Melanoma Diagnosis by Raman Spectroscopy and Neural Networks: Structure Alterations in Proteins and Lipids in Intact Cancer Tissue

Advancing precision cancer immunotherapy drug development, administration, and response prediction with AI-enabled Raman spectroscopy

Molecular characterization of tumors is essential to identify predictive biomarkers that inform treatment decisions and improve precision immunotherapy development and administration. However, challenges such as the heterogeneity of tumors and patient responses, limited efficacy of current biomarkers, and the predominant reliance on single-omics data, have hindered advances in accurately predicting treatment outcomes. Standard therapy generally applies a "one size fits all" approach, which not only provides ineffective or limited responses, but also an increased risk of off-target toxicities and acceleration of resistance mechanisms or adverse effects. As the development of emerging multi- and spatial-omics platforms continues to evolve, an effective tumor assessment platform providing utility in a clinical setting should i) enable high-throughput and robust screening in a variety of biological matrices, ii) provide in-depth information resolved with single to subcellular precision, and iii) improve accessibility in economical point-of-care settings. In this perspective, we explore the application of label-free Raman spectroscopy as a tumor profiling tool for precision immunotherapy. We examine how Raman spectroscopy's non-invasive, label-free approach can deepen our understanding of intricate inter- and intra-cellular interactions within the tumor-immune microenvironment. Furthermore, we discuss the analytical advances in Raman spectroscopy, highlighting its evolution to be utilized as a single "Raman-omics" approach. Lastly, we highlight the translational potential of Raman for its integration in clinical practice for safe and precise patient-centric immunotherapy.

Optimising Shifted Excitation Raman Difference Spectroscopy (SERDS) for application in highly fluorescent biological samples, using fibre optic probes

Fibre optic probe based Raman spectroscopy can deliver in vivo molecular compositional analysis of a range of diseases. However, some biological tissues exhibit high levels of fluorescence which limit the utility of the technique, particularly when the fluorescence induces CCD etaloning, which can be particulalry hard to remove in subsequent analysis. Furthermore, use of fibre probes can result in silica signals superimposed on the biological Raman signals. Shifted excitation Raman difference spectroscopy (SERDS) utilises a small seperation in excitation wavelengths to remove signals from fluorescence, room lights, optical components and etaloning contributions, while retaining chemical signals from the sample. In this study, we sought to measure the optimum SERDS spectra enabling reconstruction of a range a narrow and broad peaks found in biological samples.  A original wavelength of 830 nm was utilised with 7 different shifts between 0.4 and 3.9 nm to determine which gave the best performance. This range roughly corresponds to the typical range of peak widths within biological Raman spectra at 830 nm excitation; 0.41 - 3.25 nm or 6 - 47 cm-1. An wavelength shift of 2.4 nm was identified as optimal. Finally, a fibre optic Raman probe was used to measure 2 human lymph nodes ex vivo to demonstrate the feasibility of the approach with real-world examples.

Tyndall, Rayleigh, Mei, and Raman scattering: Understanding their role in aesthetics

The role of various light scattering phenomena in aesthetics and clinical practice is explored in this review. Four main types of light scattering, Tyndall, Rayleigh, Mie, and Raman, are discussed. Each type is explained in terms of its physical principles and its applications in aesthetic medicine. Tyndall scattering is relevant in understanding the blue appearance of certain dermal fillers. Rayleigh scattering contributes to skin tone perception and plays a role in certain laser treatments. Mie scattering is important in laser hair removal and the appearance of skin conditions like melasma. Raman scattering, while primarily used in research, shows promise for non-invasive skin analysis, personalized skincare, treatment monitoring, and early skin cancer detection. It is important to understand these scattering phenomena for optimizing light-based aesthetic procedures and developing effective treatments. Properly applying the appropriate scattering theory based on relative particle size is crucial in clinical aesthetic practice.

Is Raman Spectroscopy of Fingernails a Promising Tool for Diagnosing Systemic and Dermatological Diseases in Adult and Pediatric Populations?

Background: Raman spectroscopy is a well-known tool used in criminology, molecular biology, and histology. It is also applied to diagnose bone mineral disorders by taking advantage of the similarity of the structure of keratin and bone collagen. Raman spectroscopy can also be used in dermatology and diabetology. The purpose of the present review is to critically evaluate the available research about the use of Raman spectroscopy in the mentioned areas of medicine. Methodology: PubMed was searched for peer-reviewed articles on the subject of use of Raman spectroscopy in bone mineral disorders, dermatology, and diabetes mellitus. Results: Nail keratin and bone collagen are related structural proteins that require disulfide bond for structural stability. Therefore, Raman spectroscopy of keratin may have potential as a diagnostic tool for screening bone quality and distinguishing patients at risk of fracture for reasons different from low bone mineral density (BMD) in the adult women population. Raman spectroscopy can also investigate the changes in keratin's structure in nails affected by onychomycosis and distinguish between healthy and onychomycosis nail samples. It could also reduce the need for nail biopsy by distinguishing between dermatophytic and non-dermatophytic agents of onychomycosis. Additionally, Raman spectroscopy could expedite the diagnostic process in psoriasis (by assessing the secondary structure of keratin) and in diabetes mellitus (by examining the protein glycation level). Conclusions: In adult populations, Raman spectroscopy is a promising and safe method for assessing the structure of fingernails. However, data are scarce in the pediatric population; therefore, more studies are required in children.

In vivo Raman spectroscopic and fluorescence study of suspected melanocytic lesions and surrounding healthy skin

Cutaneous melanoma is the most lethal skin cancer and noninvasively distinguishing it from benign tumor is a major challenge. Raman spectroscopic measurements were conducted on 65 suspected melanocytic lesions and surrounding healthy skin from 47 patients. Compared to the spectra of healthy skin, spectra of melanocytic lesions exhibited lower intensities in carotenoid bands and higher intensities in lipid and melanin bands, suggesting similar variations in the content of these components. Distinct variations were observed among the autofluorescence intensities of healthy skin, benign nevi and malignant melanoma. By incorporating autofluorescence information, the classification accuracy of the support vector machine for spectra of healthy skin, nevi, and melanoma reached 90.2%, surpassing the 87.9% accuracy achieved without autofluorescence, with this difference being statistically significant. These findings indicate the diagnostic value of autofluorescence intensity, which reflect differences in fluorophore content, chemical composition, and structure among healthy skin, nevi, and melanoma.

Multi-Wavelength Raman Differentiation of Malignant Skin Neoplasms

Raman microspectroscopy has become an effective method for analyzing the molecular appearance of biomarkers in skin tissue. For the first time, we acquired in vitro Raman spectra of healthy and malignant skin tissues, including basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), at 532 and 785 nm laser excitation wavelengths in the wavenumber ranges of 900-1800 cm-1 and 2800-3100 cm-1 and analyzed them to find spectral features for differentiation between the three classes of the samples. The intensity ratios of the bands at 1268, 1336, and 1445 cm-1 appeared to be the most reliable criteria for the three-class differentiation at 532 nm excitation, whereas the bands from the higher wavenumber region (2850, 2880, and 2930 cm-1) were a robust measure of the increased protein/lipid ratio in the tumors at both excitation wavelengths. Selecting ratios of the three bands from the merged (532 + 785) dataset made it possible to increase the accuracy to 87% for the three classes and reach the specificities for BCC + SCC equal to 87% and 81% for the sensitivities of 95% and 99%, respectively. Development of multi-wavelength excitation Raman spectroscopic techniques provides a versatile non-invasive tool for research of the processes in malignant skin tumors, as well as other forms of cancer.

