Rapid identification of ore minerals using multi-scale dilated convolutional attention network associated with portable Raman spectroscopy

An effective deep learning fusion method for predicting the TVB-N and TVC contents of chicken breasts using dual hyperspectral imaging systems

Total volatile basic nitrogen (TVB-N) and total viable count (TVC) are important freshness indicators of meat. Hyperspectral imaging combined with chemometrics has been proven to be effective in meat detection. However, a challenge with chemometrics is the lack of a universally applicable processing combination, requiring trial-and-error experiments with different datasets. This study proposes an end-to-end deep learning model, pyramid attention features fusion model (PAFFM), integrating CNN, attention mechanism and pyramid structure. PAFFM fuses the raw visible and near-infrared range (VNIR) and shortwave near-infrared range (SWIR) spectral data for predicting TVB-N and TVC in chicken breasts. Compared with the CNN and chemometric models, PAFFM obtains excellent results without a complicated processing combinatorial optimization process. Important wavelengths that contributed significantly to PAFFM performance are visualized and interpreted. This study offers valuable references and technical support for the market application of spectral detection, benefiting related research and practical fields.

Unsupervised and interpretable discrimination of lithium-bearing minerals with Raman spectroscopy imaging

As lithium-bearing minerals become critical raw materials for the field of energy storage and advanced technologies, the development of tools to accurately identify and differentiate these minerals is becoming essential for efficient resource exploration, mining, and processing. Conventional methods for identifying ore minerals often depend on the subjective observation skills of experts, which can lead to errors, or on expensive and time-consuming techniques such as Inductively Coupled Plasma Mass Spectrometry (ICP-MS) or Optical Emission Spectroscopy (ICP-OES). More recently, Raman Spectroscopy (RS) has emerged as a powerful tool for characterizing and identifying minerals due to its ability to provide detailed molecular information. This technique excels in scenarios where minerals have similar elemental content, such as petalite and spodumene, by offering distinct vibrational information that allows for clear differentiation between such minerals. Considering this case study and its particular relevance to the lithium-mining industry, this manuscript reports the development of an unsupervised methodology for lithium-mineral identification based on Raman Imaging. The deployed machine-learning solution provides accurate and interpretable results using the specific bands expected for each mineral. Furthermore, its robustness is tested with additional blind samples, providing insights into the unique spectral signatures and analytical features that enable reliable mineral identification.

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.

TriFNet: A triple-branch feature fusion network for pH determination by surface-enhanced Raman spectroscopy

Due to the acidic tumor microenvironment caused by metabolic changes in tumor cells, the accurate pH detection of extracellular fluid is helpful for doctors in precise tumor resection. The combination of Raman spectroscopy and deep learning provides a solution for pH detection. However, most existing studies use one-dimensional convolutional neural networks (1D-CNNs) for spectral analysis, which limits the performance due to insufficient feature extraction. In this work, we propose a 2D triple-branch feature fusion network (TriFNet) for accurate pH determination using surface-enhanced Raman spectra (SERS). Specifically, we design a triple-branch network structure by converting Raman spectra into three types of images to extensively extract complex patterns in spectra. In addition, an attention fusion module, which leverages the complementarity among features in both space and channel, is designed to obtain the valuable information, achieving further accurate pH determination. On our Raman spectral dataset containing 14,137 samples, we achieved mean absolute error (MAE) of 0.059, standard deviation of the absolute error (SD) of 0.07, root mean squared error (RMSE) of 0.092, and coefficient of determination (R2) of 0.991 on the test set. Compared with other published methods, the four metrics showed an average improvement of 47%, 39%, 43%, and 6%, respectively. In addition, visualization validates the diagnostic capability of our model to correlate with biomolecular signatures. Meanwhile, our model has robustness to different SERS chips. These results prove the potential of our method to develop an effective technology based on Raman spectroscopy for accurate pH determination to guide surgery.

An integrated computational pipeline for machine learning-driven diagnosis based on Raman spectra of saliva samples

Raman Spectroscopy promises the ability to encode in spectral data the significant differences between biological samples belonging to patients affected by a disease and samples of healthy patients (controls). However, the decoding and interpretation of the Raman spectral fingerprint is still a difficult and time-consuming procedure even for domain experts. In this work, we test an end-to-end deep-learning diagnostic pipeline able to classify spectral data from saliva samples. The pipeline has been validated against the SARS-COV-2 Infection and for the screening of neurodegenerative diseases such as Parkinson's and Alzheimer's diseases. The proposed system can be used for the fast prototyping of promising non-invasive, cost and time-efficient diagnostic screening tests.

