Deep Learning for Reconstructing Low-Quality FTIR and Raman Spectra─A Case Study in Microplastic Analyses

Deep autoencoder as an interpretable tool for Raman spectroscopy investigation of chemical and extracellular vesicle mixtures

Surface-enhanced Raman spectroscopy (SERS) is a powerful tool that provides valuable insight into the molecular contents of chemical and biological samples. However, interpreting Raman spectra from complex or dynamic datasets remains challenging, particularly for highly heterogeneous biological samples like extracellular vesicles (EVs). To overcome this, we developed a tunable and interpretable deep autoencoder for the analysis of several challenging Raman spectroscopy applications, including synthetic datasets, chemical mixtures, a chemical milling reaction, and mixtures of EVs. We compared the results with classical methods (PCA and UMAP) to demonstrate the superior performance of the proposed technique. Our method can handle small datasets, provide a high degree of generalization such that it can fill unknown gaps within spectral datasets, and even quantify relative ratios of cell line-derived EVs to fetal bovine serum-derived EVs within mixtures. This simple yet robust approach will greatly improve the analysis capabilities for many other Raman spectroscopy applications.

Artificial intelligence-empowered collection and characterization of microplastics: A review

Microplastics have been detected from water and soil systems extensively, with increasing evidence indicating their detrimental impacts on human and animal health. Concerns surrounding microplastic pollution have spurred the development of advanced collection and characterization methods for studying the size, abundance, distribution, chemical composition, and environmental impacts. This paper offers a comprehensive review of artificial intelligence (AI)-empowered technologies for the collection and characterization of microplastics. A framework is presented to streamline efforts in utilizing emerging robotics and machine learning technologies for collecting, processing, and characterizing microplastics. The review encompasses a range of AI technologies, delineating their principles, strengths, limitations, representative applications, and technology readiness levels, facilitating the selection of suitable AI technologies for mitigating microplastic pollution. New opportunities for future research and development on integrating robots and machine learning technologies are discussed to facilitate future efforts for mitigating microplastic pollution and advancing AI technologies.

Ante- and Post-Mortem Fracture Identification Protocol Based on Low- and High-Level Fusion Using Fourier Transform Infrared Spectroscopy and Raman Spectroscopy Association

In this study, the application of low-level fusion (LLF) and high-level fusion (HLF) strategies using a combination of Fourier transform infrared spectroscopy (FT-IR) and Raman spectroscopy in the identification of antemortem and postmortem fracture at different postmortem intervals (PMIs) was investigated. On a technical level, the same hard tissue sample can be detected using a mix of FT-IR and Raman techniques. At the method level, two cutting-edge chemometrics approaches (LLF and HLF) combining FT-IR and Raman spectroscopic data are explored. The models were ranked in accordance with their parametric quality as follows: HLF and LLF + HLF models > LLF single model > Raman single model > FT-IR single model. The LLF model performed marginally better than the Raman model, however, when compared to other models, the HLF model performed considerably better. The HLF model achieved the best performance, with both cross-validation accuracy and test data set accuracy of 0.88. The importance of the feature wavelengths in the model construction process was subsequently evaluated by intersection fusion, and it was found that the absorbance bands of amide I, PO43- ν1 ν3, and CH2 in FT-IR and phenylalanine, CO32- ν1- PO43- ν3, and amide III in Raman have outstanding contributions to the construction of antemortem and postmortem fractures identification models. Overall, the combination of FT-IR and Raman with the HLF strategy is a novel and promising approach for developing antemortem and postmortem fracture identification models at different PMIs.

Generation of synthetic FTIR spectra to facilitate chemical identification of microplastics

In a context where learning databases of microplastic FTIR spectra are often incomplete, the objective of our work was to test whether a synthetic data generation method could be relevant to fill the gaps. To this end, synthetic spectra were generated to create new databases. The effectiveness of machine learning from these databases was then tested and compared with previous results. The results showed that the creation of synthetic learning databases could avoid, to a certain extent, the need for learning databases of environmental microplastics FTIR spectra. However, some limitations were encountered, for example, when two different chemical classes had very similar reference spectra or when the intensities of the bands associated with fouling became too intense. The FTIR study of the ageing and fouling of microplastics in the natural environment is one of the identified ways that could further improve this approach.

