Statistical approaches to Raman imaging: principal component score mapping

In this research, Raman imaging was employed to map various samples, and the resulting data were analyzed using a suite of automated tools to extract critical information, including intensity and signal-to-noise ratio. The acquired spectra were further processed to identify similarities and investigate patterns using principal component analysis. The objective of this study was to establish guidelines for investigating Raman imaging results, particularly when dealing with large datasets comprising thousands of relatively low-intensity spectra. The overall quality of the results was assessed, and representative locations were determined based on the main Raman bands. While automated software solutions are insufficient for removing baselines and fitting the data, statistical analysis proved to be a powerful tool for extracting valuable information directly from the raw spectral data. This approach enables the extraction of as much information as possible from large arrays of spectral data, even in complex cases where automated software may fall short. The findings of this study contribute to enhancing the analysis and interpretation of Raman imaging results, providing researchers with a robust methodology for extracting meaningful insights from complex datasets, reducing the amount of effort required during data interpretation and analysis.

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

Nondestructive detection methods, based on vibrational spectroscopy, are vitally important in a wide range of applications including industrial chemistry, pharmacy and national defense. Recently, deep learning has been introduced into vibrational spectroscopy showing great potential. Different from images, text, etc. that offer large labeled data sets, vibrational spectroscopic data is very limited, which requires novel concepts beyond transfer and meta learning. To tackle this, we propose a task-enhanced augmentation network (TeaNet). The key component of TeaNet is a reconstruction module that inputs randomly masked spectra and outputs reconstructed samples that are similar to the original ones, but include additional variations learned from the domain. These augmented samples are used to train the classification model. The reconstruction and prediction parts are trained simultaneously, end-to-end with back-propagation. Results on both synthetic and real-world datasets verified the superiority of the proposed method. In the most difficult synthetic scenarios TeaNet outperformed CNN by 17%. We visualized and analysed the neuron responses of TeaNet and CNN, and found that TeaNet's ability to identify discriminant wavenumbers was excellent compared to CNN. Our approach is general and can be easily adapted to other domains, offering a solution to more accurate and interpretable few-shot learning.

Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms

Introduction

Oral cancer, a predominant malignancy in developing nations, represents a global health challenge with a five-year survival rate below 50%. Nonetheless, substantial reductions in both its incidence and mortality rates can be achieved through early detection and appropriate treatment. Crucial to these treatment plans and prognosis predictions is the identification of the pathological type of oral cancer.

Methods

Toward this end, fiber-optic Raman spectroscopy emerges as an effective tool. This study combines Raman spectroscopy technology with deep learning algorithms to develop a portable intelligent prototype for oral case analysis. We propose, for the first time, a multi-task network (MTN) Raman spectroscopy classification model that utilizes a shared backbone network to simultaneously achieve different clinical staging and histological grading diagnoses.

Results

The developed model demonstrated accuracy rates of 94.88%, 94.57%, and 94.34% for tumor staging, lymph node staging, and histological grading, respectively. Its sensitivity, specificity, and accuracy compare closely with the gold standard: routine histopathological examination.

Discussion

Thus, this prototype proposed in this study has great potential for rapid, non-invasive, and label-free pathological diagnosis of oral cancer.

High wavenumber Raman spectroscopy for intraoperative assessment of breast tumour margins

Optimal oncological results and patient outcomes are achieved in surgery for early breast cancer with breast conserving surgery (BCS) where this is appropriate. A limitation of BCS occurs when cancer is present at, or close, to the resection margin - termed a 'positive' margin - and re-excision is recommended to reduce recurrence rate. This is occurs in 17% of BCS in the UK and there is therefore a critical need for a way to assess margin status intraoperatively to ensure complete excision with adequate margins at the first operation. This study presents the potential of high wavenumber (HWN) Raman spectroscopy to address this. Freshly excised specimens from thirty patients undergoing surgery for breast cancer were measured using a surface Raman probe, and a multivariate classification model to predict normal versus tumour was developed from the data. This model achieved 77.1% sensitivity and 90.8% specificity following leave one patient out cross validation, with the defining features being differences in water content and lipid versus protein content. This demonstrates the feasibility of HWN Raman spectroscopy to facilitate future intraoperative margin assessment at specific locations. Clinical utility of the approach will require further research.

Rapid Identification of Pathogens Causing Bloodstream Infections by Raman Spectroscopy and Raman Tweezers

The search for the "Holy Grail" in clinical diagnostic microbiology-a reliable, accurate, low-cost, real-time, easy-to-use method-has brought up several methods with the potential to meet these criteria. One is Raman spectroscopy, an optical, nondestructive method based on the inelastic scattering of monochromatic light. The current study focuses on the possible use of Raman spectroscopy for identifying microbes causing severe, often life-threatening bloodstream infections. We included 305 microbial strains of 28 species acting as causative agents of bloodstream infections. Raman spectroscopy identified the strains from grown colonies, with 2.8% and 7% incorrectly identified strains using the support vector machine algorithm based on centered and uncentred principal-component analyses, respectively. We combined Raman spectroscopy with optical tweezers to speed up the process and captured and analyzed microbes directly from spiked human serum. The pilot study suggests that it is possible to capture individual microbial cells from human serum and characterize them by Raman spectroscopy with notable differences among different species. IMPORTANCE Bloodstream infections are among the most common causes of hospitalizations and are often life-threatening. To establish an effective therapy for a patient, the timely identification of the causative agent and characterization of its antimicrobial susceptibility and resistance profiles are essential. Therefore, our multidisciplinary team of microbiologists and physicists presents a method that reliably, rapidly, and inexpensively identifies pathogens causing bloodstream infections-Raman spectroscopy. We believe that it might become a valuable diagnostic tool in the future. Combined with optical trapping, it offers a new approach where the microorganisms are individually trapped in a noncontact way by optical tweezers and investigated by Raman spectroscopy directly in a liquid sample. Together with the automatic processing of measured Raman spectra and comparison with a database of microorganisms, it makes the whole identification process almost real time.

