Raman Spectroscopy Technology Research Articles

Feasibility of biomass-based flexible and transparent AuNPs-acetylcellulose membrane for multifarious surface-enhanced Raman spectroscopy detection

BackgroundLignocellulosic biomass-based derivatives coupled with surface-enhanced Raman spectroscopy (SERS) technology have emerged as an appealing and indispensable tool in food safety and environmental monitoring for rapidly detecting trace contaminants like pesticide residues. The membrane material, serving as a substrate, ensures both sampling flexibility and test accuracy by directing the diffusion-adsorption process of the molecules. However, the existing membrane substrates, critical for the practical application of SERS, suffer from issues such as costly, intricate fabrication procedures, or restricted detection capabilities. ResultsHerein, we present a flexible, transparent, and biodegradable cellulose acetate membrane with gold nanoparticles (AuNPs) uniformly embedded, fabricated using a simple scraping method. This membrane achieved a limit of detection (LOD) of thiram pesticide in water at 10−8 g mL−1. The unique optical transparency of the substrates allowed for in-situ detection on surfaces, with an LOD of thiram reaching 30 ng cm−2. SignificanceFurthermore, SERS substrates made from corn stover-derived cellulose acetate enable the detection of various contaminants, highlighting their cost-effectiveness and eco-friendliness because of the abundance and low environmental impact of the raw materials.

Laser Tweezers Raman Spectroscopy and its application in bio-chemical sensing

Laser Tweezers Raman Spectroscopy (LTRS) technology combines Raman spectroscopy and optical tweezers technology, providing a new way to research in single cell analysis and microbial classification. Driven by the development of precision spectroscopy and deep learning techniques, LTRS plays an increasingly important role in biomedical research, clinical diagnosis and environmental research. For example, it can be used to detect cancer cells, analyse bacterial infections, and monitor harmful environmental substances. In this paper, we review the basic principles of LTRS technology through literature reading and case studies, explain how the technology combines the advantages of optical tweezers and Raman spectroscopy in order to provide a non-destructive, label-free and susceptible single-cell analysis method, summarize the latest development of LTRS technology in recent years, as well as its applications in the field of biochemical sensing, and finally discuss the problems it is currently facing and look forward to its future development direction. Finally, the current problems faced by LTRS are discussed, and the direction of its future development is anticipated.

Authenticity Verification of Alcoholic Beverages in IoT Environment through Fluorescence Hyperspectral Technology and Machine Learning

In the Internet of Things (IoT) environment, verifying the authenticity of beverages is an important issue. Baijiu, a unique Chinese distilled liquor, has gained popularity among people due to its distinctive flavor. In recent years, there has been increasing concern about the adulteration of baijiu. Many studies in this field have attempted to combine chemometrics, electronic nose, Raman spectroscopy, and other detection technologies with machine learning for baijiu detection. However, no research has yet applied the mature detection technology of fluorescence hyperspectral technology to this field. Additionally, existing studies have mainly focused on branded baijiu, without addressing the problem of adulteration in bulk baijiu, which remains a long-standing issue. In this study, a combination of fluorescence hyperspectral and machine learning was used for rapid and nondestructive adulteration detection of bulk liquor in Chengdu. The fluorescence hyperspectral data of three types of samples, namely, original liquor, adulterated liquor with water, and adulterated liquor with industrial alcohol, were obtained, and the raw data were preprocessed using Savitzky–Golay (SG), baseline correction (BL), multivariate scatter correction (MSC), and the combination of Savitzky–Golay and baseline correction (SG-BL). Finally, PCA and MDS are also used to extract spectral data characteristics, respectively. For model selection, three models were chosen: back-propagation artificial neural network (BP-ANN), support vector machine (SVM), and one-dimensional convolutional neural network (1D-CNN). For model evaluation, we choose accuracy, recall, precision, F1-score, memory occupied, and time consumed by the model to evaluate. The experiments show that the combination of fluorescence hyperspectral technology and machine learning can provide a new method, MSC-PCA-SVM, for bulk liquor detection, with a final classification accuracy, recall, precision, and F1-score all reaching 100%, The effectiveness and application potential of this method in the IoT environment have been demonstrated. The results of this study can not only be applied to liquor detection but also have the value of reference for the adulthood and detection of the entire food industry. It is of great significance to standardize the market and protect consumer rights.