Toward Nano- and Microplastic Sensors: Identification of Nano- and Microplastic Particles via Artificial Intelligence Combined with a Plasmonic Probe Functionalized with an Estrogen Receptor

Nano- and microplastic particles are a global and emerging environmental issue that might pose potential threats to human health. The present work exploits artificial intelligence (AI) to identify nano- and microplastics in water by monitoring the interaction of the sample with a sensitive surface. An estrogen receptor (ER) grafted onto a gold surface, realized on a nonexpensive and easy-to-produce plastic optical fiber (POF) platform in order to excite a surface plasmon resonance (SPR) phenomenon, has been developed in order to carry out a "smart" sensitive interface (ER-SPR-POF interface). The ER-SPR-POF interface offers output data useful for exploiting a machine learning-based approach to achieve nano- and microplastic particle sensors. This work developed a proof-of-concept sensor through a training phase carried out by different particles, in terms of materials and size. The experimental results have demonstrated that the proposed "smart" ER-SPR-POF interface combined with AI can be used to identify the kind of particles in terms of the materials (polystyrene; poly(methyl methacrylate)) and size (20 μm; 100 nm) with an accuracy of 90.3%.

Underappreciated microplastic galaxy biases the filter-based quantification

Long-term environmental loading of microplastics (MPs) causes alarming exposure risks for a variety of species worldwide, considered a planetary threat to the well-being of ecosystems. Robust quantitative estimates of MP extents and featured diversity are the basis for comprehending their environmental implications precisely, and of these methods, membrane-based characterizations predominate with respect to MP inspections. However, though crucial to filter-based MP quantification, aggregation statuses of retained MPs on these substrates remain poorly understood, leaving us a "blind box" that exaggerates uncertainty in quantitive strategies of preselected areas without knowing overview loading structure. To clarify this uncertainty and estimate their impacts on MP counting, using MP imaging data assembled from peer-reviewed studies through a systematic review, here we analyze the particle-specific profiles of MPs retained on various substrates according to their centre of mass with a fast-random forests algorithm. We visualize the formation of distinct galaxy-like MP aggregation-similar to the solar system and Milky Way System comprised of countless stars-across the pristine and environmental samples by leveraging two spatial parameters developed in this study. This unique pattern greatly challenges the homogeneously or randomly distributed MP presumption adopted extensively for simplified membrane-based quantification purposes and selective ROI (region of interest) estimates for smaller-sized plastics down to the nano-range, as well as the compatibility theory using pristine MPs as the standard to quantify the presence of environmental MPs. Furthermore, our evaluation with exemplified numeration cases confirms these location-specific and area-dependent biases in many imaging analyses of a selective filter area, ascribed to the minimum possibility of reaching an ideal turnover point for the selective quantitive strategies. Consequently, disproportionate MP schemes on loading substrates yield great uncertainty in their quantification processing, highlighting the prompt need to include pattern-resolved calibration prior to quantification. Our findings substantially advance our understanding of the structure, behavior, and formation of these MP aggregating statuses on filtering substrates, addressing a fundamental question puzzling scientists as to why reproducible MP quantification is barely achievable even for subsamples. This study inspires the following studies to reconsider the impacts of aggregating patterns on the effective counting protocols and target-specific removal of retained MP aggregates through membrane separation techniques.

High-throughput microplastic assessment using polarization holographic imaging

Microplastic (MP) pollution has emerged as a global environmental concern due to its ubiquity and harmful impacts on ecosystems and human health. MP assessment has therefore become increasingly necessary and common in environmental and experimental samples. Microscopy and spectroscopy are widely employed for the physical and chemical characterization of MPs. However, these analytical methods often require time-consuming pretreatments of samples or expensive instrumentation. In this work, we develop a portable and cost-effective polarization holographic imaging system that prominently incorporates deep learning techniques, enabling efficient, high-throughput detection and dynamic analysis of MPs in aqueous environments. The integration enhances the identification and classification of MPs, eliminating the need for extensive sample preparation. The system simultaneously captures holographic interference patterns and polarization states, allowing for multimodal information acquisition to facilitate rapid MP detection. The characteristics of light waves are registered, and birefringence features are leveraged to classify the material composition and structures of MPs. Furthermore, the system automates real-time counting and morphological measurements of various materials, including MP sheets and additional natural substances. This innovative approach significantly improves the dynamic monitoring of MPs and provides valuable information for their effective filtration and management.