Improving skin cancer detection by Raman spectroscopy using convolutional neural networks and data augmentation

Background

Our previous studies have demonstrated that Raman spectroscopy could be used for skin cancer detection with good sensitivity and specificity. The objective of this study is to determine if skin cancer detection can be further improved by combining deep neural networks and Raman spectroscopy.

Patients and methods

Raman spectra of 731 skin lesions were included in this study, containing 340 cancerous and precancerous lesions (melanoma, basal cell carcinoma, squamous cell carcinoma and actinic keratosis) and 391 benign lesions (melanocytic nevus and seborrheic keratosis). One-dimensional convolutional neural networks (1D-CNN) were developed for Raman spectral classification. The stratified samples were divided randomly into training (70%), validation (10%) and test set (20%), and were repeated 56 times using parallel computing. Different data augmentation strategies were implemented for the training dataset, including added random noise, spectral shift, spectral combination and artificially synthesized Raman spectra using one-dimensional generative adversarial networks (1D-GAN). The area under the receiver operating characteristic curve (ROC AUC) was used as a measure of the diagnostic performance. Conventional machine learning approaches, including partial least squares for discriminant analysis (PLS-DA), principal component and linear discriminant analysis (PC-LDA), support vector machine (SVM), and logistic regression (LR) were evaluated for comparison with the same data splitting scheme as the 1D-CNN.

Results

The ROC AUC of the test dataset based on the original training spectra were 0.886±0.022 (1D-CNN), 0.870±0.028 (PLS-DA), 0.875±0.033 (PC-LDA), 0.864±0.027 (SVM), and 0.525±0.045 (LR), which were improved to 0.909±0.021 (1D-CNN), 0.899±0.022 (PLS-DA), 0.895±0.022 (PC-LDA), 0.901±0.020 (SVM), and 0.897±0.021 (LR) respectively after augmentation of the training dataset (p<0.0001, Wilcoxon test). Paired analyses of 1D-CNN with conventional machine learning approaches showed that 1D-CNN had a 1-3% improvement (p<0.001, Wilcoxon test).

Conclusions

Data augmentation not only improved the performance of both deep neural networks and conventional machine learning techniques by 2-4%, but also improved the performance of the models on spectra with higher noise or spectral shifting. Convolutional neural networks slightly outperformed conventional machine learning approaches for skin cancer detection by Raman spectroscopy.

A Study of High-Frequency Noise for Microplastics Classification Using Raman Spectroscopy and Machine Learning

Given the growing urge for plastic management and regulation in the world, recent studies have investigated the problem of plastic material identification for correct classification and disposal. Recent works have shown the potential of machine learning techniques for successful microplastics classification using Raman signals. Classification techniques from the machine learning area allow the identification of the type of microplastic from optical signals based on Raman spectroscopy. In this paper, we investigate the impact of high-frequency noise on the performance of related classification tasks. It is well-known that classification based on Raman is highly dependent on peak visibility, but it is also known that signal smoothing is a common step in the pre-processing of the measured signals. This raises a potential trade-off between high-frequency noise and peak preservation that depends on user-defined parameters. The results obtained in this work suggest that a linear discriminant analysis model cannot generalize properly in the presence of noisy signals, whereas an error-correcting output codes model is better suited to account for inherent noise. Moreover, principal components analysis (PCA) can become a must-do step for robust classification models, given its simplicity and natural smoothing capabilities. Our study on the high-frequency noise, the possible trade-off between pre-processing the high-frequency noise and the peak visibility, and the use of PCA as a noise reduction technique in addition to its dimensionality reduction functionality are the fundamental aspects of this work.

Portable System for In-Clinic Differentiation of Skin Cancers from Benign Skin Lesions and Inflammatory Dermatoses

The exquisite sensitivity of Raman spectroscopy for detecting biomolecular changes in skin cancer has previously been explored; however, this mostly required analysis of excised tissue samples using bulky, immobile laboratory instrumentation. In this study, the technique was translated for clinical use with a portable Raman system and customized fiber optic probe and applied to differentiation of skin cancers from benign lesions and inflammatory dermatoses. The aim was to provide an easy-to-use, easy-to-manage assessment tool for clinicians to use in their daily patient examination routine to perform rapid Raman measurements of skin lesions in vivo. Using this system, >867 spectra were measured in vivo from 330 patients with a wide variety of different benign skin lesions (n = 603), inflammatory dermatoses (n = 140), and skin cancers (n = 124). Ethnicities represented were 70% European; 16% Asian; 6% Māori; 5% Pacific people; and 4% Middle East, Latin American, and African. Accurate differentiation of skin cancers from benign lesions and inflammatory dermatoses was achieved using partial least squares discriminant analysis, with area under curve for the receiver operator curves for external validation sets ranging from 0.916 to 0.958. This study shows evidence for robust clinical translation of Raman spectroscopy for rapid, accurate diagnosis of skin cancer.

Combined ultrasound and photoacoustic C-mode imaging system for skin lesion assessment

Accurate assessment of the size and depth of infiltration is critical for effectively treating and removing skin cancer, especially melanoma. However, existing methods such as skin biopsy and histologic examination are invasive, time-consuming, and may not provide accurate depth results. We present a novel system for simultaneous and co-localized ultrasound and photoacoustic imaging, with the application for non-invasive skin lesion size and depth measurement. The developed system integrates an acoustical mirror that is placed on an ultrasound transducer, which can be translated within a flexible water tank. This allows for 3D (C-mode) imaging, which is useful for mapping the skin structure and determine the invasion size and depth of lesions including skin cancer. For efficient reconstruction of photoacoustic images, we applied the open-source MUST library. The acquisition time per 2D image is <1 s and the pulse energies are below the legal Maximum Permissible Exposure (MPE) on human skin. We present the depth and resolution capabilities of the setup on several self-designed agar phantoms and demonstrate in vivo imaging on human skin. The setup also features an unobstructed optical window from the top, allowing for simple integration with other optical modalities. The perspective towards clinical application is demonstrated.

An eXplainable Artificial Intelligence analysis of Raman spectra for thyroid cancer diagnosis

Raman spectroscopy shows great potential as a diagnostic tool for thyroid cancer due to its ability to detect biochemical changes during cancer development. This technique is particularly valuable because it is non-invasive and label/dye-free. Compared to molecular tests, Raman spectroscopy analyses can more effectively discriminate malignant features, thus reducing unnecessary surgeries. However, one major hurdle to using Raman spectroscopy as a diagnostic tool is the identification of significant patterns and peaks. In this study, we propose a Machine Learning procedure to discriminate healthy/benign versus malignant nodules that produces interpretable results. We collect Raman spectra obtained from histological samples, select a set of peaks with a data-driven and label independent approach and train the algorithms with the relative prominence of the peaks in the selected set. The performance of the considered models, quantified by area under the Receiver Operating Characteristic curve, exceeds 0.9. To enhance the interpretability of the results, we employ eXplainable Artificial Intelligence and compute the contribution of each feature to the prediction of each sample.