Diagnosis and classification of kidney transplant rejection using machine learning-assisted surface-enhanced Raman spectroscopy using a single drop of serum

The quest to reduce kidney transplant rejection has emphasized the urgent requirement for the development of non-invasive, precise diagnostic technologies. These technologies aim to detect antibody-mediated rejection (ABMR) and T-cell-mediated rejection (TCMR), which are asymptomatic and pose a risk of potential kidney damage. The protocols for managing rejection caused by ABMR and TCMR differ, and diagnosis has traditionally relied on invasive biopsy procedures. Therefore, a convergence system using a nano-sensing chip, Raman spectroscopy, and AI technology was introduced to facilitate diagnosis using serum samples obtained from patients with no major abnormality, ABMR, and TCMR after kidney transplantation. Tissue biopsy and Banff score analysis were performed across the groups for validation, and 5 μL of serum obtained at the same time was added onto the Au–ZnO nanorod-based Surface-Enhanced Raman Scattering sensing chip to obtain Raman spectroscopy signals. The accuracy of machine learning algorithms for principal component-linear discriminant analysis and principal component-partial least squares discriminant analysis was 93.53% and 98.82%, respectively. The collagen (an indicative of kidney injury), creatinine, and amino acid-derived signals (markers of kidney function) contributed to this accuracy; however, the high accuracy was primarily due to the ability of the system to analyze a broad spectrum of various biomarkers.

A SERS-based point-of-care testing approach for efficient determination of diquat and paraquat residues using a flexible silver flower-coated melamine sponge

Diquat (DQ) and paraquat (PQ) residues in food are potential hazards to consumers' health. Point-of-care testing (POCT) of them remains challenging. Based on surface-enhanced Raman spectroscopy (SERS) technology, we developed a POCT strategy for DQ and PQ on apple surface and in apple juice. A point-of-use composite was fabricated using a piece of porous melamine sponge (MS) modified with silver nanoflowers (AgNFs), combining the specificity of the SERS fingerprint and the excellent adsorption capacity of MS. Using this dual-functional AgNFs@MS, the on-site determination of the DQ and PQ residues was completed within 3 min without pretreatment. Clear trends were observed between SERS intensity and logarithmic concentrations, with r values from 0.962 to 0.984. The limit of detection of DQ and PQ were 0.14–0.70 ppb in apple juice and on apple surface. This study provides a new point-of-use alternative for rapidly detecting DQ and PQ residues in nonlaboratory settings.

A Miniaturized Endoscopic Device Integrating Raman Spectroscopy and Laser Speckle Technology Via an Image Fusion Algorithm for Intraoperative Identification and Functional Protection of Parathyroid Glands

Abstract The importance of parathyroid glands (PGs) protection is increasingly recognized by thyroid surgeons in the field of minimally invasive video-assisted thyroidectomy (MIVAT). However, current techniques for intra-operative identification and vascularity assessment of the PGs are contentious and complex. This study presents the design and validation of a miniaturized device for fusion near-infrared autofluorescence (NIRAF) based on Raman spectroscopy and laser speckle contrast imaging (LSCI) via an image fusion algorithm for functional protection of PGs in the MIVAT. Our light source components include an integrated light emitting diode (LED) light source fiber, an NIRAF optical fiber, an acquisition optical fiber, and a laser speckle optical fiber in the endoscopic system to achieve identification and vascularity assessment of PGs using a single endoscopic probe. It has been validated in ex vivo tissue experiments that the fluorescence intensity detected by the device was equivalent to that of the marker indocyanine green (ICG) in visual images and superior to that of the thyroid and all other tissues in the neck. Based on clinical studies, MIVAT using functional fluorescence endoscopy, compared with the White light pattern group, the NIRAF combined with LSCI modality group increased the number of intra-operative confirmations of the PGs (P < 0.001), declined the decrease in parathyroid hormone (PTH) (P < 0.05) and calcium levels (P < 0.05) on the first postoperative day, and reduced the incidence of symptomatic hypocalcemia (P < 0.05). Our device may reduce the incidence of postoperative permanent hypoparathyroidism. Application of an miniaturized functional fluorescence endoscope for real-time and label-free PGs identification and vascularity assessment in MIVAT could be realized.

