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

Comparative study of Raman spectroscopy techniques in blood plasma-based clinical diagnostics: A demonstration on Alzheimer's disease

Nowadays, there are still many diseases with limited or no reliable methods of early diagnosis. A popular approach in clinical diagnostic research is Raman spectroscopy, as a relatively simple, cost-effective, and high-throughput method for searching for disease-specific alterations in the composition of blood plasma. However, the high variability of the experimental designs, targeted diseases, or statistical processing in the individual studies makes it challenging to compare and compile the results to critically assess the applicability of Raman spectroscopy in real clinical practice. This study aimed to compare data from a single series of blood plasma samples of patients with Alzheimer's disease and non-demented elderly controls obtained by four different techniques/experimental setups - Raman spectroscopy with excitation at 532 and 785 nm, Raman optical activity, and surface-enhanced Raman scattering spectroscopy. The obtained results showed that the spectra from each Raman spectroscopy technique contain different information about biomolecules of blood plasma or their conformation and may, therefore, offer diverse points of view on underlying biochemical processes of the disease. The classification models based on the datasets generated by the three non-chiroptical variants of Raman spectroscopy exhibited comparable diagnostic performance, all reaching an accuracy close to or equal to 80%. Raman optical activity achieved only 60% classification accuracy, suggesting its limited applicability in the specific case of Alzheimer's disease diagnostics. The described differences in the outputs of the four utilized techniques/setups of Raman spectroscopy imply that their choice may crucially affect the acquired results and thus should be approached carefully concerning the specific purpose.

An adaptive extended Gaussian peak derivative reweighted penalised least squares method for baseline correction

Baseline drift is an important issue in spectral analysis (e.g., infrared, Raman, and laser-induced spectroscopy). Most common methods for baseline correction perform poorly in high noise, complex baselines, and overlapping peaks. To solve this problem, we proposed an adaptive extended Gaussian peak derivative reweighted penalised least squares (agdPLS) method for removing baseline drift from spectra. The method added extended Gaussian peaks to spectra, added derivative terms for spectral and baseline differences during iterations, and adaptively adjusted penalty coefficients λ. Experiments with simulated and measured spectra for methane and ethane were carried out to compare the performance of the different methods. agdPLS performed better than the other methods, with more accurate baseline estimation in low- and high-noise situations. Especially when the spectrum contained high noise, complex baselines and overlapping peaks, the agdPLS method performed significantly better than other methods. Moreover, agdPLS was computationally efficient. Results of actual spectral experiments showed that the proposed agdPLS method could be effective for baseline correction of spectra which, in turn, improved qualitative and quantitative spectral performances.

Application of serum Raman spectroscopy combined with classification model for rapid breast cancer screening

Introduction

This study aimed to evaluate the feasibility of using general Raman spectroscopy as a method to screen for breast cancer. The objective was to develop a machine learning model that utilizes Raman spectroscopy to detect serum samples from breast cancer patients, benign cases, and healthy subjects, with puncture biopsy as the gold standard for comparison. The goal was to explore the value of Raman spectroscopy in the differential diagnosis of breast cancer, benign lesions, and healthy individuals.

Methods

In this study, blood serum samples were collected from a total of 333 participants. Among them, there were 129 cases of tumors (pathologically diagnosed as breast cancer and labeled as cancer), 91 cases of benign lesions (pathologically diagnosed as benign and labeled as benign), and 113 cases of healthy controls (labeled as normal). Raman spectra of the serum samples from each group were collected. To classify the normal, benign, and cancer sample groups, principal component analysis (PCA) combined with support vector machine (SVM) was used. The SVM model was evaluated using a cross-validation method.

Results

The results of the study revealed significant differences in the mean Raman spectra of the serum samples between the normal and tumor/benign groups. Although the mean Raman spectra showed slight variations between the cancer and benign groups, the SVM model achieved a remarkable prediction accuracy of up to 98% for classifying cancer, benign, and normal groups.

Discussion

In conclusion, this exploratory study has demonstrated the tremendous potential of general Raman spectroscopy as a clinical adjunctive diagnostic and rapid screening tool for breast cancer.

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

This paper comments recent findings about Raman spectroscopy application for breast cancer detection published in the Photodiagnosis and Photodynamic Therapy journal by Li et al. Despite the high performance of the proposed approach for breast cancer detection by means of Raman spectroscopy analysis of serum, the proposed results may be ambiguous due to overestimation of classification models.