Artificial Intelligence for Surface-Enhanced Raman Spectroscopy

Surface-enhanced Raman spectroscopy (SERS), well acknowledged as a fingerprinting and sensitive analytical technique, has exerted high applicational value in a broad range of fields including biomedicine, environmental protection, food safety among the others. In the endless pursuit of ever-sensitive, robust, and comprehensive sensing and imaging, advancements keep emerging in the whole pipeline of SERS, from the design of SERS substrates and reporter molecules, synthetic route planning, instrument refinement, to data preprocessing and analysis methods. Artificial intelligence (AI), which is created to imitate and eventually exceed human behaviors, has exhibited its power in learning high-level representations and recognizing complicated patterns with exceptional automaticity. Therefore, facing up with the intertwining influential factors and explosive data size, AI has been increasingly leveraged in all the above-mentioned aspects in SERS, presenting elite efficiency in accelerating systematic optimization and deepening understanding about the fundamental physics and spectral data, which far transcends human labors and conventional computations. In this review, the recent progresses in SERS are summarized through the integration of AI, and new insights of the challenges and perspectives are provided in aim to better gear SERS toward the fast track.

Automatic Identification of Individual Nanoplastics by Raman Spectroscopy Based on Machine Learning

The increasing prevalence of nanoplastics in the environment underscores the need for effective detection and monitoring techniques. Current methods mainly focus on microplastics, while accurate identification of nanoplastics is challenging due to their small size and complex composition. In this work, we combined highly reflective substrates and machine learning to accurately identify nanoplastics using Raman spectroscopy. Our approach established Raman spectroscopy data sets of nanoplastics, incorporated peak extraction and retention data processing, and constructed a random forest model that achieved an average accuracy of 98.8% in identifying nanoplastics. We validated our method with tap water spiked samples, achieving over 97% identification accuracy, and demonstrated the applicability of our algorithm to real-world environmental samples through experiments on rainwater, detecting nanoscale polystyrene (PS) and polyvinyl chloride (PVC). Despite the challenges of processing low-quality nanoplastic Raman spectra and complex environmental samples, our study demonstrated the potential of using random forests to identify and distinguish nanoplastics from other environmental particles. Our results suggest that the combination of Raman spectroscopy and machine learning holds promise for developing effective nanoplastic particle detection and monitoring strategies.

When microplastics meet electroanalysis: future analytical trends for an emerging threat

Microplastics are a major modern challenge that must be addressed to protect the environment, particularly the marine environment. Microplastics, defined as particles ≤5 mm, are ubiquitous in the environment. Their small size for a relatively large surface area, high persistence and easy distribution in water, soil and air require the development of new analytical methods to monitor their presence. At present, the availability of analytical techniques that are easy to use, automated, inexpensive and based on new approaches to improve detection remains an open challenge. This review aims to outline the evolution and novelties of classical and advanced methods, in particular the recently reported electroanalytical detectors, methods and devices. Among all the studies reviewed here, we highlight the great advantages of electroanalytical tools over spectroscopic and thermal analysis, especially for the rapid and accurate detection of microplastics in the sub-micron range. Finally, the challenges faced in the development of automated analytical methods are discussed, highlighting recent trends in artificial intelligence (AI) in microplastics analysis.

A review of recent progress in the application of Raman spectroscopy and SERS detection of microplastics and derivatives

The global environmental concern surrounding microplastic (MP) pollution has raised alarms due to its potential health risks to animals, plants, and humans. Because of the complex structure and composition of microplastics (MPs), the detection methods are limited, resulting in restricted detection accuracy. Surface enhancement of Raman spectroscopy (SERS), a spectral technique, offers several advantages, such as high resolution and low detection limit. It has the potential to be extensively employed for sensitive detection and high-resolution imaging of microplastics. We have summarized the research conducted in recent years on the detection of microplastics using Raman and SERS. Here, we have reviewed qualitative and quantitative analyses of microplastics and their derivatives, as well as the latest progress, challenges, and potential applications.