Ultrafast Early Warning of Heart Attacks through Plasmon-Enhanced Raman Spectroscopy using Collapsible Nanofingers and Machine Learning

As the leading cause of death, heart attacks result in millions of deaths annually, with no end in sight. Early intervention is the only strategy for rescuing lives threatened by heart disease. However, the detection time of the fastest heart-attack detection system is >15 min, which is too long considering the rapid passage of life. In this study, a machine learning (ML)-driven system with a simple process, low-cost, short detection time (only 10 s), and high precision is developed. By utilizing a functionalized nanofinger structure, even a trace amount of biomarker leaked before a heart attack can be captured. Additionally, enhanced Raman profiles are constructed for predictive analytics. Five ML models are developed to harness the useful characteristics of each Raman spectrum and provide early warnings of heart attacks with >98% accuracy. Through the strategic combination of nanofingers and ML algorithms, the proposed warning system accurately provides alerts on silent heart-attack attempts seconds ahead of actual attacks.

Serum Raman spectroscopy combined with multiple classification models for rapid diagnosis of breast cancer

Breast cancer is a malignant tumor with the highest incidence rate in women. Current diagnostic methods are time-consuming, costly, and dependent on physician experience. In this study, we used serum Raman spectroscopy combined with multiple classification algorithms to implement an auxiliary diagnosis method for breast cancer, which will help in the early diagnosis of breast cancer patients. We analyzed the serum Raman spectra of 171 invasive ductal carcinoma (IDC) and 100 healthy volunteers; The analysis showed differences in nucleic acids, carotenoids, amino acids, and lipid concentrations in their blood. These differences provide a theoretical basis for this experiment. First, we used adaptive iteratively reweighted penalized least squares (airPLS) and Savitzky-Golay (SG) for baseline correction and smoothing denoising to remove the effect of noise on the experiment. Then, the Principal component analysis (PCA) algorithm was used to extract features. Finally, we built four classification models: support vector machine (SVM), decision tree (DT), linear discriminant analysis (LDA), and Neural Network Language Model (NNLM). The LDA, SVM, and NNLM achieve 100% accuracy. As supplementary, we added the classification experiment of the raw data. By comparing the experimental results of the two groups, We concluded that the NNLM was the best model. The results show the reliability of the combination of serum Raman spectroscopy and classification models under large sample conditions.

Diagnosis accuracy of Raman spectroscopy in the diagnosis of breast cancer: a meta-analysis

To investigate the diagnostic efficiency of Raman spectroscopy for the diagnosis of breast cancer, we searched PubMed, Web of Science, Cochrane Library, and Embase for articles published from the database establishment to May 20, 2022. Pooled sensitivity, specificity, diagnostic odds ratio, and area under the receiver pooled operating characteristic curve were derived for the included studies as outcome measures. The methodological quality was assessed according to the questionnaires and criteria suggested by the Diagnostic Accuracy Research Quality Assessment-2 tool. Sixteen studies were included in this meta-analysis. The pooled sensitivity and specificity of Raman spectroscopy for breast cancer diagnosis were 0.97 (95% CI, [0.92-0.99]) and 0.96 (95% CI, [0.91-0.98]). The diagnostic odds ratio was 720.89 (95% CI, [135.73-3828.88]) and the area under the curve of summary receiver operating characteristic curves was 0.99 (95% CI, [0.98-1]). Subgroup analysis revealed that all subgroup types in our analysis, including different races, sample types, diagnostic algorithms, number of spectra, instrument types, and laser wavelengths, turned out to have a sensitivity and specificity greater than 0.9. Significant heterogeneity was found between studies. Deeks' funnel plot demonstrated that publication bias was acceptable. This meta-analysis suggests that Raman spectroscopy may be an effective and accurate tool to differentiate breast cancer from normal breast tissue, which will help us diagnose and treat breast cancer.

Raman spectroscopy-a tool for rapid differentiation among microbes causing urinary tract infections

Urinary tract infections belong to the most common infections in the world. Besides community-acquired infections, nosocomial infections pose a high risk especially for patients having indwelling catheters, undergoing urological surgeries or staying at hospital for prolonged time. They can be often complicated by antimicrobial resistance and/or biofilm formation. Therefore, a rapid diagnostic tool enabling timely identification of a causative agent and its susceptibility to antimicrobials is a need. Raman spectroscopy appears to be a suitable method that allows rapid differentiation among microbes and provides a space for further analyses, such as determination of capability of biofilm formation or antimicrobial susceptibility/resistance in tested strains. Our work here presents a possibility to differ among most common microbes causing urinary tract infections (belonging to 20 species). We tested 254 strains directly from colonies grown on Mueller-Hinton agar plates. The results show that it is possible to distinguish among the tested species using Raman spectroscopy, which proves its great potential for future use in clinical diagnostics. Moreover, we present here a pilot study of a real-time analysis and identification (in less than 10 min) of single microbial cells directly in urine employing optical tweezers combined with Raman spectroscopy.