Non-invasive screening and subtyping for breast cancer by serum SERS combined with LGB-DNN algorithms

Early detection of breast cancer and its molecular subtyping is crucial for guiding clinical treatment and improving survival rate. Current diagnostic methods for breast cancer are invasive, time consuming and complicated. In this work, an optical detection method integrating surface-enhanced Raman spectroscopy (SERS) technology with feature selection and deep learning algorithm was developed for identifying serum components and building diagnostic model, with the aim of efficient and accurate noninvasive screening of breast cancer. First, the high quality of serum SERS spectra from breast cancer (BC), breast benign disease (BBD) patients and healthy controls (HC) were obtained. Chi-square tests were conducted to exclude confounding factors, enhancing the reliability of the study. Then, LightGBM (LGB) algorithm was used as the base model to retain useful features to significantly improve classification performance. The DNN algorithm was trained through backpropagation, adjusting the weights and biases between neurons to improve the network's predictive ability. In comparison to traditional machine learning algorithms, this method provided more accurate information for breast cancer classification, with classification accuracies of 91.38 % for BC and BBD, and 96.40 % for BC, BBD, and HC. Furthermore, the accuracies of 90.11 % for HR+/HR- and 88.89 % for HER2+/HER2- can be reached when evaluating BC patients' molecular subtypes. These results demonstrate that serum SERS combined with powerful LGB-DNN algorithm would provide a supplementary method for clinical breast cancer screening.

Simultaneous detection of multiple aging characteristic components in oil-paper insulation using sensitive Raman technology and microfluidics

The aging characteristic components of oil-paper insulation reflect the aging status of the power equipment. In this study, we designed a novel microfluidic chip capable of automatic and rapid extraction of aging components from insulating oil. Combined with Raman spectroscopy technology, it enables simultaneous detection of various aging components. By optimizing the microfluidic chip structural and adopting an optical window encapsulation, it eliminates interference from the Polydimethylsiloxane (PDMS). Measurements and analyses were carried out on multiple oil samples containing three aging products (furfural, acetone, and methanol). The results indicate that this novel microfluidic chip facilitates simultaneous detection of multiple components, significantly improving the detection sensitivity of complex oil. The detection limits for furfural, acetone, and methanol in insulating oil are 0.43 mg/L, 1.04 mg/L, and 2.31 mg/L, respectively. This provides a new approach for the online detection of oil-paper insulation equipment.

Synergistic effects and competitive relationships between DOC and DOX as acting on DNA molecules: Studied with confocal Raman spectroscopy and molecular docking technology

Docetaxel (DOC) is one of the second-generation antineoplastic drugs of the taxanes family with excellent antitumor activity. However, the mechanism of DOC inducing tumor cell apoptosis and treating cancer diseases, especially its interaction with DNA in the nucleus, and its adjuvant or combined Doxorubicin (DOX) acting on DNA molecules are unclear. In this study, the interaction mechanism between DOC and DNA, as well as the synergistic effects and competitive relationships among DOC and DOX when they simultaneously interact with DNA molecules were studied by laser confocal Raman spectroscopy combined with UV–visible absorption spectroscopy and molecular docking technology. The spectroscopic results showed that the binding constant of DOC to DNA is 5.25 × 103 M−1, the binding modes of DOC and DNA are non-classical intercalation and electrostatic binding, and the DNA-DOC complex has good stability. When DOC or DOX interacts with DNA alone, both of them can bind with bases and phosphate backbone of DNA, and also lead to DNA conformation changes; when DOC and DOX interact with DNA at the same time, the orders of interaction not only affect their binding sites with DNA, but also cause changes in the surrounding environment of the binding sites. In addition, the molecular docking results further verified that DOC and DOX have synergy and competition when they interact with DNA molecules simultaneously. The docking energies of DNA-DOC and DNA-DOX indicate the important role of van der Waals forces and hydrogen bonds. This study has practical significance for the design and development of antitumor drugs with less toxic based on the taxanes family and the combination with other drugs for the treatment of cancer.

