Intrinsic fluorescence spectra of fresh normal and cancerous human breast tissues were measured using two selective excitation wavelengths including 290nm and 340nm. Dual-wavelength excitation may reveal more molecular information than single-wavelength excitation. In the meantime, it is significantly faster than the acquisition of excitation-emission (EEM) matrix. Unsupervised machine learning algorithms principal component analysis (PCA) and non-negative matrix factorization (NMF) were used to reduce the dimensionality of the spectral data. The relative concentrations of the basis spectra retrieved by PCA and NMF were considered features of the samples and used to distinguish normal and malignant tissues. The performances of classification using support vector machine (SVM) based on PCA and NMF features were compared. The classification using spectral data with dual-wavelength excitation was compared with single-wavelength excitation. Classification based on NMF-retrieved components from spectral data with dual-wavelength excitation yielded the best performance.
Native fluorescence spectra play important roles in cancer detection. It is widely acknowledged that the emission spectrum of a tissue is a superposition of spectra of various salient fluorophores. However, component quantification is essentially an ill-posed problem. To address this problem, the native fluorescence spectra of normal human very low (LNCap), moderately metastatic (DU-145), and advanced metastatic (PC-3) cell lines were studied by the selected wavelength of 300 nm to investigate the key fluorescent molecules such as tryptophan, collagen and NADH. The native fluorescence spectra of cancer cell lines at different risk levels were analyzed using various machine learning algorithms for feature detection and develop criteria to separate the three types of cells. Principal component analysis (PCA), nonnegative matrix factorization (NMF), and partial least squares fitting were used separately to reduce dimension, extract features and detect biomolecular alterations reflected in the spectra. The scores corresponding to the basis spectra were used for classification. A linear support vector machine (SVM) was used to classify the spectra of the cells with different metastatic ability. In detection of signals coming from tryptophan and NADH with observed data corrupted by noise and inference, a sufficient statistic can be obtained based on the basis spectra retrieved using nonnegative matrix factorization. This work shows changes of relative contents of tryptophan and NADH obtained from native fluorescence spectroscopy may present potential criteria for detecting cancer cell lines of different metastatic ability.
Worldwide breast cancer incidence has increased by more than twenty percent in the past decade. It is also known that in that time, mortality due to the affliction has increased by fourteen percent. Using optical-based diagnostic techniques, such as Raman spectroscopy, has been explored in order to increase diagnostic accuracy in a more objective way along with significantly decreasing diagnostic wait-times. In this study, Raman spectroscopy with 532-nm excitation was used in order to incite resonance effects to enhance Stokes Raman scattering from unique biomolecular vibrational modes. Seventy-two Raman spectra (41 cancerous, 31 normal) were collected from nine breast tissue samples by performing a ten-spectra average using a 500-ms acquisition time at each acquisition location. The raw spectral data was subsequently prepared for analysis with background correction and normalization. The spectral data in the Raman Shift range of 750- 2000 cm-1 was used for analysis since the detector has highest sensitivity around in this range. The matrix decomposition technique nonnegative matrix factorization (NMF) was then performed on this processed data. The resulting leave-oneout cross-validation using two selective feature components resulted in sensitivity, specificity and accuracy of 92.6%, 100% and 96.0% respectively. The performance of NMF was also compared to that using principal component analysis (PCA), and NMF was shown be to be superior to PCA in this study. This study shows that coupling the resonance Raman spectroscopy technique with subsequent NMF decomposition method shows potential for high characterization accuracy in breast cancer detection.
Food spoilage is mainly caused by microorganisms, such as bacteria. In this study, we measure the autofluorescence in meat samples longitudinally over a week in an attempt to develop a method to rapidly detect meat spoilage using fluorescence spectroscopy. Meat food is a biological tissue, which contains intrinsic fluorophores, such as tryptophan, collagen, nicotinamide adenine dinucleotide (NADH) and flavin adenine dinucleotide (FAD) etc. As meat spoils, it undergoes various morphological and chemical changes. The concentrations of the native fluorophores present in a sample may change. In particular, the changes in NADH and FAD are associated with microbial metabolism, which is the most important process of the bacteria in food spoilage. Such changes may be revealed by fluorescence spectroscopy and used to indicate the status of meat spoilage. Therefore, such native fluorophores may be unique, reliable and nonsubjective indicators for detection of spoiled meat. The results of the study show that the relative concentrations of all above fluorophores change as the meat samples kept in room temperature (~19° C) spoil. The changes become more rapidly after about two days. For the meat samples kept in a freezer (~-12° C), the changes are much less or even unnoticeable over a-week-long storage.
Native fluorescence spectra are acquired from fresh normal and cancerous human prostate tissues. The fluorescence data
are analyzed using a multivariate analysis algorithm such as non-negative matrix factorization. The nonnegative spectral
components are retrieved and attributed to the native fluorophores such as collagen, reduced nicotinamide adenine
dinucleotide (NADH), and flavin adenine dinucleotide (FAD) in tissue. The retrieved weights of the components, e.g.
NADH and FAD are used to estimate the relative concentrations of the native fluorophores and the redox ratio. A
machine learning algorithm such as support vector machine (SVM) is used for classification to distinguish normal and
cancerous tissue samples based on either the relative concentrations of NADH and FAD or the redox ratio alone. The
classification performance is shown based on statistical measures such as sensitivity, specificity, and accuracy, along
with the area under receiver operating characteristic (ROC) curve. A cross validation method such as leave-one-out is
used to evaluate the predictive performance of the SVM classifier to avoid bias due to overfitting.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.