Intraoperative pathologically-calibrated diagnosis of lymph nodes involved by breast cancer cells based on electrical impedance spectroscopy; a prospective diagnostic human model study

BACKGROUND

Nodal status evaluation is a crucial step in determining prognostic factors and managing treatment strategies for breast cancer patients. Preoperative (CNB), intraoperative (SLNB), and even postoperative techniques (Formalin-Fixed Paraffin-Embedded sectioning, FFPE) have definite limitations of precision or sometimes are time-consuming for the result declaration. The primary purpose of this prospective study is to provide a precise complementary system for distinguishing lymph nodes (LNs) involved by cancerous cells in breast cancer patients intraoperatively.

METHODS

The proposed system, Electrical Lymph Scoring(ELS), is designed based on the dielectric properties of the under-test LNs. The system has a needle-shaped 2-electrode probe entered into SLNs or ALNs dissected from patients through standard surgical guidelines. Impedance magnitude in f = 1 kH (Z_1kHz) and Impedance Phase Slope in frequency ranges of 100 kHz-500 kHz (IPS) were then extracted from the impedance spectroscopy data in a cohort study of 77 breast cancer patients(totally 282 dissected LNs) who had been undergone surgery before (n = 55) or after (n = 22) chemical therapies (non-neoadjuvant or neoadjuvant chemotherapy). A new admittance parameter(Y_n^') also proposed for LN detection in neoadjuvant chemotherapy patients.

RESULTS

Considering the permanent pathology result as the gold standard checked by two independent expert pathologists, a significant correlation was observed between the presence of cancerous cells in LNs and individual ranges of the ELS electrical responses. Compared with normal LNs containing fatty ambient and immune cells, LNs involved by cancerous clusters would reduce the Z_1kHz and increase the IPS. These changes correlate with fat metabolism by cancer cells due to their Fatty Acid Oxidation (FAO) in LN, which results in different dielectric properties between high and low-fat content of normal and cancerous LNs, respectively.

CONCLUSIONS

By finding the best correlation between our defined impedimetric parameters and pathological states of tested LNs, a real-time intraoperative detection approach was developed for highly-sensitive (92%, P<0.001) diagnosis of involved sentinel or axillary LNs. The impact of real-time intraoperative scoring of SLNs would make a pre-estimation about the necessity of excising further LNs to help the surgeon for less invasive surgery, especially in the absence of frozen-section equipment.

From Raman to SESORRS: moving deeper into cancer detection and treatment monitoring

Raman spectroscopy is a non-invasive technique that allows specific chemical information to be obtained from various types of sample. The detailed molecular information that is present in Raman spectra permits monitoring of biochemical changes that occur in diseases, such as cancer, and can be used for the early detection and diagnosis of the disease, for monitoring treatment, and to distinguish between cancerous and non-cancerous biological samples. Several techniques have been developed to enhance the capabilities of Raman spectroscopy by improving detection sensitivity, reducing imaging times and increasing the potential applicability for in vivo analysis. The different Raman techniques each have their own advantages that can accommodate the alternative detection formats, allowing the techniques to be applied in several ways for the detection and diagnosis of cancer. This feature article discusses the various forms of Raman spectroscopy, how they have been applied for cancer detection, and the adaptation of the techniques towards their use for in vivo cancer detection and in clinical diagnostics. Despite the advances in Raman spectroscopy, the clinical application of the technique is still limited and certain challenges must be overcome to enable clinical translation. We provide an outlook on the future of the techniques in this area and what we believe is required to allow the potential of Raman spectroscopy to be achieved for clinical cancer diagnostics.

RapidEELS: machine learning for denoising and classification in rapid acquisition electron energy loss spectroscopy

Recent advances in detectors for imaging and spectroscopy have afforded in situ, rapid acquisition of hyperspectral data. While electron energy loss spectroscopy (EELS) data acquisition speeds with electron counting are regularly reaching 400 frames per second with near-zero read noise, signal to noise ratio (SNR) remains a challenge owing to fundamental counting statistics. In order to advance understanding of transient materials phenomena during rapid acquisition EELS, trustworthy analysis of noisy spectra must be demonstrated. In this study, we applied machine learning techniques to denoise high frame rate spectra, benchmarking with slower frame rate "ground truths". The results provide a foundation for reliable use of low SNR data acquired in rapid, in-situ spectroscopy experiments. Such a tool-set is a first step toward both automation in microscopy as well as use of these methods to interrogate otherwise poorly understood transformations.

Through-container quantitative analysis of hand sanitizers using spatially offset Raman spectroscopy

The COVID-19 pandemic created an increased demand for hygiene supplies such as hand sanitizers. In response, a large number of new domestic or imported hand sanitizer products entered the US market. Some of these products were later found to be out of specification. Here, to quickly assess the quality of the hand sanitizer products, a quantitative, through-container screening method was developed for rapid and non-destructive screening. Using spatially offset Raman spectroscopy (SORS) and support vector regression (SVR), active ingredients (e.g., type of alcohol) of 173 commercial and in-house products were identified and quantified regardless of the container material or opacity. Alcohol content in hand sanitizer formulations were predicted with high accuracy [Formula: see text] using SVR and [Formula: see text] of the substandard test samples were identified. In sum, a SORS-SVR method was developed and used for testing medical countermeasures used against COVID-19, demonstrating a potential for high-volume testing during public health threats.

