Figure - available from: Biomedical Optics Express
This content is subject to copyright. Terms and conditions apply.
Source publication
In this paper, we investigated the feasibility of using surface enhanced Raman spectroscopy (SERS) and multivariate analysis method to discriminate liver cancer and nasopharyngeal cancer from healthy volunteers. SERS measurements were performed on serum protein samples from 104 liver cancer patients, 100 nasopharyngeal cancer patients, and 95 healt...
Similar publications
Aiming at the concrete compressive strength data measured in the field laboratory, the data samples are standardized and the missing and abnormal values of the data samples are detected and processed. Then, the principal component factors of several influencing factors are extracted with the idea of “dimensionality reduction” by principal component...
Citations
... Raman spectroscopy, relying on inelastic scattering of photons, attracts great interest for biomedical analysis, especially for cancer screening [6][7][8] . Currently, SERS also were used for detection of pathogenic bacteria. ...
Two types of pathogenic bacteria, Klebsiella pneumoniae and Serratia marcescens, had been reported as important causes of hospital-acquired infection. Rapid and accurate identification of Klebsiella pneumoniae and Serratia marcescens is vitally important for the selection of appropriate treatment modalities. In this article, the feasibility of using surface-enhanced Raman Spectroscopy (SERS) to identify Klebsiella pneumoniae and Serratia marcescens was explored. Spectrum samples were obtained from Klebsiella pneumoniae infections (n=1000) and Serratia marcescens infections (n=1000). The differences between the spectra of two types of pathogenic bacteria were also analyzed. Moreover, Principal Component Analysis- Linear Discriminant Analysis (PCA-LDA) algorithm was used to discriminate the spectra of pathogenic bacteria.
... Using PCA-PLS-DA modeling, the control, mild, and severe groups were confirmed to be divided as shown inFigure 7a. In particular, the PLS-DA approach generally performed better in finding the input variables that have the closest relationship to the output variables than in PCA, which simplifies the data set in Raman.51,52 To validate the performance, the PLS application was conducted using 50 principal components calculated from 40 samples from each of the control, mild, and severe atherosclerotic disease mice. ...
The direct preventative detection of flow‐induced atherosclerosis remains a significant challenge, impeding the development of early treatments and prevention measures. This study proposes a method for diagnosing atherosclerosis in the carotid artery using nanometer biomarker measurements through surface‐enhanced Raman spectroscopy (SERS) from single‐drop blood samples. Atherosclerotic acceleration is induced in apolipoprotein E knockout mice which underwent a partial carotid ligation and were fed a high‐fat diet to rapidly induce disturbed flow‐induced atherosclerosis in the left common carotid artery while using the unligated, contralateral right carotid artery as control. The progressive atherosclerosis development of the left carotid artery was verified by micro‐magnetic resonance imaging (micro‐MRI) and histology in comparison to the right carotid artery. Single‐drop blood samples are deposited on chips of gold‐coated ZnO nanorods grown on silicon wafers that filter the nanometer markers and provide strong SERS signals. A diagnostic classifier was established based on principal component analysis (PCA), which separates the resultant spectra into the atherosclerotic and control groups. Scoring based on the principal components enabled the classification of samples into control, mild, and severe atherosclerotic disease. The PCA‐based analysis was validated against an independent test sample and compared against the PCA‐PLS‐DA machine learning algorithm which is known for applicability to Raman diagnosis. The accuracy of the PCA modification‐based diagnostic criteria was 94.5%, and that of the machine learning algorithm 97.5%. Using a mouse model, this study demonstrates that diagnosing and classifying the severity of atherosclerosis is possible using a single blood drop, SERS technology, and machine learning algorithm, indicating the detectability of biomarkers and vascular factors in the blood which correlate with the early stages of atherosclerosis development.
... SERS-based optical sensing has been extensively investigated as a diagnostic technique for liver cancer. Multiple studies used serum as a test sample [70,76,77,[173][174][175]. While liver biopsies [176,177] and urine [152] were the samples of choice for a few others. ...
... The algorithm demonstrated a satisfactory accuracy level of 90.67%. Therefore, this method was proposed as a screening test not only for liver cancer but also for other types of cancer [174]. These results were further confirmed in a later study that used the same method on a smaller group of patients with liver cancer [178]. ...