Stratification of tumour cell radiation response and metabolic signatures visualization with Raman spectroscopy and explainable convolutional neural network

Reprogramming of cellular metabolism is a driving factor of tumour progression and radiation therapy resistance. Identifying biochemical signatures associated with tumour radioresistance may assist with the development of targeted treatment strategies to improve clinical outcomes. Raman spectroscopy (RS) can monitor post-irradiation biomolecular changes and signatures of radiation response in tumour cells in a label-free manner. Convolutional Neural Networks (CNN) perform feature extraction directly from data in an end-to-end learning manner, with high classification performance. Furthermore, recently developed CNN explainability techniques help visualize the critical discriminative features captured by the model. In this work, a CNN is developed to characterize tumour response to radiotherapy based on its degree of radioresistance. The model was trained to classify Raman spectra of three human tumour cell lines as radiosensitive (LNCaP) or radioresistant (MCF7, H460) over a range of treatment doses and data collection time points. Additionally, a method based on Gradient-Weighted Class Activation Mapping (Grad-CAM) was used to determine response-specific salient Raman peaks influencing the CNN predictions. The CNN effectively classified the cell spectra, with accuracy, sensitivity, specificity, and F1 score exceeding 99.8%. Grad-CAM heatmaps of H460 and MCF7 cell spectra (radioresistant) exhibited high contributions from Raman bands tentatively assigned to glycogen, amino acids, and nucleic acids. Conversely, heatmaps of LNCaP cells (radiosensitive) revealed activations at lipid and phospholipid bands. Finally, Grad-CAM variable importance scores were derived for glycogen, asparagine, and phosphatidylcholine, and we show that their trends over cell line, dose, and acquisition time agreed with previously established models. Thus, the CNN can accurately detect biomolecular differences in the Raman spectra of tumour cells of varying radiosensitivity without requiring manual feature extraction. Finally, Grad-CAM may help identify metabolic signatures associated with the observed categories, offering the potential for automated clinical tumour radiation response characterization.

Rapid quantitative analysis of Rongalite adulteration in rice flour using autoencoder and residual-based model associated with portable Raman spectroscopy

Rice flour is a raw material for various foods and is used as a substitute for wheat flour. However, some merchants adulterate rice flour with the illegal additive Rongalite to extend the shelf life and earn illegal profits. Rongalite is highly carcinogenic, and ingestion of more than 10 g can even cause death. high-performance liquid chromatography (HPLC) and mass spectrometry (MS) are currently the main methods for detecting food adulteration, however, the existing methods have many limitations, complex operation, expensive instrumentation, etc. Raman spectroscopy has the advantages of convenience and non-destructive samples, but Raman spectroscopy can be affected by interference such as fluorescence background that affects detection, in addition to the problem of difficult quantitative analysis due to nonlinear bias. In this article, we used the preprocessing method of Savitzky-Golay smoothing filtering and VTPspline to improve the quality of the spectra and proposed the SARNet, which combines autoencoder and residual network to achieve the quantitative analysis of Rongalite content in rice flour. The new model combines a linear model with a nonlinear model, which can solve the nonlinear problem effectively. Experiments showed that the new SARNet model achieved state-of-the-art results, achieving the best R2 of 0.9703 and RMSEP of 0.0075. The lowest Rongalite concentration detected by the portable Raman spectrometer was 0.49%. In summary, the proposed method using portable Raman spectroscopy combined with machine learning has low detection bias and high accuracy, which can realize quantitative analyses of adulterated Rongalite in rice flour quickly. The method provides an accurate and nondestructive analytical tool in the field of food detection.

Deep metric learning framework combined with Gramian angular difference field image generation for Raman spectra classification based on a handheld Raman spectrometer