Single cell detection using intracellularly-grown-Au-nanoparticle based surface-enhanced Raman scattering spectroscopy for nasopharyngeal cell line classification

The aim of this study was to evaluate the feasibility of applying intracellularly-grown-Au-nanoparticle (IGAuNP)-based surface-enhanced Raman scattering (SERS) technology to classify two types of nasopharyngeal cancer (NPC) cell lines (CNE2 and CNE1). The IGAuNP technology provides excellent delivery efficiency of Au NPs to the cytoplasm and nucleus, thus leading to an extraordinary enhancement of the Raman signals of cells. Compared with normal Raman scattering (NRS) spectra of cells, IGAuNP-based SERS spectra not only have a high signal-to-noise ratio, but also can detect more characteristic Raman peaks, which can be used to explore more differences when comparing the biochemical components of different nasopharyngeal carcinoma cell lines. Based on the linear discriminant analysis (LDA) and support vector machine (SVM) analysis of SERS spectral data, an exciting result with a diagnostic sensitivity of 100%, specificity of 100%, and accuracy of 100%, could be achieved to differentiate CNE2 and CNE1 cells, which is better than the result obtained by NRS spectroscopy. This exploratory study indicated that the SERS technology based on IGAuNPs in conjunction with multivariate statistical analysis methods has great potential in the identification of nasopharyngeal carcinoma cell lines.

A graphical user interface (NWUSA) for Raman spectral processing, analysis and feature recognition

It is a practical necessity for non-professional users to interpret biologically derived Raman spectral information for obtaining accurate and reliable analytical results. An integrated Raman spectral analysis software (NWUSA) was developed for spectral processing, analysis, and feature recognition. It provides a user-friendly graphical interface to perform the following preprocessing tasks: spectral range selection, cosmic ray removal, polynomial fitting based background subtraction, Savitzky-Golay smoothing, area-under-curve normalization, mean-centered procedure, as well as multivariate analysis algorithms including principal component analysis (PCA), linear discriminant analysis, partial least squares-discriminant analysis, support vector machine (SVM), and PCA-SVM. A spectral dataset obtained from two different samples was utilized to evaluate the performance of the developed software, which demonstrated that the analysis software can quickly and accurately achieve functional requirements in spectral data processing and feature recognition. Besides, the open-source software can not only be customized with more novel functional modules to suit the specific needs, but also benefit many Raman based investigations, especially for clinical usages.

Primary study of identification of parathyroid gland based on laser-induced breakdown spectroscopy

The identification and preservation of parathyroid glands (PGs) is a major issue in thyroidectomy. The PG is particularly difficult to distinguish from the surrounding tissues. Accidental damage or removal of the PG may result in temporary or permanent postoperative hypoparathyroidism and hypocalcemia. In this study, a novel method for identification of the PG was proposed based on laser-induced breakdown spectroscopy (LIBS) for the first time. LIBS spectra were collected from the smear samples of PG and non-parathyroid gland (NPG) tissues (thyroid and neck lymph node) of rabbits. The emission lines (related to K, Na, Ca, N, O, CN, C₂, etc.) observed in LIBS spectra were ranked and selected based on the important weight calculated by random forest (RF). Three machine learning algorithms were used as classifiers to distinguish PGs from NPGs. The artificial neural network classifier provided the best classification performance. The results demonstrated that LIBS can be adopted to discriminate between smear samples of PG and NPG, and it has a potential in intra-operative identification of PGs.

Diagnostic spectro-cytology revealing differential recognition of cervical cancer lesions by label-free surface enhanced Raman fingerprints and chemometrics

Herein we have stepped-up on a strategic spectroscopic modality by utilizing label free ultrasensitive surface enhanced Raman scattering (SERS) technique to generate a differential spectral fingerprint for the prediction of normal (NRML), high-grade intraepithelial lesion (HSIL) and cervical squamous cell carcinoma (CSCC) from exfoliated cell samples of cervix. Three different approaches i.e. single-cell, cell-pellet and extracted DNA from oncology clinic as confirmed by Pap test and HPV PCR were employed. Gold nanoparticles as the SERS substrate favored the increment of Raman intensity exhibited signature identity for Amide III/Nucleobases and carotenoid/glycogen respectively for establishing the empirical discrimination. Moreover, all the spectral invention was subjected to chemometrics including Support Vector Machine (SVM) which furnished an average diagnostic accuracy of 94%, 74% and 92% of the three grades. Combined SERS read-out and machine learning technique in field trial promises its potential to reduce the incidence in low resource countries.

Label-free diagnosis for colorectal cancer through coffee ring-assisted surface-enhanced Raman spectroscopy on blood serum

Surface-enhanced Raman spectroscopy (SERS) is garnering considerable attention for the swift diagnosis of pathogens and abnormal biological status, that is, cancers. In this work, a simple, fast and inexpensive optical sensing platform is developed by the design of SERS sampling and data analysis. The pretreatment of spectral measurement employed gold nanoparticle colloid mixing with the serum from patients with colorectal cancer (CRC). The droplet of particle-serum mixture formed coffee-ring-like region at the rim, providing strong and stable SERS profiles. The obtained spectra from cancer patients and healthy volunteers were analyzed by unsupervised principal component analysis (PCA) and supervised machine learning model, such as support-vector machine (SVM), respectively. The results demonstrate that the SVM model provides the superior performance in the classification of CRC diagnosis compared with PCA. In addition, the values of carcinoembryonic antigen from the blood samples were compiled with the corresponding SERS spectra for SVM calculation, yielding improved prediction results.

