Discrimination of liver malignancies with 1064 nm dispersive Raman spectroscopy

Abstract

Abstract:Raman spectroscopy has been widely demonstrated for tissue characterization and disease discrimination, however current implementations with either 785 or 830 nm near-infrared (NIR) excitation have been ineffectual in tissues with intense autofluorescence such as the liver. Here we report the use of a dispersive 1064 nm Raman system using a low-noise Indium-Gallium-Arsenide (InGaAs) array to discriminate highly autofluorescent bulk tissue ex vivo specimens from healthy liver, adenocarcinoma, and hepatocellular carcinoma (N = 5 per group). The resulting spectra have been combined with a multivariate discrimination algorithm, sparse multinomial logistic regression (SMLR), to predict class membership of healthy and diseased tissues, and spectral bands selected for robust classification have been extracted. A quantitative metric called feature importance is defined based on classification outputs and is used to guide the association of spectral features with biological indicators of healthy and diseased liver tissue. Spectral bands with high feature importance for healthy and liver tumor specimens include retinol, heme, biliverdin, or quinones (1595 cm −1 ); lactic acid (838 cm −1 ); collagen (873 cm −1 ); and nucleic acids (1485 cm −1 ). Classification performance in both binary (normal versus tumor, 100% sensitivity and 89% specificity) and three-group cases (classification accuracy: normal 89%, adenocarcinoma 74%, hepatocellular carcinoma 64%) indicates the potential for accurately separating healthy and cancerous tissues and suggests implications for utilizing Raman techniques during surgical guidance in liver resection.

Clinical characterization of in vivo inflammatory bowel disease with Raman spectroscopy

“…These average signals exhibit subtle interclass variations that indicate separation across the Raman fingerprint region (450-1800 cm −1 ). Multivariate analysis techniques can be employed for pattern recognition and feature selection to take advantage of the feature rich signals for Raman spectra and IBD [24][25][26]. Fig.…”

“…SMLR is a versatile multiclass iterative algorithm that reduces the high dimensionality of Raman data to only those spectral basis features needed for discrimination [23,24]. SMLR reduces the data set by creating a transformation of the original data in which distinguishing spectral basis features were weighted based on their ability to successfully separate classes of training data.…”

Discrimination of malignant and normal kidney tissue with short wave infrared dispersive Raman spectroscopy

“…SMLR selects distinguishing spectral features that are weighted according to their ability to differentiate classes of training data. The implementation of the training procedure is described in detail in our group's previous work [17]. Validation was performed with a leave-one-specimen-out cross-validation (LOSOCV).…”

“…Recently, short wave infrared (SWIR) dispersive RS systems incorporating a 1064 nm wavelength excitation source in combination with an InGaAs detector array sensitive to wavelengths >1000 nm have demonstrated the ability to collect spectra with a dramatic reduction of background autofluorescence in certain bulk tissue specimens in comparison with conventional 785 nm excitation RS systems . While the inherently higher noise associated with InGaAs arrays results in spectra with lower signal‐to‐noise ratio's in tissues with low autofluorescence, such as the breast , it improves signal fidelity in tissues with high Near Infra‐Red (NIR) autofluorescence such as the liver and pigmented skin lesions .…”

Clinical instrumentation and applications of Raman spectroscopy

“…Partial least squares, a regression-based technique, as well as hybrid linear analysis, have been used to model tissue based on component spectra, finding component contributions for disease detection and extracting accurate concentrations of analytes such as glucose using NIR Raman spectra for transcutaneous blood analysis. 90,91 More complex multivariate and machine learning methods have also been utilized, including support vector machines, 92 logistic regression models, 49,93 genetic algorithms, 82 neural networks, 94 decision trees, 95 optimization techniques, 91 and generalized linear models. These methods allow the integration of non-Gaussian constraints and variable weights to optimize classification performance.…”