Rapid identification of unknown material samples using portable or handheld Raman spectroscopy detection equipment is becoming a common analytical tool. However, the design and implementation of a set of Raman spectroscopy-based devices for substance identification must include spectral sampling of standard reference substance samples, resolution matching between different devices, and the training process of the corresponding classification models. The process of selecting a suitable classification model is frequently time-consuming, and when the number of classes of substances to be recognised increases dramatically, recognition accuracy decreases dramatically. In this paper, we propose a fast classification method for Raman spectra based on deep metric learning networks combined with the Gramian angular difference field (GADF) image generation approach. First, we uniformly convert Raman spectra acquired at different resolutions into GADF images of the same resolution, addressing spectral dimension disparities induced by resolution differences in different Raman spectroscopy detection devices. Second, a network capable of implementing nonlinear distance measurements between GADF images of different classes of substances is designed based on a deep metric learning approach. The Raman spectra of 450 different mineral classes obtained from the RRUFF database were converted into GADF images and used to train this deep metric learning network. Finally, the trained network can be installed on an embedded computing platform and used in conjunction with portable or handheld Raman spectroscopic detection sensors to perform material identification tasks at various scales. A series of experiments demonstrate that our trained deep metric learning network outperforms existing mainstream machine learning models on classification tasks of different sizes. For the two tasks of Raman spectral classification of natural minerals of 260 classes and Raman spectral classification of pathogenic bacteria of 8 classes with significant noise, our suggested model achieved 98.05% and 90.13% classification accuracy, respectively. Finally, we also deployed the model in a handheld Raman spectrometer and conducted identification experiments on 350 samples of chemical substances attributed to 32 classes, achieving a classification accuracy of 99.14%. These results demonstrate that our method can greatly improve the efficiency of developing Raman spectroscopy-based substance detection devices and can be widely used in tasks of unknown substance identification.

Multi-scale sequential feature selection for disease classification using Raman spectroscopy data

Raman spectroscopy (RS) optical technology promises non-destructive and fast application in medical disease diagnosis in a single step. However, achieving clinically relevant performance levels remains challenging due to the inability to search for significant Raman signals at different scales. Here we propose a multi-scale sequential feature selection method that can capture global sequential features and local peak features for disease classification using RS data. Specifically, we utilize the Long short-term memory network (LSTM) module to extract global sequential features in the Raman spectra, as it can capture long-term dependencies present in the Raman spectral sequences. Meanwhile, the attention mechanism is employed to select local peak features that were ignored before and are the key to distinguishing different diseases. Experimental results on three public and in-house datasets demonstrate the superiority of our model compared with state-of-the-art methods for RS classification. In particular, our model achieves an accuracy of 97.9 ± 0.2% on the COVID-19 dataset, 76.3 ± 0.4% on the H-IV dataset, and 96.8 ± 1.9% on the H-V dataset.

On-line multi-gas component measurement in the mud logging process based on Raman spectroscopy combined with a CNN-LSTM-AM hybrid model

The qualitative and quantitative analysis of gas components extracted from drilling fluids during mud logging is essential for identifying drilling anomalies, reservoir characteristics, and hydrocarbon properties during oilfield recovery. Gas chromatography (GC) and gas mass spectrometers (GMS) are currently used for the online analysis of gases throughout the mud logging process. Nevertheless, these methods have limitations, including expensive equipment, high maintenance costs, and lengthy detection periods. Raman spectroscopy can be applied to the online quantification of gases at mud logging sites due to its in-situ analysis, high resolution, and rapid detection. However, laser power fluctuations, field vibrations, and the overlapping of characteristic peaks of different gases in the existing online detection system of Raman spectroscopy can affect the quantitative accuracy of the model. For these reasons, a gas Raman spectroscopy system with a high reliability, low detection limits, and increased sensitivity has been designed and applied to the online quantification of gases in the mud logging process. The near-concentric cavity structure is used to improve the signal acquisition module in the gas Raman spectroscopic system, thus enhancing the Raman spectral signal of the gases. One-dimensional convolutional neural networks (1D-CNN) combined with long- and short-term memory networks (LSTM) are applied to construct quantitative models based on the continuous acquisition of Raman spectra of gas mixtures. In addition, the attention mechanism is used to futher improve the quantitative model performance. The results indicated that our proposed method has the capability to continuously on-line detect 10 hydrocarbon and non-hydrocarbon gases in the mud logging process. The limitation of detection (LOD) for different gas components based on the proposed method are in the range of 0.0035%-0.0223%. Based on the proposed CNN-LSTM-AM model, the average detection errors of different gas components range from 0.899% to 3.521%, and their maximum detection errors range from 2.532% to 11.922%. These results demonstrate that our proposed method has a high accuracy, low deviation, and good stability and can be applied to the on-line gas analysis process in the mud logging field.