... Later on, researchers investigated the combined use of Raman spectroscopy and chemometrics in the diagnosis of CLDs [111,120,121,170]. In the mean time, some research groups explored the use of SERS as a potential diagnostic tool for CLDs [69,79,174,175]. Recently published studies focused either on developing advanced SERS sensors to be used in the diagnosis of CLDs [70], or on investigating the potential use of SERS technology as prognostic tool to monitor the response of liver cancer patients to chemotherapy [180]. ...
Chronic liver diseases (CLDs) are a major public health problem. Despite the progress achieved in fighting against viral hepatitis, the emergence of non-alcoholic fatty liver disease might pose a serious challenge to the public's health in the coming decades. Medical management of CLDs represents a substantial burden on the public health infrastructures. The health care cost of these diseases is an additional burden that weighs heavily on the economies of developing countries. Effective management of CLDs requires the adoption of reliable and cost-effective screening and diagnosing methods to ensure early detection and accurate clinical assessment of these diseases. Vibrational spectroscopies have emerged as universal analytical methods with promising applications in various industrial and biomedical fields. These revolutionary analytical techniques rely on analyzing the interaction between a light beam and the test sample to generate a spectral fingerprint. This latter is defined by the analyte's chemical structure and the molecular vibrations of its functional groups. Raman spectroscopy and surface-enhanced Raman spectroscopy have been used in combination with various chemometric tests to diagnose a wide range of malignant, metabolic and infectious diseases. The aim of the current review is to cast light on the use of these optical sensing methods in the diagnosis of CLDs. The vast majority of research works that investigated the potential application of these spectroscopic techniques in screening and detecting CLDs were discussed here. The advantages and limitations of these modern analytical methods, as compared with the routine and gold standard diagnostic approaches, were also reviewed in details.
... Lin's final experimental results showed that the PLS-SVM method has excellent classification and prediction ability between different diseases, achieving an accuracy of 95.09 % in the experiments ( Figure 5). [85] LDA as a clustering method is also suitable for application in the classification of clinical diagnoses. Neagoe et al. used PCA-LDA to extract features and classify patients with breast cancer, colorectal cancer, lung cancer, ovarian cancer and oral cancer. ...
Surface‐enhanced Raman spectroscopy (SERS) has shown strength in non‐invasive, rapid, trace analysis and has been used in many fields in medicine. Machine learning (ML) is an algorithm that can imitate human learning styles and structure existing content with the knowledge to effectively improve learning efficiency. Integrating SERS and ML can have a promising future in the medical field. In this review, we summarize the applications of SERS combined with ML in recent years, such as the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi‐quantitative measurements. Ultimately, the possible opportunities and challenges of combining SERS with ML are addressed. ML to the help for SERS: Applications of Surface‐Enhanced Raman Spectroscopy (SERS) combined with Machine Learning (ML) in recent years are summarized in this review, including the recognition of biological molecules, rapid diagnosis of diseases, developing of new immunoassay techniques, and enhancing SERS capabilities in semi‐quantitative measurements.
... One of the advantages of conventional substrates such as AuNP and AgNP is they can be applied to differentiate between the various disorders and still maintain their high reliability. As an example, nasopharyngeal and liver cancer, and healthy species (overall 75 samples) were distinguished with an accuracy of 90.7% in the study conducted by Yun et al. employing AgNP as a SERS substrate [271]. Fang Yaping achieved 81.2% accuracy in differentiating the 7 different types of cancer cells in 350 samples by using gold nanoparticles for the SERS measurements [272]. ...
... All: 145 (75; 220). [271,283,[296][297][298][299][300] Note: The sensitivity/specificity/accuracy of the overall substrate group is presented in the following way: average (min; max). The number of samples: All samples (positive "+", negative "−"). ...