Multispectral Raman Differentiation of Malignant Skin Neoplasms In Vitro: Search for Specific Biomarkers and Optimal Wavelengths

Confocal scanning Raman and photoluminescence (PL) microspectroscopy is a structure-sensitive optical method that allows the non-invasive analysis of biomarkers in the skin tissue. We used it to perform in vitro diagnostics of different malignant skin neoplasms at several excitation wavelengths (532, 785 and 1064 nm). Distinct spectral differences were noticed in the Raman spectra of basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), compared with healthy skin. Our analysis of Raman/PL spectra at the different excitation wavelengths enabled us to propose two novel wavelength-independent spectral criteria (intensity ratios for 1302 cm-1 and 1445 cm-1 bands, 1745 cm-1 and 1445 cm-1 bands), related to the different vibrational "fingerprints" of cell membrane lipids as biomarkers, which was confirmed by the multivariate curve resolution (MCR) technique. These criteria allowed us to differentiate healthy skin from BCC and SCC with sensitivity and specificity higher than 95%, demonstrating high clinical importance in the differential diagnostics of skin tumors.

Combining Raman spectroscopy and machine learning to assist early diagnosis of gastric cancer

Gastric cancers, with gastric adenocarcinoma (GAC) as the most common histological type, cause quite a few of deaths. In order to improve the survival rate after GAC treatment, it is important to develop a method for early detection and therapy support of GAC. Raman spectroscopy is a potential tool for probing cancer cell due to its real-time and non-destructive measurements without any additional reagents. In this study, we use Raman spectroscopy to examine GAC samples, and distinguish cancerous gastric mucosa from normal gastric mucosa. Average Raman spectra of two groups show differences at 750 cm^-1, 1004 cm^-1, 1449 cm^-1, 1089-1128 cm^-1, 1311-1367 cm^-1 and 1585-1665 cm^-1, These peaks were assigned to cytochrome c, phenylalanine, phospholipid, collagen, lipid, and unsaturated fatty acid respectively. Furthermore, we build a SENet-LSTM model to realize the automatic classification of cancerous gastric mucosa and normal gastric mucosa, with all preprocessed Raman spectra in the range of 400-1800 cm^-1 as input. An accuracy 96.20% was achieved. Besides, by using masking method, we found the Raman spectral features which determine the classification and explore the explainability of the classification model. The results are consistent with the conclusions obtained from the average spectrum. All results indicate it is potential for pre-cancerous screening to combine Raman spectroscopy and machine learning.

Raman microspectroscopy and machine learning for use in identifying radiation-induced lung toxicity

OBJECTIVE

In this work, we explore and develop a method that uses Raman spectroscopy to measure and differentiate radiation induced toxicity in murine lungs with the goal of setting the foundation for a predictive disease model.

METHODS

Analysis of Raman tissue data is achieved through a combination of techniques. We first distinguish between tissue measurements and air pockets in the lung by using group and basis restricted non-negative matrix factorization. We then analyze the tissue spectra using sparse multinomial logistic regression to discriminate between fibrotic gradings. Model validation is achieved by splitting the data into a training set containing 70% of the data and a test set with the remaining 30%; classification accuracy is used as the performance metric. We also explore several other potential classification tasks wherein the response considered is the grade of pneumonitis and fibrosis sickness.

RESULTS

A classification accuracy of 91.6% is achieved on the test set of fibrotic gradings, illustrating the ability of Raman measurements to detect differing levels of fibrotic disease among the murine lungs. It is also shown via further modeling that coarser consideration of fibrotic grading via binning (ie. 'Low', 'Medium', 'High') does not degrade performance. Finally, we consider preliminary models for pneumonitis discrimination using the same methodologies.

Diagnostics Using Non-Invasive Technologies in Dermatological Oncology

The growing incidence of skin cancer, with its associated mortality and morbidity, has in recent years led to the developing of new non-invasive technologies, which allow an earlier and more accurate diagnosis. Some of these, such as digital photography, 2D and 3D total-body photography and dermoscopy are now widely used and others, such as reflectance confocal microscopy and optical coherence tomography, are limited to a few academic and referral skin cancer centers because of their cost or the long training period required. Health care professionals involved in the treatment of patients with skin cancer need to know the implications and benefits of new non-invasive technologies for dermatological oncology. In this article we review the characteristics and usability of the main diagnostic imaging methods available today.

Sensor technologies for quality control in engineered tissue manufacturing

The use of engineered cells, tissues, and organs has the opportunity to change the way injuries and diseases are treated. Commercialization of these groundbreaking technologies has been limited in part by the complex and costly nature of their manufacture. Process-related variability and even small changes in the manufacturing process of a living product will impact its quality. Without real-time integrated detection, the magnitude and mechanism of that impact are largely unknown. Real-time and non-destructive sensor technologies are key for in-process insight and ensuring a consistent product throughout commercial scale-up and/or scale-out. The application of a measurement technology into a manufacturing process requires cell and tissue developers to understand the best way to apply a sensor to their process, and for sensor manufacturers to understand the design requirements and end-user needs. Furthermore, sensors to monitor component cells' health and phenotype need to be compatible with novel integrated and automated manufacturing equipment. This review summarizes commercially relevant sensor technologies that can detect meaningful quality attributes during the manufacturing of regenerative medicine products, the gaps within each technology, and sensor considerations for manufacturing.

Multidimensional quantitative characterization of the tumor microenvironment by multicontrast nonlinear microscopy

Characterization of the microenvironment features of tumors, such as its microstructures, biomolecular metabolism, and functional dynamics, may provide essential pathologic information about the tumor, tumor margin, and adjacent normal tissue for early and intraoperative diagnosis. However, it can be particularly challenging to obtain faithful and comprehensive pathological information simultaneously from unperturbed tissues due to the complexity of the microenvironment in organisms. Super-multiplex nonlinear optical imaging system emerged and matured as an attractive tool for acquisition and elucidation of the nonlinear properties correlated with tumor microenvironment. Here, we introduced a nonlinear effects-based multidimensional optical imaging platform and methodology to simultaneously and efficiently capture contrasting and complementary nonlinear optical signatures of freshly excised human skin tissues. The qualitative and quantitative analysis of autofluorescence (FAD), collagen fiber, and intracellular components (lipids and proteins) illustrated the differences about morphological changes and biomolecular metabolic processes of the epidermis and dermis in different skin carcinogenic types. Interpretation of multi-parameter stain-free histological findings complements conventional H&E-stained slides for investigating basal cell carcinoma and pigmented nevus, validates the platform's versatility and efficiency for classifying subtypes of skin carcinoma, and provides the potential to translate endogenous molecule into biomarker for assisting in rapid cancer screening and diagnosis.

