Vibrational biospectroscopy coupled with multivariate analysis extracts potentially diagnostic features in blood plasma/serum of ovarian cancer patients

Despite numerous advances in "omics" research, early detection of ovarian cancer still remains a challenge. The aim of this study was to determine whether attenuated total reflection Fourier-transform infrared (ATR-FTIR) or Raman spectroscopy could characterise alterations in the biomolecular signatures of human blood plasma/serum obtained from ovarian cancer patients compared to non-cancer controls. Blood samples isolated from ovarian cancer patients (n = 30) and healthy controls (n = 30) were analysed using ATR-FTIR spectroscopy. For comparison, a smaller cohort of samples (n = 8) were analysed using an InVia Renishaw Raman spectrometer. Resultant spectra were pre-processed prior to being inputted into principal component analysis (PCA) and linear discriminant analysis (LDA). Statistically significant differences (P < 0.001) were observed between spectra of ovarian cancer versus control subjects for both biospectroscopy methods. Using a support vector machine classifier for Raman spectra of blood plasma, a diagnostic accuracy of 74% was achieved, while the same classifier showed 93.3% accuracy for IR spectra of blood plasma. These observations suggest that a biospectroscopy approach could be applied to identify spectral alterations associated with the presence of insidious ovarian cancer.

Investigation of noise-induced instabilities in quantitative biological spectroscopy and its implications for noninvasive glucose monitoring

Over the past decade, optical spectroscopy has been employed in combination with multivariate chemometric models to investigate a wide variety of diseases and pathological conditions, primarily due to its excellent chemical specificity and lack of sample preparation requirements. Despite promising results in several proof-of-concept studies, its translation to the clinical setting has often been hindered by inadequate accuracy of the conventional spectroscopic models. To address this issue and the possibility of curved (nonlinear) effects in the relationship between the concentrations of the analyte of interest and the mixture spectra (due to fluctuations in sample and environmental conditions), support vector machine-based least-squares nonlinear regression (LS-SVR) has been recently proposed. In this paper, we investigate the robustness of this methodology to noise-induced instabilities and present an analytical formula for estimating modeling precision as a function of measurement noise and model parameters. This formalism can be readily used to evaluate uncertainty in information extracted from spectroscopic measurements, particularly important for rapid-acquisition biomedical applications. Subsequently, using field data (Raman spectra) acquired from a glucose clamping study on an animal model subject, we perform the first systematic investigation of the relative effect of additive interference components (namely, noise in prediction spectra, calibration spectra, and calibration concentrations) on the prediction error of nonlinear spectroscopic models. Our results show that the LS-SVR method gives more accurate results and is substantially more robust to additive noise when compared with conventional regression methods such as partial least-squares regression (PLS), when careful selection of the LS-SVR model parameters are performed. We anticipate that these results will be useful for uncertainty estimation in similar biomedical applications where the precision of measurements and its response to noise in the data set is as important, if not more so, than the generic accuracy level.

Epithelial-mesenchymal transition biomarkers and support vector machine guided model in preoperatively predicting regional lymph node metastasis for rectal cancer

Background:

Current imaging modalities are inadequate in preoperatively predicting regional lymph node metastasis (RLNM) status in rectal cancer (RC). Here, we designed support vector machine (SVM) model to address this issue by integrating epithelial–mesenchymal-transition (EMT)-related biomarkers along with clinicopathological variables.

Methods:

Using tissue microarrays and immunohistochemistry, the EMT-related biomarkers expression was measured in 193 RC patients. Of which, 74 patients were assigned to the training set to select the robust variables for designing SVM model. The SVM model predictive value was validated in the testing set (119 patients).

Results:

In training set, eight variables, including six EMT-related biomarkers and two clinicopathological variables, were selected to devise SVM model. In testing set, we identified 63 patients with high risk to RLNM and 56 patients with low risk. The sensitivity, specificity and overall accuracy of SVM in predicting RLNM were 68.3%, 81.1% and 72.3%, respectively. Importantly, multivariate logistic regression analysis showed that SVM model was indeed an independent predictor of RLNM status (odds ratio, 11.536; 95% confidence interval, 4.113–32.361; P<0.0001).

Conclusion:

Our SVM-based model displayed moderately strong predictive power in defining the RLNM status in RC patients, providing an important approach to select RLNM high-risk subgroup for neoadjuvant chemoradiotherapy.

