {article} } Diffuse reflectance spectroscopy can be used in colorectal cancer surgery for tissue classification. The main challenge in the classification task is to separate healthy colorectal wall from tumor tissue. In this study, four normalization techniques, four feature extraction methods and five classifiers are applied to nine datasets, to obtain the optimal method to separate spectra measured on healthy colorectal wall from spectra measured on tumor tissue. All results are compared to the use of the entire non-normalized spectra. It is found that the most optimal classification approach is to apply a feature extraction method on non-normalized spectra combined with support vector machine or neural network classifier. | ![]() |