Multimodal system for optical biopsy of melanoma with integrated ultrasound, optical coherence tomography and Raman spectroscopy

We introduce a new single-head multimodal optical system that integrates optical coherence tomography (OCT), 18 MHz ultrasound (US) tomography and Raman spectroscopy (RS), allowing for fast (<2 min) and noninvasive skin cancer diagnostics and lesion depth measurement. The OCT can deliver structural and depth information of smaller skin lesions (<1 mm), while the US allows to measure the penetration depth of thicker lesions (≥4 mm), and the RS analyzes the chemical composition from a small chosen spot (≤300 μm) that can be used to distinguish between benign and malignant melanoma. The RS and OCT utilize the same scanning and optical setup, allowing for co-localized measurements. The US on the other side is integrated with an acoustical reflector, which enables B-mode measurements on the same position as OCT and RS. The US B-mode scans can be translated across the sample by laterally moving the US transducer, which is made possible by the developed adapter with a flexible membrane. We present the results on custom-made liquid and agar phantoms that show the resolution and depth capabilities of the setup, as well as preliminary ex vivo measurements on mouse models with ∼4.3 mm thick melanoma.

Fingerprinting of skin cells by live cell Raman spectroscopy reveals melanoma cell heterogeneity and cell-type-specific responses to UVR

Raman spectroscopy is an emerging dermatological technique with the potential to discriminate biochemically between cell types in a label-free and non-invasive manner. Here, we use live single-cell Raman spectroscopy and principal component analysis (PCA) to fingerprint mouse melanoblasts, melanocytes, keratinocytes and melanoma cells. We show the differences in their spectra are attributable to biomarkers in the melanin biosynthesis pathway and that melanoma cells are a heterogeneous population that sit on a trajectory between undifferentiated melanoblasts and differentiated melanocytes. We demonstrate the utility of Raman spectroscopy as a highly sensitive tool to probe the melanin biosynthesis pathway and its immediate response to ultraviolet (UV) irradiation revealing previously undescribed opposing responses to UVA and UVB irradiation in melanocytes. Finally, we identify melanocyte-specific accumulation of β-carotene correlated with a stabilisation of the UVR response in lipids and proteins consistent with a β-carotene-mediated photoprotective mechanism. In summary, our data show that Raman spectroscopy can be used to determine the differentiation status of cells of the melanocyte lineage and describe the immediate and temporal biochemical changes associated with UV exposure which differ depending on cell type, differentiation status and competence to synthesise melanin. Our work uniquely applies Raman spectroscopy to discriminate between cell types by biological function and differentiation status while they are growing in culture. In doing so, we demonstrate for the first time its utility as a tool with which to probe the melanin biosynthesis pathway.

Novel aspects of Raman spectroscopy in skin research

The analytical technology of Raman spectroscopy has an almost 100‐year history. During this period, many modifications and developments happened in the method like discovery of laser, improvements in optical elements and sensitivity of spectrometer and also more advanced light detection systems. Many types of the innovative techniques appeared (e.g. Transmittance Raman spectroscopy, Coherent Raman Scattering microscopy, Surface‐Enhanced Raman scattering and Confocal Raman spectroscopy/microscopy). This review article gives a short description about these different Raman techniques and their possible applications. Then, a short statistical part is coming about the appearance of Raman spectroscopy in the scientific literature from the beginnings to these days. The third part of the paper shows the main application options of the technique (especially confocal Raman spectroscopy) in skin research, including skin composition analysis, drug penetration monitoring and analysis, diagnostic utilizations in dermatology and cosmeto‐scientific applications. At the end, the possible role of artificial intelligence in Raman data analysis and the regulatory aspect of these techniques in dermatology are briefly summarized. For the future of Raman Spectroscopy, increasing clinical relevance and in vivo applications can be predicted with spreading of non‐destructive methods and appearance with the most advanced instruments with rapid analysis time.

Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis

While Raman spectroscopy can provide label-free discrimination between highly similar biological species, the discrimination is often marginal, and optimal use of spectral information is imperative. Here, we compare two machine learning models, an artificial neural network and a support vector machine, for discriminating between Raman spectra of 11 bacterial mutants of Escherichia coli MDS42. While we find that both models discriminate the 11 bacterial strains with similarly high accuracy, sensitivity and specificity, it is clear that the models form different class boundaries. By extracting strain-specific (and function-specific) spectral features utilized by the models, we find that both models utilize a small subset of high intensity peaks while separate subsets of lower intensity peaks are utilized by only one method or the other. This analysis highlights the need for methods to use the complete spectral information more effectively, beginning with a better understanding of the distinct information gained from each model.

Lung Cancer: Spectral and Numerical Differentiation among Benign and Malignant Pleural Effusions Based on the Surface-Enhanced Raman Spectroscopy

We present here that the surface-enhanced Raman spectroscopy (SERS) technique in conjunction with the partial least squares analysis is as a potential tool for the differentiation of pleural effusion in the course of the cancerous disease and a tool for faster diagnosis of lung cancer. Pleural effusion occurs mainly in cancer patients due to the spread of the tumor, usually caused by lung cancer. Furthermore, it can also be initiated by non-neoplastic diseases, such as chronic inflammatory infection (the most common reason for histopathological examination of the exudate). The correlation between pleural effusion induced by tumor and non-cancerous diseases were found using surface-enhanced Raman spectroscopy combined with principal component regression (PCR) and partial least squares (PLS) multivariate analysis method. The PCR predicts 96% variance for the division of neoplastic and non-neoplastic samples in 13 principal components while PLS 95% in only 10 factors. Similarly, when analyzing the SERS data to differentiate the type of tumor (squamous cell vs. adenocarcinoma), PLS gives more satisfactory results. This is evidenced by the calculated values of the root mean square errors of calibration and prediction but also the coefficients of calibration determination and prediction (R2C = 0.9570 and R2C = 0.7968), which are more robust and rugged compared to those calculated for PCR. In addition, the relationship between cancerous and non-cancerous samples in the dependence on the gender of the studied patients is presented.

Establishment of an Epicutaneously Sensitized Murine Model of Shellfish Allergy and Evaluation of Skin Condition by Raman Microscopy

Background: Shellfish allergy is one of the most common food allergies. Recent studies have shown that sensitization to allergens via the skin is involved in the development of food allergies. In this study, a mouse model of shrimp allergy was generated by epicutaneous sensitization and used to identify skin conditions associated with susceptibility to sensitization. Methods: Four-week-old female BALB/c mice were sensitized by repeated application of 0.1 mg of tropomyosin to tape-stripped skin on days 0, 7, and 15, followed by a challenge on days 28 and 35. Results: Epicutaneously sensitized mice exhibited higher serum levels of tropomyosin-specific IgE on day 15 than control mice. After the oral challenge, model mice had higher anaphylaxis scores and lower rectal temperature. After three tape-strip treatments for sensitization, the skin was analyzed by Raman microscopy. The sensitized mice exhibited lower relative intensities of Raman bands at 399, 915, and 1073 cm−1 than control mice, which could be helpful noninvasive markers in screening for potential sensitization via the skin. Conclusions: An epicutaneous sensitization shellfish allergy model was generated. This model will be useful in studies to elucidate the pathogenesis of skin sensitization. Raman microscopy may also be valuable for capturing subtle skin changes leading to sensitization.