FRDA: Fingerprint Region based Data Augmentation using explainable AI for FTIR based microplastics classification

Marine microplastics (MPs) contamination has become an enormous hazard to aquatic creatures and human life. For MP identification, many Machine learning (ML) based approaches have been proposed using Attenuated Total Reflection Fourier Transform Infrared Spectroscopy (ATR-FTIR). One major challenge for training MP identification models now is the imbalanced and inadequate samples in MP datasets, especially when these conditions are combined with copolymers and mixtures. To improve the ML performance in identifying MPs, data augmentation method is an effective approach. This work utilizes Explainable Artificial Intelligence (XAI) and Gaussian Mixture Models (GMM) to reveal the influence of FTIR spectral regions in identifying each type of MPs. Based on the identified regions, this work proposes a Fingerprint Region based Data Augmentation (FRDA) method to generate new FTIR data to supplement MP datasets. The evaluation results show that FRDA outperforms the existing spectral data augmentation approaches.

A deep learning-based simulator for comprehensive two-dimensional GC applications

Among the main approaches for predicting the spatial positions of eluates in comprehensive two-dimensional gas chromatography, the still under-explored computational models based on deep learning algorithms emerge as robust and reliable options due to their high adaptability to the structure and complexity of the data. In this work, an open-source program based on deep neural networks was developed to optimize chromatographic methods and simulate operating conditions outside the laboratory. The deep neural networks models were fit to convenient experimental predictors, resulting in scaled losses (mean squared error) equivalent to 0.006 (relative average deviation = 8.56%, R2  = 0.9202) and 0.014 (relative average deviation = 1.67%, R2  = 0.8009) in the prediction of the first- and second-dimension retention times, respectively. Good compliance was observed for the main chemical classes, such as environmental contaminants: volatile, semivolatile organic compounds, and pesticides; biochemistry molecules: amino acids and lipids; pharmaceutical industry and personal care products and residues: drugs and metabolites; among others. On the other hand, there is a need for continuous database updates to predict retention times of less common compounds accurately. Thus, forming a collaborative database is proposed, gathering voluntary findings from other users.

Predicting adsorption capacity of pharmaceuticals and personal care products on long-term aged microplastics using machine learning

We investigated the adsorption mechanism of 66 coexisting pharmaceuticals and personal care products (PPCPs) on microplastics treated with potassium persulfate, potassium hydroxide, and Fenton reagent for 54, 110, and 500 days. The total adsorption capacity (q_e) of 66 PPCPs on 15 original microplastics was 171.8 - 1043.7 μg/g, far below that of 177 long-term aged microplastics (7114.0 - 13,114.4 μg/g). Around 69.8% of q_e was primarily influenced by the total energy, energy of the highest occupied molecular orbital, and energy gap of PPCPs, calculated using the B3LYP/6-31 G* level. Furthermore, 111 aged microplastics exhibited similar total q_e values. Additionally, we developed predictive models based on attenuated total reflectance Fourier transform infrared spectroscopy to predict the individual and total q_e on 192 microplastics. These models, including the maximal information coefficient and gradient boosting decision tree regression, exhibited high accuracy with R_training² values of 0.9772 and 0.9661, respectively, and p-values below 0.001. Spectroscopic analysis and machine learning models highlighted surface functional group alterations and the importance of the 1528-1700 cm^-1 spectral region and carbon skeleton in the adsorption process. In summary, our findings contribute to understanding the adsorption of PPCPs on microplastics, particularly in the context of long-term aging effects.

Random forest microplastic classification using spectral subsamples of FT-IR hyperspectral images

In this work, a random decision forest model is built for fast identification of Fourier-transform infrared spectra of the eleven most common types of microplastics in the environment. The random decision forest input data is reduced to a combination of highly discriminative single wavenumbers selected using a machine learning classifier. This dimension reduction allows input from systems with individual wavenumber measurements, and decreases prediction time. The training and testing spectra are extracted from Fourier-transform infrared hyperspectral images of pure-type microplastic samples, automatizing the process with reference spectra and a fast background correction and identification algorithm. Random decision forest classification results are validated using procedurally generated ground truth. The classification accuracy achieved on said ground truths are not expected to carry over to environmental samples as those usually contain a broader variety of materials.