A breakthrough in phytochemical profiling: ultra-sensitive surface-enhanced Raman spectroscopy platform for detecting bioactive components in medicinal and edible plants.

A perennial challenge in harnessing the rich biological activity of medicinal and edible plants is the accurate identification and sensitive detection of their active compounds. In this study, an innovative, ultra-sensitive detection platform for plant chemical profiling is created using surface-enhanced Raman spectroscopy (SERS) technology. The platform uses silver nanoparticles as the enhancing substrate, excess sodium borohydride prevents substrate oxidation, and methanol enables the tested molecules to be better adsorbed onto the silver nanoparticles. Subsequently, nanoparticle aggregation to form stable "hot spots" is induced by Ca2+, and the Raman signal of the target molecule is strongly enhanced. At the same time, deuterated methanol was used as the internal standard for quantitative determination. The method has excellent reproducibility, RSD ≤ 1.79%, and the enhancement factor of this method for the detection of active ingredients in the medicinal plant Coptis chinensis was 1.24 × 109, with detection limits as low as 3 fM. The platform successfully compared the alkaloid distribution in different parts of Coptis chinensis: root > leaf > stem, and the difference in content between different batches of Coptis chinensis decoction was successfully evaluated. The analytical technology adopted by the platform can speed up the determination of Coptis chinensis and reduce the cost of analysis, not only making better use of these valuable resources but also promoting development and innovation in the food and pharmaceutical industries. This study provides a new method for the development, evaluation, and comprehensive utilization of both medicinal and edible plants. It is expected that this method will be extended to the modern rapid detection of other medicinal and edible plants and will provide technical support for the vigorous development of the medicinal and edible plants industry.

SERS-Based Microneedle Biosensor for In Situ and Sensitive Detection of Tyrosinase.

Tyrosinase (TYR) emerges as a key enzyme that exerts a regulatory influence on the synthesis of melanin, thereby assuming the role of a critical biomarker for the detection of melanoma. Detecting the authentic concentration of TYR in the skin remains a primary challenge. Distinguished from ex vivo detection methods, this study introduces a novel sensor platform that integrates a microneedle (MN) biosensor with surface-enhanced Raman spectroscopy (SERS) technology for the in situ detection of TYR in human skin. The platform utilized dopamine (DA)-functionalized gold nanoparticles (Au NPs) as the capturing substrate and 4-mercaptophenylboronic acid (4-MPBA)-modified silver nanoparticles (Ag NPs) acting as the SERS probe. Here, the Au NPs were functionalized with mercaptosuccinic acid (MSA) for DA capture. In the presence of TYR, DA immobilized on the MN is preferentially oxidized to dopamine quinone (DQ), a process that results in a decreased density of SERS probes on the platform. TYR concentration was detected through variations in the signal intensity emitted by the phenylboronic acid. The detection system was able to evaluate TYR concentrations within a linear range of 0.05 U/mL to 200 U/mL and showed robust anti-interference capabilities. The proposed platform, integrating MN-based in situ sensing, SERS technology, and TYR responsiveness, holds significant importance for diagnosing cutaneous melanoma.

Application of one-dimensional hierarchical network assisted screening for cervical cancer based on Raman spectroscopy combined with attention mechanism