Artificial Intelligence and Machine Learning in Cancer Research: A Systematic and Thematic Analysis of the Top 100 Cited Articles Indexed in Scopus Database

INTRODUCTION

Cancer is a major public health problem and a global leading cause of death where the screening, diagnosis, prediction, survival estimation, and treatment of cancer and control measures are still a major challenge. The rise of Artificial Intelligence (AI) and Machine Learning (ML) techniques and their applications in various fields have brought immense value in providing insights into advancement in support of cancer control.

METHODS

A systematic and thematic analysis was performed on the Scopus database to identify the top 100 cited articles in cancer research. Data were analyzed using RStudio and VOSviewer.Var1.6.6.

RESULTS

The top 100 articles in AI and ML in cancer received a 33 920 citation score with a range of 108 to 5758 times. Doi Kunio from the USA was the most cited author with total number of citations (TNC = 663). Out of 43 contributed countries, 30% of the top 100 cited articles originated from the USA, and 10% originated from China. Among the 57 peer-reviewed journals, the "Expert Systems with Application" published 8% of the total articles. The results were presented in highlight technological advancement through AI and ML via the widespread use of Artificial Neural Network (ANNs), Deep Learning or machine learning techniques, Mammography-based Model, Convolutional Neural Networks (SC-CNN), and text mining techniques in the prediction, diagnosis, and prevention of various types of cancers towards cancer control.

CONCLUSIONS

This bibliometric study provides detailed overview of the most cited empirical evidence in AI and ML adoption in cancer research that could efficiently help in designing future research. The innovations guarantee greater speed by using AI and ML in the detection and control of cancer to improve patient experience.

Rapid parameter estimation of discrete decaying signals using autoencoder networks

In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cramér–Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, our exploration of the limitations of our approach in different computational systems suggests that analysis rates of > 200 kHz are feasible using neural networks in systems where the transfer time between the data-acquisition system and data-analysis modules can be kept below ∼3 µs.

Finding reduced Raman spectroscopy fingerprint of skin samples for melanoma diagnosis through machine learning

Early-stage detection of cutaneous melanoma can vastly increase the chances of cure. Excision biopsy followed by histological examination is considered the gold standard for diagnosing the disease, but requires long high-cost processing time, and may be biased, as it involves qualitative assessment by a professional. In this paper, we present a new machine learning approach using raw data for skin Raman spectra as input. The approach is highly efficient for classifying benign versus malignant skin lesions (AUC 0.98, 95% CI 0.97-0.99). Furthermore, we present a high-performance model (AUC 0.97, 95% CI 0.95-0.98) using a miniaturized spectral range (896-1039 cm^-1), thus demonstrating that only a single fragment of the biological fingerprint Raman region is needed for producing an accurate diagnosis. These findings could favor the future development of a cheaper and dedicated Raman spectrometer for fast and accurate cancer diagnosis.

Development of the fluorescent carbon nanosensor for pH and temperature of liquid media with artificial neural networks

The present study is devoted to the creation of optical nanosensors for pH and temperature of liquid media based on carbon dots (CD) prepared via hydrothermal synthesis. The application of artificial neural networks to the CD fluorescence spectra database provided simultaneous determination of pH and ambient temperature values with an accuracy of 0.005 pH units and 0.67 °C, respectively. The obtained results are unique since they indicate the possibility of creating a multifunctional CD-based nanosensor that operates in a wide temperature range (22-81 °C) and provides an accuracy of pH determination exceeding the accuracy of nanoscale analogs by an order of magnitude.

Advances in the Etiology, Detection, and Clinical Management of Seborrheic Keratoses

Seborrheic keratoses (SKs) are ubiquitous, generally benign skin tumors that exhibit high clinical variability. While age is a known risk factor, the precise roles of UV exposure and immune abnormalities are currently unclear. The underlying mechanisms of this benign disorder are paradoxically driven by oncogenic mutations and may have profound implications for our understanding of the malignant state. Advances in molecular pathogenesis suggest that inhibition of Akt and APP, as well as existing treatments for skin cancer, may have therapeutic potential in SK. Dermoscopic criteria have also become increasingly important to the accurate detection of SK, and other noninvasive diagnostic methods, such as reflectance confocal microscopy and optical coherence tomography, are rapidly developing. Given their ability to mimic malignant tumors, SK cases are often used to train artificial intelligence-based algorithms in the computerized detection of skin disease. These technologies are becoming increasingly accurate and have the potential to significantly augment clinical practice. Current treatment options for SK cause discomfort and can lead to adverse post-treatment effects, especially in skin of color. In light of the discontinuation of ESKATA in late 2019, promising alternatives, such as nitric-zinc and trichloroacetic acid topicals, should be further developed. There is also a need for larger, head-to-head trials of emerging laser therapies to ensure that future treatment standards address diverse patient needs.

Feature fusion of Raman chemical imaging and digital histopathology using machine learning for prostate cancer detection

The diagnosis of prostate cancer is challenging due to the heterogeneity of its presentations, leading to the over diagnosis and treatment of non-clinically important disease. Accurate diagnosis can directly benefit a patient's quality of life and prognosis. Towards addressing this issue, we present a learning model for the automatic identification of prostate cancer. While many prostate cancer studies have adopted Raman spectroscopy approaches, none have utilised the combination of Raman Chemical Imaging (RCI) and other imaging modalities. This study uses multimodal images formed from stained Digital Histopathology (DP) and unstained RCI. The approach was developed and tested on a set of 178 clinical samples from 32 patients, containing a range of non-cancerous, Gleason grade 3 (G3) and grade 4 (G4) tissue microarray samples. For each histological sample, there is a pathologist labelled DP-RCI image pair. The hypothesis tested was whether multimodal image models can outperform single modality baseline models in terms of diagnostic accuracy. Binary non-cancer/cancer models and the more challenging G3/G4 differentiation were investigated. Regarding G3/G4 classification, the multimodal approach achieved a sensitivity of 73.8% and specificity of 88.1% while the baseline DP model showed a sensitivity and specificity of 54.1% and 84.7% respectively. The multimodal approach demonstrated a statistically significant 12.7% AUC advantage over the baseline with a value of 85.8% compared to 73.1%, also outperforming models based solely on RCI and mean and median Raman spectra. Feature fusion of DP and RCI does not improve the more trivial task of tumour identification but does deliver an observed advantage in G3/G4 discrimination. Building on these promising findings, future work could include the acquisition of larger datasets for enhanced model generalization.

Cancer Surgery 2.0: Guidance by Real-Time Molecular Technologies

In vivo cancer margin delineation during surgery remains a major challenge. Despite the availability of several image guidance techniques and intraoperative assessment, clear surgical margins and debulking efficiency remain scarce. For this reason, there is particular interest in developing rapid intraoperative tools with high sensitivity and specificity to help guide cancer surgery in vivo. Recently, several emerging technologies including intraoperative mass spectrometry have paved the way for molecular guidance in a clinical setting. We evaluate these techniques and assess their relevance for intraoperative surgical guidance and how they can transform the future of molecular cancer surgery, diagnostics, patient management and care.