This article compares the applications of traditional gold and silver-based SERS substrates and less conventional (Pd/Pt, Cu, Al, Si-based) SERS substrates, focusing on sensing, biosensing, and clinical analysis. In recent decades plethora of new biosensing and clinical SERS applications have fueled the search for more cost-effective, scalable, and stable substrates since traditional gold and silver-based substrates are quite expensive, prone to corrosion, contamination and non-specific binding, particularly by S-containing compounds. Following that, we briefly described our experimental experience with Si and Al-based SERS substrates and systematically analyzed the literature on SERS on substrate materials such as Pd/Pt, Cu, Al, and Si. We tabulated and discussed figures of merit such as enhancement factor (EF) and limit of detection (LOD) from analytical applications of these substrates. The results of the comparison showed that Pd/Pt substrates are not practical due to their high cost; Cu-based substrates are less stable and produce lower signal enhancement. Si and Al-based substrates showed promising results, particularly in combination with gold and silver nanostructures since they could produce comparable EFs and LODs as conventional substrates. In addition, their stability and relatively low cost make them viable alternatives for gold and silver-based substrates. Finally, this review highlighted and compared the clinical performance of non-traditional SERS substrates and traditional gold and silver SERS substrates. We discovered that if we take the average sensitivity, specificity, and accuracy of clinical SERS assays reported in the literature, those parameters, particularly accuracy (93–94%), are similar for SERS bioassays on AgNP@Al, Si-based, Au-based, and Ag-based substrates. We hope that this review will encourage research into SERS biosensing on aluminum, silicon, and some other substrates. These Al and Si based substrates may respond efficiently to the major challenges to the SERS practical application. For instance, they may be not only less expensive, e.g., Al foil, but also in some cases more selective and sometimes more reproducible, when compared to gold-only or silver-only based SERS substrates. Overall, it may result in a greater diversity of applicable SERS substrates, allowing for better optimization and selection of the SERS substrate for a specific sensing/biosensing or clinical application.
... The first SERS report regarding the detection of cancer from blood plasma, investigated nasopharyngeal cancer [30]. Later, the detection of different cancer types with the technique was reported [31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49]. We also demonstrated that SERS could successfully differentiate cancerous tissues and cells from controls in our previous studies [50][51][52]. ...
Blood is a vital reservoir housing numerous disease-related metabolites and cellular components. Thus, it is also of interest for cancer diagnosis. Surface-enhanced Raman spectroscopy (SERS) is widely used for molecular detection due to its very high sensitivity and multiplexing properties. Its real potential for cancer diagnosis is not yet clear. In this study, using silver nanoparticles (AgNPs) as substrates, a number of experimental parameters and scenarios were tested to disclose the potential for this technique for cancer diagnosis. The discrimination of serum samples from cancer patients, healthy individuals and patients with chronic diseases was successfully demonstrated with over 90% diagnostic accuracies. Moreover, the SERS spectra of the blood serum samples obtained from cancer patients before and after tumor removal were compared. It was found that the spectral pattern for serum from cancer patients evolved into the spectral pattern observed with serum from healthy individuals after the removal of tumors. The data strongly suggests that the technique has a tremendous potential for cancer detection and screening bringing the possibility of early detection onto the table.
... [9][10][11][12] The feasibility of using serum SERS analysis to diagnose liver cancer and liver cirrhosis has also been investigated and results suggest that SERS combined with multivariate analysis might improve the diagnostic accuracy. 13,14 Recent studies suggest that the postoperative SERS evaluation of serum proteins might provide a new optical tool for prognostic analysis. 15,16 In this preliminary study, the feasibility of using SERS to identify biomarkers in the serum of HCC patients was investigated. ...
... 4,7,24 Early studies also suggest that it might be feasible to use serum SERS analysis for the diagnosis of liver cancer. 13,14 This study analyzed SERS spectra of serum samples of 25 HCC patients and 30 healthy adults. Results show that nanoAg-based SERS could identify many important biomolecules in serum samples (see Table 1). ...
Early diagnosis of liver cancer plays a significant role in reducing its high mortality. In this preliminary study, the feasibility of using serum surface-enhanced Raman spectroscopy (SERS) to identify liver cancer was studied. Serum samples were obtained from liver cancer patients and healthy controls. The differences between the SERS spectra of pre-operation and post-operation of liver cancer patients were also analyzed. The general shape and trend of SERS spectra of health control and liver cancer patients were similar. Multivariate analysis, e.g., PLS-SVM, might be useful for the discrimination of serum SERS spectra of pre-operation and post-operation.
... The confusion matrixes of the binary classification results based on the SVM algorithm are detailed in Tables 3-5. The performance of the above classification models was all evaluated using the LOOCV method, but the diagnostic ability of the classification algorithm can also be evaluated by the prediction accuracy of unknown test samples [30]. Thus, we further selected 10 samples from 96 samples for blind testing, including 3 healthy cases, 3 hysteromyoma cases, and 4 cervical cancer cases. ...