Rapid Prediction of Multidrug-Resistant Klebsiella pneumoniae through Deep Learning Analysis of SERS Spectra

Klebsiella pneumoniae is listed by the WHO as a priority pathogen of extreme importance that can cause serious consequences in clinical settings. Due to its increasing multidrug resistance all over the world, K. pneumoniae has the potential to cause extremely difficult-to-treat infections. Therefore, rapid and accurate identification of multidrug-resistant K. pneumoniae in clinical diagnosis is important for its prevention and infection control. However, the limitations of conventional and molecular methods significantly hindered the timely diagnosis of the pathogen. As a label-free, noninvasive, and low-cost method, surface-enhanced Raman scattering (SERS) spectroscopy has been extensively studied for its application potentials in the diagnosis of microbial pathogens. In this study, we isolated and cultured 121 K. pneumoniae strains from clinical samples with different drug resistance profiles, which included polymyxin-resistant K. pneumoniae (PRKP; n = 21), carbapenem-resistant K. pneumoniae, (CRKP; n = 50), and carbapenem-sensitive K. pneumoniae (CSKP; n = 50). For each strain, a total of 64 SERS spectra were generated for the enhancement of data reproducibility, which were then computationally analyzed via the convolutional neural network (CNN). According to the results, the deep learning model CNN plus attention mechanism could achieve a prediction accuracy as high as 99.46%, with robustness score of 5-fold cross-validation at 98.87%. Taken together, our results confirmed the accuracy and robustness of SERS spectroscopy in the prediction of drug resistance of K. pneumoniae strains with the assistance of deep learning algorithms, which successfully discriminated and predicted PRKP, CRKP, and CSKP strains. IMPORTANCE This study focuses on the simultaneous discrimination and prediction of Klebsiella pneumoniae strains with carbapenem-sensitive, carbapenem-resistant, and polymyxin-resistant phenotypes. The implementation of CNN plus an attention mechanism makes the highest prediction accuracy at 99.46%, which confirms the diagnostic potential of the combination of SERS spectroscopy with the deep learning algorithm for antibacterial susceptibility testing in clinical settings.

Raman spectroscopy and convolutional neural networks for monitoring biochemical radiation response in breast tumour xenografts

Tumour cells exhibit altered metabolic pathways that lead to radiation resistance and disease progression. Raman spectroscopy (RS) is a label-free optical modality that can monitor post-irradiation biomolecular signatures in tumour cells and tissues. Convolutional Neural Networks (CNN) perform automated feature extraction directly from data, with classification accuracy exceeding that of traditional machine learning, in cases where data is abundant and feature extraction is challenging. We are interested in developing a CNN-based predictive model to characterize clinical tumour response to radiation therapy based on their degree of radiosensitivity or radioresistance. In this work, a CNN architecture is built for identifying post-irradiation spectral changes in Raman spectra of tumour tissue. The model was trained to classify irradiated versus non-irradiated tissue using Raman spectra of breast tumour xenografts. The CNN effectively classified the tissue spectra, with accuracies exceeding 92.1% for data collected 3 days post-irradiation, and 85.0% at day 1 post-irradiation. Furthermore, the CNN was evaluated using a leave-one-out- (mouse, section or Raman map) validation approach to investigate its generalization to new test subjects. The CNN retained good predictive accuracy (average accuracies 83.7%, 91.4%, and 92.7%, respectively) when little to no information for a specific subject was given during training. Finally, the classification performance of the CNN was compared to that of a previously developed model based on group and basis restricted non-negative matrix factorization and random forest (GBR-NMF-RF) classification. We found that CNN yielded higher classification accuracy, sensitivity, and specificity in mice assessed 3 days post-irradiation, as compared with the GBR-NMF-RF approach. Overall, the CNN can detect biochemical spectral changes in tumour tissue at an early time point following irradiation, without the need for previous manual feature extraction. This study lays the foundation for developing a predictive framework for patient radiation response monitoring.

Multi-scale convolution neural network with residual modules for determination of drugs in human hair using surface-enhanced Raman spectroscopy with a gold nanorod film self-assembled by inverted evaporation

Detection of illegal drug users is crucial in controlling drug-related crimes, reducing drug prevalence, and protecting human lives to ensure social stability. In this study, surface-enhanced Raman spectroscopy (SERS) and deep learning networks were employed to determine methamphetamine, ketamine, and morphine in human hair. Drugs were obtained from hair through alkaline hydrolysis and liquid-liquid extraction, and gold nanorods were employed to prepare the self-assembled film as the SERS substrate by inverted evaporation. The film showed good uniformity and excellent sensitivity, with a relative standard deviation of 15.6% and a detection limit of at least 10^-10 M in the SERS detection of crystal violet. The spectra of methamphetamine, ketamine, and morphine at 0.05-1.0, 0.1-2.0, and 0.1-2.0 ng/mg were obtained, and the three drugs could be detected. Inception, a multi-scale feature extraction network, was combined with residual modules (Inception-ResNet) to develop the identification models of drugs, and the effect of spectral input form as a vector or matrix was explored. Inception-ResNet with input form of matrix outweighed other methods with 100.00%, 100.00%, and 99.23% accuracies in the training, validation, and prediction sets, respectively. In brief, SERS and Inception-ResNet with the spectra in matrix form provide an efficient and accurate determination of drugs in human hair, enabling the retrospective evaluation of drug use, and the method will be anticipated to detect excitant, poison, and toxic chemicals in human hair.