Implementation of a classification strategy of Raman data collected in different clinical conditions: application to the diagnosis of chronic lymphocytic leukemia

The literature is rich in proof of concept studies demonstrating the potential of Raman spectroscopy for disease diagnosis. However, few studies are conducted in a clinical context to demonstrate its applicability in current clinical practice and workflow. Indeed, this translational research remains far from the patient's bedside for several reasons. First, samples are often cultured cell lines. Second, they are prepared on non-standard substrates for clinical routine. Third, a unique supervised classification model is usually constructed using inadequate cross-validation strategy. Finally, the implemented models maximize classification accuracy without taking into account the clinician's needs. In this paper, we address these issues through a diagnosis problem in real clinical conditions, i.e., the diagnosis of chronic lymphocytic leukemia from fresh unstained blood smears spread on glass slides. From Raman data acquired in different experimental conditions, a repeated double cross-validation strategy was combined with different cross-validation approaches, a consensus label strategy and adaptive thresholds able to adapt to the clinician's needs. Combined with validation at the patient level, classification results were improved compared to traditional strategies.

Raman Spectroscopy for Rapid Evaluation of Surgical Margins during Breast Cancer Lumpectomy

Failure to precisely distinguish malignant from healthy tissue has severe implications for breast cancer surgical outcomes. Clinical prognoses depend on precisely distinguishing healthy from malignant tissue during surgery. Laser Raman spectroscopy (LRS) has been previously shown to differentiate benign from malignant tissue in real time. However, the cost, assembly effort, and technical expertise needed for construction and implementation of the technique have prohibited widespread adoption. Recently, Raman spectrometers have been developed for non-medical uses and have become commercially available and affordable. Here we demonstrate that this current generation of Raman spectrometers can readily identify cancer in breast surgical specimens. We evaluated two commercially available, portable, near-infrared Raman systems operating at excitation wavelengths of either 785 nm or 1064 nm, collecting a total of 164 Raman spectra from cancerous, benign, and transitional regions of resected breast tissue from six patients undergoing mastectomy. The spectra were classified using standard multivariate statistical techniques. We identified a minimal set of spectral bands sufficient to reliably distinguish between healthy and malignant tissue using either the 1064 nm or 785 nm system. Our results indicate that current generation Raman spectrometers can be used as a rapid diagnostic technique distinguishing benign from malignant tissue during surgery.

Identification of ability to form biofilm in Candida parapsilosis and Staphylococcus epidermidis by Raman spectroscopy

Aim: Finding rapid, reliable diagnostic methods is a big challenge in clinical microbiology. Raman spectroscopy is an optical method used for multiple applications in scientific fields including microbiology. This work reports its potential in identifying biofilm positive strains of Candida parapsilosis and Staphylococcus epidermidis. Materials & methods: We tested 54 S. epidermidis strains (23 biofilm positive, 31 negative) and 51 C. parapsilosis strains (27 biofilm positive, 24 negative) from colonies on Mueller-Hinton agar plates, using Raman spectroscopy. Results: The accuracy was 98.9% for C. parapsilosis and 96.1% for S. epidermidis. Conclusion: The method showed great potential for identifying biofilm positive bacterial and yeast strains. We suggest that Raman spectroscopy might become a useful aid in clinical diagnostics.

SVM Optimization for Brain Tumor Identification Using Infrared Spectroscopic Samples

The work presented in this paper is focused on the use of spectroscopy to identify the type of tissue of human brain samples employing support vector machine classifiers. Two different spectrometers were used to acquire infrared spectroscopic signatures in the wavenumber range between 1200⁻3500 cm^-1. An extensive analysis was performed to find the optimal configuration for a support vector machine classifier and determine the most relevant regions of the spectra for this particular application. The results demonstrate that the developed algorithm is robust enough to classify the infrared spectroscopic data of human brain tissue at three different discrimination levels.

Use of Raman spectroscopy to screen diabetes mellitus with machine learning tools

Type 2 diabetes mellitus (DM2) is one of the most widely prevalent diseases worldwide and is currently screened by invasive techniques based on enzymatic assays that measure plasma glucose concentration in a laboratory setting. A promising plan of action for screening DM2 is to identify molecular signatures in a non-invasive fashion. This work describes the application of portable Raman spectroscopy coupled with several supervised machine-learning techniques, to discern between diabetic patients and healthy controls (Ctrl), with a high degree of accuracy. Using artificial neural networks (ANN), we accurately discriminated between DM2 and Ctrl groups with 88.9-90.9% accuracy, depending on the sampling site. In order to compare the ANN performance to more traditional methods used in spectroscopy, principal component analysis (PCA) was carried out. A subset of features from PCA was used to generate a support vector machine (SVM) model, albeit with decreased accuracy (76.0-82.5%). The 10-fold cross-validation model was performed to validate both classifiers. This technique is relatively low-cost, harmless, simple and comfortable for the patient, yielding rapid diagnosis. Furthermore, the performance of the ANN-based method was better than the typical performance of the invasive measurement of capillary blood glucose. These characteristics make our method a promising screening tool for identifying DM2 in a non-invasive and automated fashion.

Analysis of hepatitis B virus infection in blood sera using Raman spectroscopy and machine learning

This study presents the analysis of hepatitis B virus (HBV) infection in human blood serum using Raman spectroscopy combined with pattern recognition technique. In total, 119 confirmed samples of HBV infected sera, collected from Pakistan Atomic Energy Commission (PAEC) general hospital have been used for the current analysis. The differences between normal and HBV infected samples have been evaluated using support vector machine (SVM) algorithm. SVM model with two different kernels i.e. polynomial function and Gaussian radial basis function (RBF) have been investigated for the classification of normal blood sera from HBV infected sera based on Raman spectral features. Furthermore, the performance of the model with each kernel function has also been analyzed with two different implementations of optimization problem i.e. Quadratic programming and least square. 5-fold cross validation method has been used for the evaluation of the model. In the current study, best classification performance has been achieved for polynomial kernel of order-2. A diagnostic accuracy of about 98% with the precision of 97%, sensitivity of 100% and specificity of 95% has been achieved under these conditions.