Identification of pediatric brain neoplasms using Raman spectroscopy

PURPOSE

Raman spectroscopy can quickly and accurately diagnose tissue in near real-time. This study evaluated the capacity of Raman spectroscopy to diagnose pediatric brain tumors.

EXPERIMENTAL DESIGN

Samples of untreated pediatric medulloblastoma (4 samples and 4 patients), glioma (i.e. astrocytoma, oligodendroglioma, ependymoma, ganglioglioma and other gliomas; 27 samples and 19 patients), and normal brain samples (33 samples and 5 patients) were collected fresh from the operating room or from our frozen tumor bank. Samples were divided and tested using routine pathology and Raman spectroscopy. Twelve Raman spectra were collected per sample. Support vector machine analysis was used to classify spectra using the pathology diagnosis as the gold standard.

RESULTS

Normal brain (321 spectra), glioma (246 spectra) and medulloblastoma (82 spectra) were identified with 96.9, 96.7 and 93.9% accuracy, respectively, when compared with each other. High-grade ependymomas (41 spectra) were differentiated from low-grade ependymomas (25 spectra) with 100% sensitivity and 96.0% specificity. Normal brain tissue was distinguished from low-grade glioma (118 spectra) with 91.5% sensitivity and 97.8% specificity. For these analyses, the tissue-level classification was determined to be 100% accurate.

CONCLUSION

These results suggest Raman spectroscopy can accurately distinguish pediatric brain neoplasms from normal brain tissue, similar tumor types from each other and high-grade from low-grade tumors.

Raman Spectroscopy for Clinical Oncology

Cancer is one of the leading causes of death throughout the world. Advancements in early and improved diagnosis could help prevent a significant number of these deaths. Raman spectroscopy is a vibrational spectroscopic technique which has received considerable attention recently with regards to applications in clinical oncology. Raman spectroscopy has the potential not only to improve diagnosis of cancer but also to advance the treatment of cancer. A number of studies have investigated Raman spectroscopy for its potential to improve diagnosis and treatment of a wide variety of cancers. In this paper the most recent advances in dispersive Raman spectroscopy, which have demonstrated promising leads to real world application for clinical oncology are reviewed. The application of Raman spectroscopy to breast, brain, skin, cervical, gastrointestinal, oral, and lung cancers is reviewed as well as a special focus on the data analysis techniques, which have been employed in the studies.

Infrared spectroscopic imaging of renal tumor tissue

Fourier transform infrared (FTIR) spectroscopic imaging has been used to probe the biochemical composition of human renal tumor tissue and adjacent normal tissue. Freshly resected renal tumor tissue from surgery was prepared as a thin cryosection and examined by FTIR spectroscopic imaging. Tissue types could be discriminated by utilizing a combination of fuzzy k-means cluster analysis and a supervised classification algorithm based on a linear discriminant analysis. The spectral classification is compared and contrasted with the histological stained image. It is further shown that renal tumor cells have spread in adjacent normal tissue. This study demonstrates that FTIR spectroscopic imaging can potentially serve as a fast and objective approach for discrimination of renal tumor tissue from normal tissue and even in the detection of tumor infiltration in adjacent tissue.

Raman spectroscopic grading of astrocytoma tissues: using soft reference information

Gliomas are the most frequent primary brain tumours. During neurosurgical treatment, locating the exact tumour border is often difficult. This study assesses grading of astrocytomas based on Raman spectroscopy for a future application in intra-surgical guidance. Our predictive classification models distinguish the surgically relevant classes "normal tissue" and "low" and "high grade astrocytoma" in Raman maps of moist bulk samples (80 patients) acquired with a fibre-optic probe. We introduce partial class memberships as a strategy to utilize borderline cases for classification. Borderline cases supply the most valuable training and test data for our application. They are (a) examples of the sought boundary and (b) the cases for which new diagnostics are needed. Besides, the number of suitable training samples increases considerably: soft logistic regression (LR) utilizes 85% more spectra and 50% more patients than linear discriminant analysis (LDA). The predictive soft LR models achieve ca. 85, 67 and 84% (normal, low and high grade) sensitivity and specificity. We discuss the different heuristics of LR and LDA in the light of borderline samples. While we focus on prediction, the spectroscopic interpretation of the predictive models agrees with previous descriptive studies. Unsaturated lipids are used to differentiate between normal and tumour tissues, while the total lipid content prominently contributes to the determination of the tumour grade. The high-wavenumber region above 2,800 cm(-1) alone did not allow successful grading. We give a proof of concept for Raman spectroscopic grading of moist astrocytoma tissues and propose to include borderline samples into classifier training and testing.