Cervical cancer is one of the most common malignant tumors among women, and its pathological change is a relatively slow process. If it can be detected in time and treated properly, it can effectively reduce the incidence rate and mortality rate of cervical cancer, so the early screening of cervical cancer is particularly critical and significant. In this paper, we used Raman spectroscopy technology to collect the tissue sample data of patients with cervicitis, Low-grade Squamous Intraepithelial Lesion, High-grade Squamous Intraepithelial Lesion, Well differentiated squamous cell carcinoma, Moderately differentiated squamous cell carcinoma, Poorly differentiated squamous cell carcinoma and cervical adenocarcinoma. A one-dimensional hierarchical convolutional neural network based on attention mechanism was constructed to classify and identify seven types of tissue samples. The attention mechanism Efficient Channel Attention Networks module and Squeeze-and-Excitation Networks module were combined with the established one-dimensional convolutional hierarchical network model, and the results showed that the combined model had better diagnostic performance. The average accuracy, F1, and AUC of the Principal Component Analysis-Squeeze and Excitation-hierarchical network model after 5-fold cross validations could reach 96.49%±2.12%, 0.97±0.03, and 0.98±0.02, respectively, which were 1.58%, 0.0140, and 0.008 higher than those of hierarchical network. The recall rate of the Principal Component Analysis-Efficient Channel Attention-hierarchical network model was as high as 96.78%±2.85%, which is 1.47% higher than hierarchical network. Compared with the classification results of traditional CNN and ResNet for seven types of cervical cancer staging, the accuracy of the Principal Component Analysis-Squeeze and Excitation-hierarchical network model is 3.33% and 11.05% higher, respectively. The experimental results indicate that the model established in this study is easy to operate and has high accuracy. It has good reference value for rapid screening of cervical cancer, laying a foundation for further research on Raman spectroscopy as a clinical diagnostic method for cervical cancer.

Escherichia coli research on Raman measurement mechanism and diagnostic model

Escherichia coli (E. coli) is one of the most important pathogenic bacteria causing poultry diseases, characterized by a wide distribution range, rapid spread, and high mortality rate. Early diagnosis of E. coli in poultry feces provides the possibility for targeted treatment and rapid recovery of diseased poultry, and more importantly, prevents the rapid spread of pathogens among densely bred poultry. In order to implement rapid, low-cost, and high-frequency detection of E. coli, this study explored the feasibility of Raman spectroscopy. Firstly, theoretical configurations and density functional calculations of N-acetylmuramic acid and N-acetylglucosamine in the cell wall of E. coli were performed. Then, Raman measurement models for E. coli were established based on two feature extraction methods (Successive Projections Algorithm, Competitive Adaptive Reweighted Sampling) and four modeling methods (Random Forest Algorithm, Convolutional Neural Networks, Back Propagation Neural Networks, Radial Basis Function). Finally, a method based on the extraction of Raman spectral features using density functional theory was determined to optimize the existing models, and it was demonstrated that this feature variable extraction method improved the accuracy of all four measurement models to some extent. Ultimately, the optimal model, the improved SPA-RF, was obtained through comparative analysis, with an accuracy, precision, recall, specificity, FNR, FDR, and AUC of 98.38%, 98.61%, 99.83%, 88.08%, 0.81%, 11.82%, and 1, respectively. This study reports an early method for the early treatment of E. coli diseases and provides a molecular structure database for studying N-acetylmuramic acid and N-acetylglucosamine, as well as a basis for vibrational spectroscopy detection of E. coli diseases, promoting the application of Raman spectroscopy technology in the diagnosis of livestock diseases.

Surface Enhanced Raman Spectroscopy Application of Aluminum Nanofilm in Improving the Performance of Optical Telescopes

Optical telescopes play a crucial role in exploring the universe, and understanding various aspects of the Earth and the universe. However, traditional optical telescopes have problems with high noise in the optical signal, which is not conducive to material analysis. To improve the performance of optical telescopes, this study utilized surface enhanced Raman spectroscopy technology of aluminum nanofilms for spectral analysis. The experimental results demonstrated that the amorphous aluminum film prepared by UV annealing exhibited Raman spectral enhancement effect at different laser wavelengths. The optimal effect can be achieved by using excitation light with a wavelength of 670 nm. The transmittance curve modified by aluminum nanofilm met the requirements of a day blind ultraviolet detector. Moreover, the bandgap energy gap was approximately 5 eV. The detector with a 7 nm aluminum deposition had the best performance improvement. The modification of aluminum nanoparticles improves the photoelectric response and reduces the time constant of the slow response stage. This study provides a foundation for further exploration and application of surface enhanced Raman spectroscopy technology in improving the performance of optical telescopes.

