Classification of Hyperspectral In Vivo Brain Tissue Based on Linear Unmixing

Abstract

Hyperspectral imaging is a multidimensional optical technique with the potential of providing fast and accurate tissue classification. The main challenge is the adequate processing of the multidimensional information usually linked to long processing times and significant computational costs, which require expensive hardware. In this study, we address the problem of tissue classification for intraoperative hyperspectral images of in vivo brain tissue. For this goal, two methodologies are introduced that rely on a blind linear unmixing (BLU) scheme for practical tissue classification. Both methodologies identify the characteristic end-members related to the studied tissue classes by BLU from a training dataset and classify the pixels by a minimum distance approach. The proposed methodologies are compared with a machine learning method based on a supervised support vector machine (SVM) classifier. The methodologies based on BLU achieve speedup factors of ~459× and ~429× compared to the SVM scheme, while keeping constant and even slightly improving the classification performance.

Supervised Machine Learning Methods and Hyperspectral Imaging Techniques Jointly Applied for Brain Cancer Classification

“…However, cameras used in the state of the art present different characteristics to those used in this work. The most notable difference is the number of bands, where, in some articles [ 33 , 42 ], authors used 128 bands; in other works, they used 826 bands [ 43 ], instead of the 25 bands that the proposed snapshot camera captures.…”

“…In addition, some works [ 33 , 42 ] used four classes for classification—normal, tumor, blood vessels and background—while [ 43 ] used three classes: normal, tumor and others. In the proposed work, five classes have been classified, so the accuracy results may be affected.…”

“…Related state-of-the-art HSI cameras feature a greater number of bands. In [ 33 , 42 ], 128 bands are employed, while the number of bands used in [ 43 ] is 826. In contrast, the proposed snapshot camera only captures 25 bands.…”

“…Therefore, based on this metric, the methodology proposed in this work is 3.81 times better than the best one found in the state-of-the-art glioblastoma classification using HSI. In addition, some works [33,42] used four classes for classification-normal, tumor, blood vessels and background-while [43] used three classes: normal, tumor and others. In the proposed work, five classes have been classified, so the accuracy results may be affected.…”

Hyperspectral Imaging Benchmark based on Machine Learning for Intraoperative Brain Tumour Detection

“…We have developed an intraoperative customized HS acquisition system, employed in three data acquisition campaigns, to collect 62 HS images of exposed brain surface from 34 different patients that underwent surgery due to brain cancer or another disease that required surgery. Using this extended database with respect to previous works [30][31][32]39,40 , we have analysed the spectral characteristics of the brain tissue (normal and tumour) and blood vessels, and the different tumour /15 types according to their malignancy grades (G1 to G4) and origin (primary and secondary), performing a statistical analysis between all the medians of each spectral channel when comparing the different classes and tumour grades and origins. Moreover, a robust 5-fold cross-validation approach was used to evaluate eight different processing algorithms, first using only spectral information, and then using both spatial and spectral information following a processing framework that we previously developed 30 .…”