Raman spectroscopy--a potential new method for the intra-operative assessment of axillary lymph nodes

Sentinel Lymph Node Biopsy has become the standard surgical procedure for the sampling of axillary lymph nodes in breast cancer. Intra-operative node assessment of these nodes would allow definitive axillary surgery to take place immediately with associated benefits for patient management. Our experimental study aims to demonstrate that a Raman spectroscopy probe system could overcome many of the disadvantages of current intra-operative methods. 59 axillary lymph nodes, 43 negative and 16 positive from 58 patients undergoing breast surgery at our district general hospital were mapped using Raman micro-spectroscopy. These maps were then used to model the effect of using a Raman spectroscopic probe by selecting 5 and 10 probe points across the mapped images and evaluating the impact on disease detection. Results demonstrated sensitivities of up to 81% and specificities of up to 97% when differentiating between positive and negative lymph nodes, dependent on the number of probe points included. The results would have concurred with histopathology assessment in 89% and 91% of cases in the 5 and 10 point models respectively. Using Raman spectroscopy in this way could allow lymph node assessment within a time-frame suitable for intra-operative use.

Support vector machine regression (SVR/LS-SVM)--an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data

In this study, we make a general comparison of the accuracy and robustness of five multivariate calibration models: partial least squares (PLS) regression or projection to latent structures, polynomial partial least squares (Poly-PLS) regression, artificial neural networks (ANNs), and two novel techniques based on support vector machines (SVMs) for multivariate data analysis: support vector regression (SVR) and least-squares support vector machines (LS-SVMs). The comparison is based on fourteen (14) different datasets: seven sets of gasoline data (density, benzene content, and fractional composition/boiling points), two sets of ethanol gasoline fuel data (density and ethanol content), one set of diesel fuel data (total sulfur content), three sets of petroleum (crude oil) macromolecules data (weight percentages of asphaltenes, resins, and paraffins), and one set of petroleum resins data (resins content). Vibrational (near-infrared, NIR) spectroscopic data are used to predict the properties and quality coefficients of gasoline, biofuel/biodiesel, diesel fuel, and other samples of interest. The four systems presented here range greatly in composition, properties, strength of intermolecular interactions (e.g., van der Waals forces, H-bonds), colloid structure, and phase behavior. Due to the high diversity of chemical systems studied, general conclusions about SVM regression methods can be made. We try to answer the following question: to what extent can SVM-based techniques replace ANN-based approaches in real-world (industrial/scientific) applications? The results show that both SVR and LS-SVM methods are comparable to ANNs in accuracy. Due to the much higher robustness of the former, the SVM-based approaches are recommended for practical (industrial) application. This has been shown to be especially true for complicated, highly nonlinear objects.

Shortened acquisition protocols for the quantitative assessment of the 2-tissue-compartment model using dynamic PET/CT 18F-FDG studies

(18)F-FDG kinetics are quantified by a 2-tissue-compartment model. The routine use of dynamic PET is limited because of this modality's 1-h acquisition time. We evaluated shortened acquisition protocols up to 0-30 min regarding the accuracy for data analysis with the 2-tissue-compartment model.

METHODS

Full dynamic series for 0-60 min were analyzed using a 2-tissue-compartment model. The time-activity curves and the resulting parameters for the model were stored in a database. Shortened acquisition data were generated from the database using the following time intervals: 0-10, 0-16, 0-20, 0-25, and 0-30 min. Furthermore, the impact of adding a 60-min uptake value to the dynamic series was evaluated. The datasets were analyzed using dedicated software to predict the results of the full dynamic series. The software is based on a modified support vector machines (SVM) algorithm and predicts the compartment parameters of the full dynamic series.

RESULTS

The SVM-based software provides user-independent results and was accurate at predicting the compartment parameters of the full dynamic series. If a squared correlation coefficient of 0.8 (corresponding to 80% explained variance of the data) was used as a limit, a shortened acquisition of 0-16 min was accurate at predicting the 60-min 2-tissue-compartment parameters. If a limit of 0.9 (90% explained variance) was used, a dynamic series of at least 0-20 min together with the 60-min uptake values is required.

CONCLUSION

Shortened acquisition protocols can be used to predict the parameters of the 2-tissue-compartment model. Either a dynamic PET series of 0-16 min or a combination of a dynamic PET/CT series of 0-20 min and a 60-min uptake value is accurate for analysis with a 2-tissue-compartment model.