A deep learning model designed for Raman spectroscopy with a novel hyperparameter optimization method

Raman spectroscopy is a spectroscopic technique typically used to determine vibrational modes of molecules and is commonly used in chemistry to provide a structural fingerprint by which molecules can be identified. With the help of deep learning, Raman spectroscopy can be analyzed more efficiently and thus provide more accurate molecular information. However, no general neural network is designed for one-dimensional Raman spectral data so far. Furthermore, different combinations of hyperparameters of neural networks lead to results with significant differences, so the optimization of hyperparameters is a crucial issue in deep learning modeling. In this work, we propose a deep learning model designed for Raman spectral data and a hyperparameter optimization method to achieve its best performance, i.e., a method based on the simulated annealing algorithm to optimize the hyperparameters of the model. The proposed model and optimization method have been fully validated in a glioma Raman spectroscopy dataset. Compared with other published methods including linear regression, support vector regression, long short-term memory, VGG and ResNet, the mean squared error is reduced by 0.1557 while the coefficient determination is increased by 0.1195 on average.

Prediction approach of larch wood density from visible-near-infrared spectroscopy based on parameter calibrating and transfer learning

Wood density, as a key indicator to measure wood properties, is of weighty significance in enhancing wood utilization and modifying wood properties in sustainable forest management. Visible-near-infrared (Vis-NIR) spectroscopy provides a feasible and efficient solution for obtaining wood density by the advantages of its efficiency and non-destructiveness. However, the spectral responses are different in wood products with different moisture content conditions, and changes in external factors may cause the regression model to fail. Although some calibration transfer methods and convolutional neural network (CNN)-based deep transfer learning methods have been proposed, the generalization ability and prediction accuracy of the models still need to be improved. For the prediction problem of Vis-NIR wood density in different moisture contents, a deep transfer learning hybrid method with automatic calibration capability (Resnet1D-SVR-TrAdaBoost.R2) was proposed in this study. The disadvantage of overfitting was avoided when CNN processes small sample data, which considered the complex exterior factors in actual production to enhance feature extraction and migration between samples. Density prediction of the method was performed on a larch dataset with different moisture content conditions, and the hybrid method was found to achieve the best prediction results under the calibration samples with different target domain calibration samples and moisture contents, and the performance of models was better than that of the traditional calibration transfer and migration learning methods. In particular, the hybrid model has achieved an improvement of about 0.1 in both R ² and root mean square error (RMSE) values compared to the support vector regression model transferred by piecewise direct standardization method (SVR+PDS), which has the best performance among traditional calibration methods. To further ascertain the generalizability of the hybrid model, the model was validated with samples collected from mixed moisture contents as the target domain. Various experiments demonstrated that the Resnet1D-SVR-TrAdaBoost.R2 model could predict larch wood density with a high generalization ability and accuracy effectively but was computation consuming. It showed the potential to be extended to predict other metrics of wood.

Machine Learning Sorting Method of Bauxite Based on SE-Enhanced Network

A fast and accurate bauxite recognition method combining an attention module and a clustering algorithm is proposed in this paper. By introducing the K-means clustering algorithm into the YOLOv4 network and embedding the SE attention module, we calculate the corresponding anchor box value, enhance the feature learning ability of the network to bauxite, automatically learn the importance of different channel features, and improve the accuracy of bauxite target detection. In the experiment, 2189 bauxite photos were taken and screened as the target detection datasets, and the targets were divided into four categories: No. 55, No. 65, No. 70, and Nos. 72–73. By selecting the category volume balanced datasets, the optimal YOLOv4 network model was obtained after training 7000 times, so that the average accuracy of bauxite sorting reached 99%, and the reasoning speed was better than 0.05 s. Realizing the high-speed and high-precision sorting of bauxite greatly improves the mining efficiency and accuracy of the bauxite industry. At the same time, the model provides key technical support for the practical application of the same type of engineering.