Environmental metabolomics with data science for investigating ecosystem homeostasis

A natural ecosystem can be viewed as the interconnections between complex metabolic reactions and environments. Humans, a part of these ecosystems, and their activities strongly affect the environments. To account for human effects within ecosystems, understanding what benefits humans receive by facilitating the maintenance of environmental homeostasis is important. This review describes recent applications of several NMR approaches to the evaluation of environmental homeostasis by metabolic profiling and data science. The basic NMR strategy used to evaluate homeostasis using big data collection is similar to that used in human health studies. Sophisticated metabolomic approaches (metabolic profiling) are widely reported in the literature. Further challenges include the analysis of complex macromolecular structures, and of the compositions and interactions of plant biomass, soil humic substances, and aqueous particulate organic matter. To support the study of these topics, we also discuss sample preparation techniques and solid-state NMR approaches. Because NMR approaches can produce a number of data with high reproducibility and inter-institution compatibility, further analysis of such data using machine learning approaches is often worthwhile. We also describe methods for data pretreatment in solid-state NMR and for environmental feature extraction from heterogeneously-measured spectroscopic data by machine learning approaches.

Tuberculosis determination using SERS and chemometric methods

Nanostructures have been multiplying the advantages of Raman spectroscopy and further amplify the advantages of Raman spectroscopy is a continuous effort focused on the appropriate design of nanostructures. Herein, we designed different shapes of plasmonic nanostructures such as Vertical, Zig Zag, Slant nanorods and Spherical nanoparticles employing the DC magnetron sputtering system as SERS-active substrates for ultrasensitive detection of target molecules. The fabricated plasmonic nanostructures sensitivity and uniformity were exploited by reference dye analyte. These nanostructures were utilized in the label free detection of infectious disease, Tuberculosis (TB). For the first time, TB detection from serum samples using SERS has been demonstrated. Various multivariate statistical methods such as principal component analysis, support vector machine, decision tree and random forest were developed and tested their ability to discriminate the healthy and active TB samples. The results demonstrate the performance of the SERS spectra, chemometric methods and potential of the method in clinical diagnosis.

A high-throughput serum Raman spectroscopy platform and methodology for colorectal cancer diagnostics

Translating Raman spectroscopy for colorectal cancer diagnosis with a focus on high-throughput design, inter-user variability and sample handling considerations.

Rapid identification of staphylococci by Raman spectroscopy

Clinical treatment of the infections caused by various staphylococcal species differ depending on the actual cause of infection. Therefore, it is necessary to develop a fast and reliable method for identification of staphylococci. Raman spectroscopy is an optical method used in multiple scientific fields. Recent studies showed that the method has a potential for use in microbiological research, too. Our work here shows a possibility to identify staphylococci by Raman spectroscopy. We present a method that enables almost 100% successful identification of 16 of the clinically most important staphylococcal species directly from bacterial colonies grown on a Mueller-Hinton agar plate. We obtained characteristic Raman spectra of 277 staphylococcal strains belonging to 16 species from a 24-hour culture of each strain grown on the Mueller-Hinton agar plate using the Raman instrument. The results show that it is possible to distinguish among the tested species using Raman spectroscopy and therefore it has a great potential for use in routine clinical diagnostics.

Raman Spectroscopy Combined with Principal Component Analysis for Screening Nasopharyngeal Cancer in Human Blood Sera

This study demonstrates the analysis of nasopharyngeal cancer (NPC) in human blood sera using Raman spectroscopy combined with the multivariate analysis technique. Blood samples of confirmed NPC patients and healthy individuals have been used in this study. The Raman spectra from all these samples were recorded using 785 nm laser for excitation. Important Raman bands at 760, 800, 815, 834, 855, 1003, 1220-1275, and 1524 cm^-1, have been observed in both normal and NPC samples. A decrease in the lipids content, phenylalanine, and β-carotene, whereas increases in amide III, tyrosine, and tryptophan have been observed in the NPC samples. The two data sets were well separated using principal component analysis (PCA) based on Raman spectral data. The spectral variations between the healthy and cancerous samples have been further highlighted by plotting loading vectors PC1 and PC2, which shows only those spectral regions where the differences are obvious.

Detection of Metastatic Breast and Thyroid Cancer in Lymph Nodes by Desorption Electrospray Ionization Mass Spectrometry Imaging

Ambient ionization mass spectrometry has been widely applied to image lipids and metabolites in primary cancer tissues with the purpose of detecting and understanding metabolic changes associated with cancer development and progression. Here, we report the use of desorption electrospray ionization mass spectrometry (DESI-MS) to image metastatic breast and thyroid cancer in human lymph node tissues. Our results show clear alterations in lipid and metabolite distributions detected in the mass spectra profiles from 42 samples of metastatic thyroid tumors, metastatic breast tumors, and normal lymph node tissues. 2D DESI-MS ion images of selected molecular species allowed discrimination and visualization of specific histologic features within tissue sections, including regions of metastatic cancer, adjacent normal lymph node, and fibrosis or adipose tissues, which strongly correlated with pathologic findings. In thyroid cancer metastasis, increased relative abundances of ceramides and glycerophosphoinisitols were observed. In breast cancer metastasis, increased relative abundances of various fatty acids and specific glycerophospholipids were seen. Trends in the alterations in fatty acyl chain composition of lipid species were also observed through detailed mass spectra evaluation and chemical identification of molecular species. The results obtained demonstrate DESI-MSI as a potential clinical tool for the detection of breast and thyroid cancer metastasis in lymph nodes, although further validation is needed. Graphical Abstract Desorption electrospray ionization mass spectrometry imaging is used to differentiate metastatic cancer from adjacent lymph node tissue.