Can Coupling Multiple Complementary Methods Improve the Spectroscopic Based Diagnosis of Gastrointestinal Illnesses? A Proof of Principle Ex Vivo Study Using Celiac Disease as the Model Illness

Spectroscopic methods are a promising approach for providing a point-of-care diagnostic method for gastrointestinal mucosa associated illnesses. Such a tool is desired to aid immediate decision making and to provide a faster pathway to appropriate treatment. In this pilot study, Raman, near-infrared, low frequency Raman, and autofluoresence spectroscopic methods were explored alone and in combination for the diagnosis of celiac disease. Duodenal biopsies (n = 72) from 24 participants were measured ex vivo using the full suite of studied spectroscopic methods. Exploratory principal component analysis (PCA) highlighted the origin of spectral differences between celiac and normal tissue with celiac biopsies tending to have higher protein relative to lipid signals and lower carotenoid spectral signals than the samples with normal histology. Classification of the samples based on the histology and overall diagnosis was carried out for all combinations of spectroscopic methods. Diagnosis based classification (majority rule of class per participant) yielded sensitivities of 0.31 to 0.77 for individual techniques, which was increased up to 0.85 when coupling multiple techniques together. Likewise, specificities of 0.50 to 0.67 were obtained for individual techniques, which was increased up to 0.78 when coupling multiple techniques together. It was noted that the use of antidepressants contributed to false positives, which is believed to be associated with increased serotonin levels observed in the gut mucosa in both celiac disease and the use of selective serotonin reuptake inhibitors (SSRIs); however, future work with greater numbers is required to confirm this observation. Inclusion of two additional spectroscopic methods could improve the accuracy of diagnosis (0.78) by 7% over Raman alone (0.73). This demonstrates the potential for further exploration and development of a multispectroscopic system for disease diagnosis.

Unveiling Cancer Metabolism through Spontaneous and Coherent Raman Spectroscopy and Stable Isotope Probing

Metabolic reprogramming is a common hallmark in cancer. The high complexity and heterogeneity in cancer render it challenging for scientists to study cancer metabolism. Despite the recent advances in single-cell metabolomics based on mass spectrometry, the analysis of metabolites is still a destructive process, thus limiting in vivo investigations. Being label-free and nonperturbative, Raman spectroscopy offers intrinsic information for elucidating active biochemical processes at subcellular level. This review summarizes recent applications of Raman-based techniques, including spontaneous Raman spectroscopy and imaging, coherent Raman imaging, and Raman-stable isotope probing, in contribution to the molecular understanding of the complex biological processes in the disease. In addition, this review discusses possible future directions of Raman-based technologies in cancer research.

Using the Method of "Optical Biopsy" of Prostatic Tissue to Diagnose Prostate Cancer

Simple Summary

Analytical discrimination models of Raman spectra of prostate cancer tissue were constructed by using the projections onto latent structures data analysis (PLS-DA) method for different wavelengths of exciting radiation—532 and 785 nm. These models allowed us to divide the Raman spectra of prostate cancer and the spectra of hyperplasia sites for validation datasets with the accuracy of 70–80%, depending on the specificity value. Meanwhile, for the calibration datasets, the accuracy values reached 100% for the excitation of a laser with a wavelength of 785 nm. Due to the registration of Raman “fingerprints”, the main features of cellular metabolism occurring in the tissue of a malignant prostate tumor were confirmed, namely the absence of aerobic glycolysis, over-expression of markers, and a strong increase in the concentration of cholesterol and its esters, as well as fatty acids and glutamic acid.

Abstract

The possibilities of using optical spectroscopy methods in the differential diagnosis of prostate cancer were investigated. Analytical discrimination models of Raman spectra of prostate tissue were constructed by using the projections onto latent structures data analysis(PLS-DA) method for different wavelengths of exciting radiation—532 and 785 nm. These models allowed us to divide the Raman spectra of prostate cancer and the spectra of hyperplasia sites for validation datasets with the accuracy of 70–80%, depending on the specificity value. Meanwhile, for the calibration datasets, the accuracy values reached 100% for the excitation of a laser with a wavelength of 785 nm. Due to the registration of Raman “fingerprints”, the main features of cellular metabolism occurring in the tissue of a malignant prostate tumor were confirmed, namely the absence of aerobic glycolysis, over-expression of markers (FASN, SREBP1, stearoyl-CoA desaturase, etc.), and a strong increase in the concentration of cholesterol and its esters, as well as fatty acids and glutamic acid. The presence of an ensemble of Raman peaks with increased intensity, inherent in fatty acid, beta-glucose, glutamic acid, and cholesterol, is a fundamental factor for the identification of prostate cancer.

Characterization of the COPD Salivary Fingerprint through Surface Enhanced Raman Spectroscopy: A Pilot Study

Chronic Obstructive Pulmonary Disease (COPD) is a debilitating pathology characterized by reduced lung function, breathlessness and rapid and unrelenting decrease in quality of life. The severity rate and the therapy selection are strictly dependent on various parameters verifiable after years of clinical observations, missing a direct biomarker associated with COPD. In this work, we report the methodological application of Surface Enhanced Raman Spectroscopy combined with Multivariate statistics for the analysis of saliva samples collected from 15 patients affected by COPD and 15 related healthy subjects in a pilot study. The comparative Raman analysis allowed to determine a specific signature of the pathological saliva, highlighting differences in determined biological species, already studied and characterized in COPD onset, compared to the Raman signature of healthy samples. The unsupervised principal component analysis and hierarchical clustering revealed a sharp data dispersion between the two experimental groups. Using the linear discriminant analysis, we created a classification model able to discriminate the collected signals with accuracies, specificities, and sensitivities of more than 98%. The results of this preliminary study are promising for further applications of Raman spectroscopy in the COPD clinical field.

Supervised learning methods for the recognition of melanoma cell lines through the analysis of their Raman spectra

Malignant melanoma is an aggressive form of skin cancer, which develops from the genetic mutations of melanocytes - the most frequent involving BRAF and NRAS genes. The choice and the effectiveness of the therapeutic approach depend on tumour mutation; therefore, its assessment is of paramount importance. Current methods for mutation analysis are destructive and take a long time; instead, Raman spectroscopy could provide a fast, label-free and non-destructive alternative. In this study, confocal Raman microscopy has been used for examining three in vitro melanoma cell lines, harbouring different molecular profiles and, in particular, specific BRAF and NRAS driver mutations. The molecular information obtained from Raman spectra has served for developing two alternative classification algorithms based on linear discriminant analysis and artificial neural network. Both methods provide high accuracy (≥90%) in discriminating all cell types, suggesting that Raman spectroscopy may be an effective tool for detecting molecular differences between melanoma mutations.

Decoding Optical Data with Machine Learning

Optical spectroscopy and imaging techniques play important roles in many fields such as disease diagnosis, biological study, information technology, optical science, and materials science. Over the past decade, machine learning (ML) has proved promising in decoding complex data, enabling rapid and accurate analysis of optical spectra and images. This review aims to shed light on various ML algorithms for optical data analysis with a focus on their applications in a wide range of fields. The goal of this work is to sketch the validity of ML-based optical data decoding. The review concludes with an outlook on unaddressed problems and opportunities in this emerging subject that interfaces optics, data science and ML.