Covalent organic frameworks modified with silver nanoparticles as substrates for label-free SERS detection of fungicides

AbstractDespite prohibition in many countries, malachite green (MG) and crystal violet (CV) are illegally used in aquaculture, endangering both human health and the environment. Therefore, it is crucial to develop a method to accurately detect MG and CV. Surface-enhanced Raman spectroscopy (SERS) technology based on noble metal materials has attracted considerable attention for detecting food contaminations. However, noble metal materials are of poor stability and have a very low affinity for organic molecules. Herein, in this study, covalent organic frameworks (COFs) modified with silver nanoparticles (Ag NPs) were used as SERS substrates for the adsorption and detection of fungicides. COFs prepared by the Schiff base reaction of 1,3,5-tris (4-aminophenyl) benzene (TAPB) and 2,5-dimethoxybenzene-1,4-dicarboxaldehyde (DMTA) had a huge specific surface area and could provide sufficient adsorption sites and Ag NPs grown on the surface of COFs not only generated dense SERS “hot spots” but also improved their stability. The results showed that COF@Ag NPs exhibited a high enhancement factor (1.4 × 106), high reproducibility (RSD = 6.18%), and good stability within 50 days (RSD = 8.88%). Regression analyses in the ranges of 0.0001–10.0 mg/L and 0.0002–10.0 mg/L showed that the limits of detection (LOD) for the standard solutions of MG and CV were 3.8 × 10−5 mg/L and 1.8 × 10−5 mg/L, respectively. Furthermore, for MG and CV in fish samples, significant recoveries of 90.83–107.91% and 98.60–116.69% were achieved. Hence, it is hoped that this work could expand the application of COF materials for trace detection in SERS analyses.

Developing a magnetic SERS nanosensor utilizing aminated Fe-Based MOF for ultrasensitive trace detection of organophosphorus pesticides in apple juice

The unreasonable use of organophosphorus pesticides leads to excessive pesticide residues in food, seriously threatening public health, and the potential of surface-enhanced Raman spectroscopy (SERS) technology, incorporating a metal–organic framework, is substantial for the rapid detection of trace pesticide residues. Here, a novel Fe3O4@NH2-MIL-101(Fe)@Ag (FNMA) SERS nanosensor was developed. Results indicated that the FNMA had a high enhancement factor of 1.53 × 108, a low limit of detection (LOD) of 4.55 × 10−12 M, and a relative standard deviation of 7.73 % for 4-nitrothiophenol, demonstrating its good SERS sensitivity and uniformity, and also possessed good storage stability for one month. In quantifying fenthion and methyl parathion in standard solutions and apple juice in the range of 0.05/0.02–20 mg/L, it showed LODs of 3.02 × 10−3 mg/L and 1.43 × 10−3 mg/L, and 0.0407 and 0.0075 mg/L, respectively, demonstrating potentials in ultrasensitive trace detection of pesticides in food.

Machine learning-based exosome profiling of multi-receptor SERS sensors for differentiating adenocarcinoma in situ from early-stage invasive adenocarcinoma

Exosomes, extracellular vesicles released by cells, hold potential as diagnostic markers for the early detection of lung cancer. Despite their clinical promise, current technologies lack rapid and effective means to discriminate between exosomes derived from adenocarcinoma in situ (AIS) and early-stage invasive adenocarcinoma (IAC). This challenge arises from the intrinsic structural heterogeneity of exosomes, necessitating the development of advanced methodologies for precise differentiation. Here, we demonstrate a novel approach for plasma exosome detection utilizing multi-receptor surface-enhanced Raman spectroscopy (SERS) technology to differentiate between AIS and early-stage IAC. To accomplish this, we synthesized a stable and uniform two-dimensional SERS substrate (BC/Au NPs film) by fabricating gold nanoparticles onto bacterial cellulose. We then enhanced its capabilities by introducing multi-receptor SERS functionality via modifying the substrate with both low-specificity and physicochemical-selective molecules. Furthermore, by strategically combining all capturer-exosome SERS spectra, comprehensive “combined-SERS spectra” are reconstructed to enhance spectral variations of the exosome. Combining these features with partial least squares regression-discriminant analysis (PLS-DA) modeling significantly improved discriminatory accuracy, achieving 90% sensitivity and 95% specificity in distinguishing AIS from early-stage IAC. Our developed SERS sensor provides an effective method for early detection of lung cancer, thereby paving a new way for innovative advancements in diagnosing lung cancer.