Deep convolutional neural networks for Raman spectrum recognition: a unified solution

Classification of unprocessed Raman spectra using a convolutional neural network.

Rapid and Quantitative Determination of S-Adenosyl-L-Methionine in the Fermentation Process by Surface-Enhanced Raman Scattering

Concentrations of S-Adenosyl-L-Methionine (SAM) in aqueous solution and fermentation liquids were quantitatively determined by surface-enhanced Raman scattering (SERS) and verified by high-pressure liquid chromatography (HPLC). The Ag nanoparticle/silicon nanowire array substrate was fabricated and employed as an active SERS substrate to indirectly measure the SAM concentration. The linear relationship between the integrated intensity of peak centered at ~2920 cm-1 in SERS spectra and the SAM concentration was established, and the limit of detections of SAM concentrations was analyzed to be ~0.1 g/L. The concentration of SAM in real solution could be predicted by the linear relationship and verified by the HPLC detection method. The relative deviations (δ) of the predicted SAM concentration are less than 13% and the correlation coefficient is 0.9998. Rolling-Circle Filter was utilized to subtract fluorescence background and the optimal results were obtained when the radius of the analyzing circle is 650 cm-1.

Analysis of dengue infection based on Raman spectroscopy and support vector machine (SVM)

The current study presents the use of Raman spectroscopy combined with support vector machine (SVM) for the classification of dengue suspected human blood sera. Raman spectra for 84 clinically dengue suspected patients acquired from Holy Family Hospital, Rawalpindi, Pakistan, have been used in this study.The spectral differences between dengue positive and normal sera have been exploited by using effective machine learning techniques. In this regard, SVM models built on the basis of three different kernel functions including Gaussian radial basis function (RBF), polynomial function and linear functionhave been employed to classify the human blood sera based on features obtained from Raman Spectra.The classification model have been evaluated with the 10-fold cross validation method. In the present study, the best performance has been achieved for the polynomial kernel of order 1. A diagnostic accuracy of about 85% with the precision of 90%, sensitivity of 73% and specificity of 93% has been achieved under these conditions.

Diagnosis approach of chronic lymphocytic leukemia on unstained blood smears using Raman microspectroscopy and supervised classification

We have investigated the potential of Raman microspectroscopy combined with supervised classification algorithms to diagnose a blood lymphoproliferative disease, namely chronic lymphocytic leukemia (CLL). This study was conducted directly on human blood smears (27 volunteers and 49 CLL patients) spread on standard glass slides according to a cytological protocol before the staining step. Visible excitation at 532 nm was chosen, instead of near infrared, in order to minimize the glass contribution in the Raman spectra. After Raman measurements, blood smears were stained using the May-Grünwald Giemsa procedure to correlate spectroscopic data classifications with cytological analysis. A first prediction model was built using support vector machines to discriminate between the two main leukocyte subpopulations (lymphocytes and polymorphonuclears) with sensitivity and specificity over 98.5%. The spectral differences between these two classes were associated to higher nucleic acid content in lymphocytes compared to polymorphonuclears. Then, we developed a classification model to discriminate between neoplastic and healthy lymphocyte spectra, with a mean sensitivity and specificity of 88% and 91% respectively. The main molecular differences between healthy and CLL cells were associated with DNA and protein changes. These spectroscopic markers could lead, in the future, to the development of a helpful medical tool for CLL diagnosis.

Characterization and Visualization of Vesicles in the Endo-Lysosomal Pathway with Surface-Enhanced Raman Spectroscopy and Chemometrics

Surface-enhanced Raman spectroscopy (SERS) is an ultrasensitive vibrational fingerprinting technique widely used in analytical and biosensing applications. For intracellular sensing, typically gold nanoparticles (AuNPs) are employed as transducers to enhance the otherwise weak Raman spectroscopy signals. Thus, the signature patterns of the molecular nanoenvironment around intracellular unlabeled AuNPs can be monitored in a reporter-free manner by SERS. The challenge of selectively identifying molecular changes resulting from cellular processes in large and multidimensional data sets and the lack of simple tools for extracting this information has resulted in limited characterization of fundamental cellular processes by SERS. Here, this shortcoming in analysis of SERS data sets is tackled by developing a suitable methodology of reference-based PCA-LDA (principal component analysis-linear discriminant analysis). This method is validated and exemplarily used to extract spectral features characteristic of the endocytic compartment inside cells. The voluntary uptake through vesicular endocytosis is widely used for the internalization of AuNPs into cells, but the characterization of the individual stages of this pathway has not been carried out. Herein, we use reporter-free SERS to identify and visualize the stages of endocytosis of AuNPs in cells and map the molecular changes via the adaptation and advantageous use of chemometric methods in combination with tailored sample preparation. Thus, our study demonstrates the capabilities of reporter-free SERS for intracellular analysis and its ability to provide a way of characterizing intracellular composition. The developed analytical approach is generic and enables the application of reporter-free SERS to identify unknown components in different biological matrices and materials.

Raman spectroscopy for cancer diagnosis: how far have we come?

