Multi-branch attention Raman network and surface-enhanced Raman spectroscopy for the classification of neurological disorders.

Surface-enhanced Raman spectroscopy (SERS), a rapid, low-cost, non-invasive, ultrasensitive, and label-free technique, has been widely used in-situ and ex-situ biomedical diagnostics questions. However, analyzing and interpreting the untargeted spectral data remains challenging due to the difficulty of designing an optimal data pre-processing and modelling procedure. In this paper, we propose a Multi-branch Attention Raman Network (MBA-RamanNet) with a multi-branch attention module, including the convolutional block attention module (CBAM) branch, deep convolution module (DCM) branch, and branch weights, to extract more global and local information of characteristic Raman peaks which are more distinctive for classification tasks. CBAM, including channel and spatial aspects, is adopted to enhance the distinctive global information on Raman peaks. DCM is used to supplement local information of Raman peaks. Autonomously trained branch weights are applied to fuse the features of each branch, thereby optimizing the global and local information of the characteristic Raman peaks for identifying diseases. Extensive experiments are performed for two different neurological disorders classification tasks via untargeted serum SERS data. The results demonstrate that MBA-RamanNet outperforms commonly used CNN methods with an accuracy of 88.24% for the classification of healthy controls, mild cognitive impairment, Alzheimer's disease, and Non-Alzheimer's dementia; an accuracy of 90% for the classification of healthy controls, elderly depression, and elderly anxiety.

Raman spectromics method for fast and label-free genotype screening.

It is now understood that genes and their various mutations are associated with the onset and progression of diseases. However, routine genetic testing techniques are limited by their high cost, time consumption, susceptibility to contamination, complex operation, and data analysis difficulties, rendering them unsuitable for genotype screening in many cases. Therefore, there is an urgent need to develop a rapid, sensitive, user-friendly, and cost-effective method for genotype screening and analysis. In this study, we propose and investigate a Raman spectroscopic method for achieving fast and label-free genotype screening. The method was validated using spontaneous Raman measurements of wild-type Cryptococcus neoformans and its six mutants. An accurate identification of different genotypes was achieved by employing a one-dimensional convolutional neural network (1D-CNN), and significant correlations between metabolic changes and genotypic variations were revealed. Genotype-specific regions of interest were also localized and visualized using a gradient-weighted class activation mapping (Grad-CAM)-based spectral interpretable analysis method. Furthermore, the contribution of each metabolite to the final genotypic decision-making was quantified. The proposed Raman spectroscopic method demonstrated huge potential for fast and label-free genotype screening and analysis of conditioned pathogens.

Identification of late-life depression and mild cognitive impairment via serum surface-enhanced Raman spectroscopy and multivariate statistical analysis.

Identification of age-related neuropsychiatric disorders, i.e., late-life depression (LDD) and mild cognitive impairment (MCI) is of imperative clinical value considering the large probability of misdiagnosis and current lack of sensitive, non-invasive and low-cost diagnostic approaches. Here, the serum surface-enhanced Raman spectroscopy (SERS) technique is proposed to identify healthy controls, LDD and MCI patients. Based on SERS peaks analysis, abnormal levels of ascorbic acid, saccharide, cell-free DNA and amino acids in serum are found to be potential biomarkers for identifying LDD and MCI. These biomarkers might be related to oxidative stress, nutritional status, lipid peroxidation and metabolic abnormalities. Moreover, partial least square analysis-linear discriminant analysis (PLS-LDA) is applied to those collected SERS spectra. Finally, the overall identification accuracy is 83.2%, and accuracies are 91.6% and 85.7% for differentiating healthy versus neuropsychiatric disorders and LDD versus MCI, respectively. Thus, the serum SERS combined with multivariate statistical analysis has proved its successful potential for rapid, sensitive and non-invasive identification of healthy, LDD and MCI, which may open new avenues for early diagnosis and timely intervention for age-related neuropsychiatric disorders.

Rapid and precise detection of cancers via label-free SERS and deep learning.

Early, express, and reliable detection of cancer can provide a favorable prognosis and decrease mortality. Tumor biomarkers have been proven to be closely related to tumor occurrence and development. Conventional tumor biomarker detection based on genomic, proteomic, and metabolomic methods is time and equipment-consuming and always needs a specific target marker. Surface-enhanced Raman scattering (SERS), as a non-invasive ultrasensitive and label-free vibrational spectroscopy technique, can detect cancer-related biomedical changes in biofluids. In this paper, 110 serum samples were collected from 30 healthy controls and 80 cancer patients (including 30 bladder cancer (BC), 30 adrenal cancer (AC), and 20 acute myeloid leukemia (AML)). One microliter of blood serum was mixed with 1 µl silver colloid and then was air-dried for SERS measurements. After spectral data augmentation, one-dimensional convolutional neural network (1D-CNN) was proposed for precise and rapid identification of healthy and three different cancers with high accuracy of 98.27%. After gradient-weighted class activation mapping (Grad-CAM) based spectral interpretation, the contributions of SERS peaks corresponding to biochemical substances indicated the most potential biomarkers, i.e., L-tyrosine in bladder cancer; acetoacetate and riboflavin in adrenal cancer and phospholipids, amide-I, and α-Helix in acute myeloid leukemia, which might provide an insight into the mechanism of intelligent diagnosis of different cancers based on label-free serum SERS. The integration of label-free SERS and deep learning has great potential for the rapid, reliable, and non-invasive detection of cancers, which may significantly improve the precise diagnosis in clinical practice.