Fourier-Transform InfraRed (FT-IR) spectroscopy to show alterations in molecular composition of EV subpopulations from melanoma cell lines in different malignancy

Background

Melanoma cells release extracellular vesicles (EVs) subpopulations which differ in size, phenotype and molecular content. Melanoma derived EVs play a role in the development and progression of cancer by delivering surface receptors and bioactive (proteins, lipids, nucleic acids) or signaling molecules to target cells.

Methods

We applied Fourier Transform Infrared Spectroscopy (FTIR) to compare infrared spectra of absorption for different subpopulations of EVs originating from normal human melanocytes, primary cutaneous melanoma (WM115) and metastatic cutaneous melanoma (WM266-4).

Results

FTIR results showed that exosome and ectosome populations differ in content of protein and lipid components. We obtained higher lipid to protein ratio for ectosomes in comparison with exosomes what confirms that exosomes are very densely packed with protein cargo. We identified the lowest value of saturated fatty acids/unsaturated fatty acids parameter in the metastatic WM266-4 cell line and ectosomes derived from WM266-4 cell line in comparison with normal melanocytes and the primary WM115 cell line. We identified the alterations in the content of secondary structures of proteins present in EV subpopulations originating from melanocytes and melanoma cells in different malignancy.

Conclusions

Obtained results revealed differences in the molecular composition of melanoma derived EVs subtypes, including protein secondary structure, and showed progressive structural changes during cancer development.

•

Fourier-Transformed Infrared spectroscopy allows recognition lipid and protein content in extracellular vesicles (EVs).

•

Subpopulations of (EVs) from human melanocytes and melanoma cells contain distinct lipid composition and protein structure.

•

Ectosomes from malignant human melanoma are rich in saturated fatty acids and random coiled proteins.

•

Exosomes from malignant human melanoma are bigger in compare to those from melanocytes and have higher lipid to amid ratio.

AI-enabled real-time dual-comb molecular fingerprint imaging

Hyperspectral imaging provides spatially resolved spectral information. Utilizing dual-frequency combs as active illumination sources, hyperspectral imaging with ultra-high spectral resolution can be implemented in a scan-free manner when a detector array is used for heterodyne detection. Here, we show that dual-comb hyperspectral imaging can be performed with an uncooled near-to-mid-infrared detector by exploiting the detector array's high frame rate, achieving 10 Hz acquisition in 30 spectral channels across 16,384 pixels. Artificial intelligence (AI) enables real-time data reduction and imaging of gas concentration based on characteristic molecular absorption signatures. Owing to the detector array's sensitivity from 1 to 5 µm wavelength, this demonstration lays the foundation for real-time versatile imaging of molecular fingerprint signatures across the infrared wavelength regime with high temporal resolution.

Optical clearing agent increases effectiveness of photodynamic therapy in a mouse model of cutaneous melanoma: an analysis by Raman microspectroscopy

Melanoma is the most aggressive type of skin cancer and a relevant health problem due to its poor treatment response with high morbidity and mortality rates. This study, aimed to investigate the tissue changes of an improved photodynamic therapy (PDT) response when combined with optical clearing agent (OCA) in the treatment of cutaneous melanoma in mice. Photodithazine (PDZ) was administered intraperitoneally and a solution of OCA was topically applied before PDT irradiation. Due to a resultant refractive index matching, OCA-treated tumors are more optically homogenous, improving the PDT response. Raman analysis revealed, when combined with OCA, the PDT response was more homogenous down to 725 µm-depth in thickness.

Raman Probes for In Situ Molecular Analyses of Peripheral Nerve Myelination

The myelinating activity of living Schwann cells in coculture with neuronal cells was examined in situ in a Raman microprobe spectroscope. The Raman label-free approach revealed vibrational fingerprints directly related to the activity of Schwann cells' metabolites and identified molecular species peculiar to myelinating cells. The identified chemical species included antioxidants, such as hypotaurine and glutathione, and compartmentalized water, in addition to sphingolipids, phospholipids, and nucleoside triphosphates also present in neuronal and nonmyelinating Schwann cells. Raman maps at specific frequencies could be collected, which clearly visualized the myelinating action of Schwann cells and located the demyelinated ones. An important finding was the spectroscopic visualization of confined water in the myelin structure, which exhibited a quite pronounced Raman signal at ∼3470 cm^-1. This peculiar signal, whose spatial location precisely corresponded to a low-frequency fingerprint of hypotaurine, was absent in unmyelinating cells and in bulk water. Raman enhancement was attributed to frustration in the hydrogen-bond network as induced by interactions with lipids in the myelin sheaths. According to a generally accepted morphological model of myelin, an explanation was offered of the peculiar Raman scattering of water confined in intraperiod lines, according to an ordered hydrogen bonding structure. The possibility of concurrently mapping antioxidant molecules and compartmentalized water structure with high spectral accuracy and microscopic spatial resolution enables probing myelinating activity and might play a key-role in future studies of neuronal pathologies. Compatible with life, Raman microprobe spectroscopy with the newly discovered probes could be suitable for developing advanced strategies in the reconstruction of injured nerves and nerve terminals at neuromuscular junctions.

Assessment of Raman Spectroscopy for Reducing Unnecessary Biopsies for Melanoma Screening

A key challenge in melanoma diagnosis is the large number of unnecessary biopsies on benign nevi, which requires significant amounts of time and money. To reduce unnecessary biopsies while still accurately detecting melanoma lesions, we propose using Raman spectroscopy as a non-invasive, fast, and inexpensive method for generating a “second opinion” for lesions being considered for biopsy. We collected in vivo Raman spectral data in the clinical skin screening setting from 52 patients, including 53 pigmented lesions and 7 melanomas. All lesions underwent biopsies based on clinical evaluation. Principal component analysis and logistic regression models with leave one lesion out cross validation were applied to classify melanoma and pigmented lesions for biopsy recommendations. Our model achieved an area under the receiver operating characteristic (ROC) curve (AUROC) of 0.903 and a specificity of 58.5% at perfect sensitivity. The number needed to treat for melanoma could have been decreased from 8.6 (60/7) to 4.1 (29/7). This study in a clinical skin screening setting shows the potential of Raman spectroscopy for reducing unnecessary skin biopsies with in vivo Raman data and is a significant step toward the application of Raman spectroscopy for melanoma screening in the clinic.

Brain tumour homogenates analysed by surface-enhanced Raman spectroscopy: Discrimination among healthy and cancer cells

One of the biggest challenge for modern medicine is to make a discrimination among healthy and cancerous tissues. Therefore, nowadays big effort of scientist are devoted to find a new way for as fast as possible diagnosis with as much as possible accuracy in distinguishing healthy from cancerous tissues. That issues are probably the most important in the case of brain tumours, when the diagnosis time plays a great role. Herein we present the surface-enhanced Raman spectroscopy (SERS) together with the principal component analysis (PCA) used to identify the spectra of different brain specimens, healthy and tumour tissues homogenates. The presented analyses include three sets of brain tissues as control samples taken from healthy objects (one set consists of samples from four brain lobes and both hemispheres; eight samples) and the brain tumours from five patients (two Anaplastic Astrocytoma and three Glioblastoma samples). Results prove that tumour brain samples can be discriminated well from the healthy tissues by using only three main principal components, with 96% of accuracy. The largest influence onto the calculated separation is attributed to the spectral regions corresponding in SERS spectra to vibrations of the L-Tryptophan (1450, 1278 cm^-1), protein (1300 cm^-1), phenylalanine and Amide-I (1005, 1654 cm^-1). Therefore, the presented method may open the way for the probable application as a very fast diagnosis tool alternative for conventionally used histopathology or even more as an intraoperative diagnostic tool during brain tumour surgery.