Raman spectroscopy is increasingly investigated for cancer diagnosis. As the potential of the technique is explored and realized, it is slowly making its way into clinics. There are more reports in recent years showing promise that it can help clinicians for cancer diagnosis. However, a number of challenges remain to be overcome, especially in vivo cancer diagnosis. In this article, the recent progress of the technique toward clinical cancer diagnosis is discussed from a critical perspective.

Application of support vector machine to rapid classification of uranium waste drums using low-resolution γ-ray spectra

We investigated the feasibility of using support vector machine (SVM), a computer learning method, to classify uranium waste drums as natural uranium or reprocessed uranium based on their origins. The method was trained using 12 training datasets were used and tested on 955 datasets of γ-ray spectra obtained with NaI(Tl) scintillation detectors. The results showed that only 4 out of 955 test datasets were different from the original labels-one of them was mislabeled and the other three were misclassified by SVM. These findings suggest that SVM is an effective method to classify a large quantity of data within a short period of time. Consequently, SVM is a feasible method for supporting the scaling factor method and as a supplemental tool to check original labels.

Emerging technology: applications of Raman spectroscopy for prostate cancer

There is a need in prostate cancer diagnostics and research for a label-free imaging methodology that is nondestructive, rapid, objective, and uninfluenced by water. Raman spectroscopy provides a molecular signature, which can be scaled from micron-level regions of interest in cells to macroscopic areas of tissue. It can be used for applications ranging from in vivo or in vitro diagnostics to basic science laboratory testing. This work describes the fundamentals of Raman spectroscopy and complementary techniques including surface enhanced Raman scattering, resonance Raman spectroscopy, coherent anti-Stokes Raman spectroscopy, confocal Raman spectroscopy, stimulated Raman scattering, and spatially offset Raman spectroscopy. Clinical applications of Raman spectroscopy to prostate cancer will be discussed, including screening, biopsy, margin assessment, and monitoring of treatment efficacy. Laboratory applications including cell identification, culture monitoring, therapeutics development, and live imaging of cellular processes are discussed. Potential future avenues of research are described, with emphasis on multiplexing Raman spectroscopy with other modalities.

Spectrometer calibration protocol for Raman spectra recorded with different excitation wavelengths

The combination of Raman spectroscopy with chemometrics has gained significant importance within the last years to address a broad variety of biomedical and life science questions. However, the routine application of chemometric models to analyze Raman spectra recorded with Raman devices different from the device used to establish the model is extremely challenging due to Raman device specific influences on the recorded Raman spectra. Here we report on the influence of different non-resonant excitation wavelengths on Raman spectra and propose a calibration routine, which corrects for the main part of the spectral differences between Raman spectra recorded with different (non-resonant) excitation wavelengths. The calibration routine introduced within this contribution is an improvement to the known 'standard' calibration routines and is a starting point for the development of a calibration protocol to generate spectrometer independent Raman spectra. The presented routine ensures that a chemometric model utilizes only Raman information of the sample and not artifacts from small shifts in the excitation wavelength. This is crucial for the application of Raman-spectroscopy in real-world-settings, such as diagnostics of diseases or identification of bacteria.

Competitive evaluation of data mining algorithms for use in classification of leukocyte subtypes with Raman microspectroscopy

In this study Raman spectral data from peripheral blood mononuclear cells (PBMCs) is used for the competitive evaluation of three data-mining models in discriminating a highly pure population of T-cell lymphocytes from other myeloid cells within the PBMCs fraction.

Exploring type II microcalcifications in benign and premalignant breast lesions by shell-isolated nanoparticle-enhanced Raman spectroscopy (SHINERS)

The characteristics of type II microcalcifications in fibroadenoma (FB), atypical ductal hyperplasia (ADH), and ductal carcinoma in situ (DCIS) breast tissues has been analyzed by the fingerprint features of Raman spectroscopy. Fresh breast tissues were first handled to frozen sections and then they were measured by normal Raman spectroscopy. Due to inherently low sensitivity of Raman scattering, Au@SiO2 shell-isolated nanoparticle-enhanced Raman spectroscopy (SHINERS) technique was utilized. A total number of 71 Raman spectra and 70 SHINERS spectra were obtained from the microcalcifications in benign and premalignant breast tissues. Principal component analysis (PCA) was used to distinguish the type II microcalcifications between these tissues. This is the first time to detect type II microcalcifications in premalignant (ADH and DCIS) breast tissue frozen sections, and also the first time SHINERS has been utilized for breast cancer detection. Conclusions demonstrated in this paper confirm that SHINERS has great potentials to be applied to the identification of breast lesions as an auxiliary method to mammography in the early diagnosis of breast cancer.

Identification and characterization of colorectal cancer using Raman spectroscopy and feature selection techniques

This study aims to detect colorectal cancer with near-infrared Raman spectroscopy and feature selection techniques. A total of 306 Raman spectra of colorectal cancer tissues and normal tissues are acquired from 44 colorectal cancer patients. Five diagnostically important Raman bands in the regions of 815-830, 935-945, 1131-1141, 1447-1457 and 1665-1675 cm(-1) related to proteins, nucleic acids and lipids of tissues are identified with the ant colony optimization (ACO) and support vector machine (SVM). The diagnostic models built with the identified Raman bands provide a diagnostic accuracy of 93.2% for identifying colorectal cancer from normal Raman spectroscopy. The study demonstrates that the Raman spectroscopy associated with ACO-SVM diagnostic algorithms has great potential to characterize and diagnose colorectal cancer.