Raman spectroscopy combined with multivariate statistical algorithms for the simultaneous screening of cervical and breast cancers.

Breast and cervical cancers are becoming the leading causes of death among women worldwide, but current diagnostic methods have many drawbacks, such as being time-consuming and high cost. Raman spectroscopy, as a rapid, reliable, and non-destructive spectroscopic detection technique, has achieved many breakthrough results in the screening and prognosis of various cancer tumors. Therefore, in this study, Raman spectroscopy technology was used to diagnose breast cancer and cervical cancer. A total of 225 spectra were recorded from 87 patients with cervical cancer, 60 patients with breast cancer, and 78 healthy individuals. The obvious difference in Raman spectrum between the three groups was mainly shown at 809cm-1 (tyrosine), 958cm-1 (carotenoid), 1004cm-1 (phenylalanine), 1154cm-1 (β-carotene), 1267cm-1 (Amide III), 1445cm-1 (phospholipids), 1515cm-1 (β-carotene), and 1585cm-1 (C = C olefinic stretch). We used one-way analysis of variance for these peaks and demonstrated that they were significantly different. Then, we combined the detected Raman spectra with multivariate statistical calculations using the principal component analysis-linear discrimination algorithm (PCA-LDA) to discriminate between the three groups of collected serum samples. The diagnostic results showed that the model's accuracy, precision, recall, and F1 score of the model were 92.90%, 92.62%, 92.10%, and 92.36%, respectively. These results suggest that Raman spectroscopy can achieve ultra-sensitive detection of serum, and the developed diagnostic models have great potential for the prognosis and simultaneous screening of cervical and breast cancers.

Raman spectroscopy and fusion machine learning algorithm: A novel approach to identify dairy fraud

In addressing food safety verification, ensuring the authenticity of food labels remains of utmost importance. With the objective of enhancing label validation and fraud detection, our research introduces an innovative fusion model utilizing Raman spectroscopy technology. This model is uniquely designed to differentiate various dairy products and provide a quantitative assessment of their nutritional components. To achieve this, we integrated four foundational machine learning algorithms: Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), Random Forest (RF), and extreme Gradient Boosting (XGBoost). These algorithms individually showcased a classification accuracy exceeding 90% for differentiating dairy brands and achieved a fat prediction Normalized Root Mean Square Error (NRMSE) under 13%. However, when these algorithms were synergistically combined in our fusion model, we observed a remarkable improvement in classification accuracy, reaching 99%. Additionally, for the pivotal task of predicting fat content in dairy samples, the fusion model manifested an unparalleled performance, with metrics indicating R2 = 0.98, Root Mean Square Error (RMSE) = 0.2 g/100 mL, and NRMSE = 6.2%. Notably, while the efficiency of the individual models fluctuated depending on the training objectives, the fusion model consistently outperformed in all scenarios. In essence, our fusion model's adaptability, precision, and generalization capabilities underscore its potential as an invaluable tool in the domain of dairy product quality assessment.

Research Progress in Tumor Diagnosis Based on Raman Spectroscopy

Background: Cancer is a major disease that threatens human life and health. Raman spectroscopy can provide an effective detection method. Objective: The study aimed to introduce the application of Raman spectroscopy to tumor detection. We have introduced the current mainstream Raman spectroscopy technology and related application research. Methods: This article has first introduced the grim situation of malignant tumors in the world. The advantages of tumor diagnosis based on Raman spectroscopy have also been analyzed. Secondly, various Raman spectroscopy techniques applied in the medical field are introduced. Several studies on the application of Raman spectroscopy to tumors in different parts of the human body are discussed. Then the advantages of combining deep learning with Raman spectroscopy in the diagnosis of tumors are discussed. Finally, the related problems of tumor diagnosis methods based on Raman spectroscopy are pointed out. This may provide useful clues for future work. Conclusion: Raman spectroscopy can be an effective method for diagnosing tumors. Moreover, Raman spectroscopy diagnosis combined with deep learning can provide more convenient and accurate detection results.