Differentiating smokers and nonsmokers based on Raman spectroscopy of oral fluid and advanced statistics for forensic applications

Raman spectroscopy has proven to be a valuable tool for analyzing various types of forensic evidence such as traces of body fluids. In this work, Raman spectroscopy was employed as a nondestructive technique for the analysis of dry traces of oral fluid to differentiate between smoker and nonsmoker donors with the aid of advanced statistical tools. A total of 32 oral fluid samples were collected from donors of differing gender, age and race and were subjected to Raman spectroscopic analysis. A genetic algorithm was used to determine eight spectral regions that contribute the most to the differentiation of smokers and nonsmokers. Thereafter, a classification model was developed based on the artificial neural network that showed 100% accuracy after external validation. The developed approach demonstrates great potential for the differentiation of smokers and nonsmokers based on the analysis of dry traces of oral fluid.

SERS-based biosensor for Alzheimer disease evaluation through the fast analysis of human serum

Alzheimer disease (AD) is the most common form of dementia in the elderly, progressively affecting the cognitive functions with a complex diagnostic procedure that limits the time for a prompt intervention. In this study we optimized a reliable protocol for the analysis of AD patients and healthy subjects' serum using the Surface Enhanced Raman Spectroscopy (SERS), taking into consideration the effect of different variables on the final spectra, analyzed and compared through multivariate analysis and correlated with hippocampus volume. As results, we demonstrated a statistical difference between the spectra collected from the two investigated groups, with an accuracy, precision and specificity of respectively 83%, 86%, and 86%. The correlation of these data with those obtained from MRI, demonstrated a direct correlation between Raman spectra and hippocampus degeneration showing the Raman Spectroscopy (RS) as a potential tool for the monitoring of AD progression and rehabilitation treatments.

Differentiation of skin biopsies by light scattering spectroscopy

Introduction

Spectroscopic systems are medical tools that are used for the detection of cancerous tissues ex vivo and in vivo.

Aim

To differentiate inflammatory and benign skin lesions of excised biopsy samples via a combination of multivariate statistical analysis.

Material and methods

Spectral data were obtained from a total of 22 inflammatory and ten benign skin biopsy samples from 30 patients in the visible wavelength (450–750 nm) regions. Spectral data were compared with the dermatopathology results. Spectral data analyses of biopsy samples were performed via principal component analysis (PCA), followed by linear discriminant analysis (LDA). The differentiation performance was calculated with the receiver operating characteristic (ROC) curve analysis.

Results

The classification based on the discriminant function score provided a sensitivity of 90.9% and a specificity of 80% in discriminating benign from inflammatory lesions with an accuracy of 87.5%.

Conclusions

Our study revealed that light scattering spectroscopy could discriminate between inflammatory and benign skin lesions of excised biopsy samples with high sensitivity by using multivariate statistical analysis. It can be concluded that the high diagnostic accuracy of the optical spectroscopy method has the potential to use as a supplementary system to distinguish inflammatory skin lesions from benign during the pathological examination.

Raman Scattering: From Structural Biology to Medical Applications

This is a review of relevant Raman spectroscopy (RS) techniques and their use in structural biology, biophysics, cells, and tissues imaging towards development of various medical diagnostic tools, drug design, and other medical applications. Classical and contemporary structural studies of different water-soluble and membrane proteins, DNA, RNA, and their interactions and behavior in different systems were analyzed in terms of applicability of RS techniques and their complementarity to other corresponding methods. We show that RS is a powerful method that links the fundamental structural biology and its medical applications in cancer, cardiovascular, neurodegenerative, atherosclerotic, and other diseases. In particular, the key roles of RS in modern technologies of structure-based drug design are the detection and imaging of membrane protein microcrystals with the help of coherent anti-Stokes Raman scattering (CARS), which would help to further the development of protein structural crystallography and would result in a number of novel high-resolution structures of membrane proteins—drug targets; and, structural studies of photoactive membrane proteins (rhodopsins, photoreceptors, etc.) for the development of new optogenetic tools. Physical background and biomedical applications of spontaneous, stimulated, resonant, and surface- and tip-enhanced RS are also discussed. All of these techniques have been extensively developed during recent several decades. A number of interesting applications of CARS, resonant, and surface-enhanced Raman spectroscopy methods are also discussed.

Applications of Raman spectroscopy in the development of cell therapies: state of the art and future perspectives

This comprehensive review article discusses current and future perspectives of Raman spectroscopy-based analyses of cell therapy processes and products.

Normal-subtracted preprocessing of Raman spectra aiming to discriminate skin actinic keratosis and neoplasias from benign lesions and normal skin tissues

The differences in the biochemistry of normal and cancerous tissue could be better exploited by Raman spectroscopy when the spectral information from normal tissue is subtracted from the abnormal tissues. In this study, we evaluated the use of the normal-subtracted spectra to evidence the biochemical differences in the pre-cancerous and cancerous skin tissues compared with normal skin, and to discriminate the groups with altered tissues with respect to the normal sites. Raman spectra from skin tissues [normal (Normal), benign (dermatitis-BEN), basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and actinic keratosis (KER)] were obtained in vivo (Silveira et al., 2015, doi: https://doi.org/10.1002/lsm.22318) and used to develop the spectral model. The mean spectrum of the normal sites (circumjacent to each lesion) from each subject was calculated and subtracted from each individual spectrum of that particular subject independently of the group (Normal, BEN, BCC, SCC, KERAT). The mean spectra of each altered group and the mean spectra of the differences were firstly evaluated in terms of biochemical contribution or differentiation comparing the normal site. Then, the normal-subtracted spectra were submitted to discriminant models based on partial least squares and principal components regression (PLS-DA and PCR-DA), and the discrimination were compared with the model using non-subtracted spectra. Results showed that the peaks of nucleic acids, lipids (triolein) and proteins (elastin and collagens I, III, and IV) were significantly different in the lesions, higher for the pre- and neoplastic lesions compared with normal and benign. The PLS-DA showed that the groups could be discriminated with 90.3% accuracy when the mean-subtracted spectra were used, contrasting with 75.1% accuracy when the non-subtracted spectra were used. Also, when discriminating non-neoplastic tissue (Normal + BEN) from pre- and neoplastic sites (BCC + SCC + KERAT), the accuracy increases to 92.5% for the normal-subtracted compared with 85.3% for the non-subtracted. The subtraction of the mean normal spectrum from the subject obtained circumjacent to each lesion could significantly increase the diagnostic capability of the Raman-based discrimination algorithm.