In this study, we investigated the feasibility of using surface-enhanced Raman spectroscopy (SERS) combined with a support vector machine (SVM) algorithm to discriminate hysteromyoma and cervical cancer from healthy volunteers rapidly. SERS spectra of serum samples were recorded from 30 hysteromyoma patients, 36 cervical cancer patients as well as 30 healthy subjects. SVM was used to establish the classification models, and three types of kernel functions, namely linear, polynomial, and Gaussian radial basis function (RBF), were utilized for comparison. When the polynomial kernel function was employed, the overall diagnostic accuracy for classifying the three groups could achieve 86.5%. In addition, when the optimal kernel function was selected, the diagnostic accuracy for identifying healthy versus hysteromyoma, healthy versus cervical cancer, and hysteromyoma versus cervical cancer reached 98.3%, 93.9%, and 90.9%, respectively. The current results indicate that serum SERS technology, together with the SVM algorithm, is expected to become a clinical tool for rapid screening of hysteromyoma and cervical cancer.
... 57,58 Yu et al. used PCA and partial least square (PLS)-SVM to investigate the differentiation of SERS spectral profiles from serum protein samples from 104 liver cancer patients, 100 nasopharyngeal cancer patients and 95 healthy volunteers. 56 Major vibrational bands were identified, including tryptophan at 760 (ring breathing), 878, 1340 (CH 2 /CH 3 wagging, twisting, and/or bending mode) and 1552 (C]C stretching mode) cm À1 . They found that the performance of the PLS-SVM algorithm to diagnosis cancer was better than when using PCA techniques. ...
Recently, machine learning algorithms have had major success in the interdisciplinary field of biophotonics, a field of science based on the interaction of light with biological systems. The use of machine learning in biophotonics has resulted in enhanced optical image reconstruction and classification, as well as increased interpretability of spectral data. Despite these advances, techniques which rely on biophotonics have grown so rapidly, particularly when used in the assessment and detection of disease that the use of machine learning has not yet caught up. Indeed this drawback is due to the emerging field of biophotonics but it is also due, in part, to the evolving, underlying changes within machine learning algorithms. In this chapter, key mathematical principles behind several popular machine learning algorithms are discussed, in the hopes of better understanding these algorithms, while highlighting key limitations to their use. Finally, the use of machine learning in biophotonics and disease, specifically in optical spectroscopy (fluorescence and Raman spectroscopy) is discussed. Optical spectroscopy, based on the key biomolecule tryptophan has been utilized in the assessment of diseases such as breast cancer and Alzheimer’s disease. There is immense potential to utilize machine learning algorithms in biophotonics to enhance optical modalities and advance disease diagnosis and assessment. Machine learning algorithms and the optical properties of tryptophan may provide a powerful tool in the assessment of disease.
... Two papers, Li et al. [99] and Yu et al. [100] investigated the application of SERS using silver nanoparticles to serum samples from patients with liver diseases. Li et al. [99] used SERS to discriminate between 44 healthy patients, 45 liver cancer patients, 42 post-treatment liver cancer patients and 45 liver cirrhosis patients. ...
... The SERS spectra were subjected to SVM, PLS and artificial neural networks, which resulted in accuracies of 92%, 89% and 90% respectively. Yu et al. [100] also used SERS on blood serum however applied this approach to a different cohort with 104 healthy volunteers, 104 liver cancer patients and 100 nasopharyngeal patients. SERS spectra were acquired using laser at 785 nm at 0.1mW with a 10 second acquisition time and subjected to either PLS or PCA for dimensionality reduction which were then used in SVM with a Gaussian radio basis function. ...
Analytical technologies that can improve disease diagnosis are highly sought after. Current screening/diagnostic tests for several diseases are limited by their moderate diagnostic performance, invasiveness, costly and laborious methodologies or the need for multiple tests before a definitive diagnosis. Spectroscopic techniques, including infrared (IR) and Raman, have attracted great interest in the medical field, with applications expanding from early disease detection to monitoring and real-time diagnosis. This review highlights applications of IR and Raman spectroscopy, with a focus on cancer and infectious diseases since 2015, and underscores the diverse sample types that can be analyzed, such as biofluids, cells and tissues. Studies involving more than 25 participants per group (disease and control group; if no control group >25 in disease group) were considered eligible, to retain the clinical focus of the paper. Following literature searches, we identified 94 spectroscopic studies on different cancers and 30 studies on infectious diseases. The review suggests that such technologies have the potential to develop into
an objective, inexpensive, point-of-care test or facilitate disease diagnosis and monitoring. Up-to-date considerations for the implementation of spectroscopic techniques into a clinical setting, health economics and successful applications of vibrational spectroscopic tests in the clinical arena are also discussed.