Evaluation of the Deterioration of Untreated Commercial Polystyrene by Psychrotrophic Antarctic Bacterium

Polystyrene (PS) and microplastic production pose persistent threats to the ecosystem. Even the pristine Antarctic, which is widely believed to be pollution-free, was also affected by the presence of microplastics. Therefore, it is important to comprehend the extent to which biological agents such as bacteria utilise PS microplastics as a carbon source. In this study, four soil bacteria from Greenwich Island, Antarctica, were isolated. A preliminary screening of the isolates for PS microplastics utilisation in the Bushnell Haas broth was conducted with the shake-flask method. The isolate AYDL1 identified as Brevundimonas sp. was found to be the most efficient in utilising PS microplastics. An assay on PS microplastics utilisation showed that the strain AYDL1 tolerated PS microplastics well under prolonged exposure with a weight loss percentage of 19.3% after the first interval (10 days of incubation). Infrared spectroscopy showed that the bacteria altered the chemical structure of PS while a deformation of the surface morphology of PS microplastics was observed via scanning electron microscopy after being incubated for 40 days. The obtained results may essentially indicate the utilisation of liable polymer additives or "leachates" and thus, validate the mechanistic approach for a typical initiation process of PS microplastics biodeterioration by the bacteria (AYDL1)-the biotic process.

Detection of amylase activity and moisture content in rice by reflectance spectroscopy combined with spectral data transformation

In this study, reflectance spectroscopy was used to achieve rapid and non-destructive detection of amylase activity and moisture content in rice. Since rice husk can interfere with spectral measurements, spectral data transformation was used to remove the husk interference. Reflectance spectra of rice were transformed by direct standardization, convolutional autoencoder network, and kernel regression (KR). Then, random frog and elliptical envelope were adopted to select effective wavelengths, and partial least squares regression (PLSR) and support vector regression were used to establish analysis models. The optimal transformation was from KR, and PLSR and effective wavelengths of the transformed spectra obtained excellent performance with coefficient of determination of test of 0.6987 and 0.8317 and root-mean-square error of test of 0.3359 and 2.2239, respectively. The result was better than that of the rice spectra and was close to that of the husked rice spectra. When the moisture content was integrated into the regression model of amylase activity, a better result was obtained. Thus, the proposed method can detect amylase activity and moisture content in rice accurately.

Manifold Learning Enables Interpretable Analysis of Raman Spectra from Extracellular Vesicle and Other Mixtures

Extracellular vesicles (EVs) have emerged as promising diagnostic and therapeutic candidates in many biomedical applications. However, EV research continues to rely heavily on in vitro cell cultures for EV production, where the exogenous EVs present in fetal bovine (FBS) or other required serum supplementation can be difficult to remove entirely. Despite this and other potential applications involving EV mixtures, there are currently no rapid, robust, inexpensive, and label-free methods for determining the relative concentrations of different EV subpopulations within a sample. In this study, we demonstrate that surface-enhanced Raman spectroscopy (SERS) can biochemically fingerprint fetal bovine serum-derived and bioreactor-produced EVs, and after applying a novel manifold learning technique to the acquired spectra, enables the quantitative detection of the relative amounts of different EV populations within an unknown sample. We first developed this method using known ratios of Rhodamine B to Rhodamine 6G, then using known ratios of FBS EVs to breast cancer EVs from a bioreactor culture. In addition to quantifying EV mixtures, the proposed deep learning architecture provides some knowledge discovery capabilities which we demonstrate by applying it to dynamic Raman spectra of a chemical milling process. This label-free characterization and analytical approach should translate well to other EV SERS applications, such as monitoring the integrity of semipermeable membranes within EV bioreactors, ensuring the quality or potency of diagnostic or therapeutic EVs, determining relative amounts of EVs produced in complex co-culture systems, as well as many Raman spectroscopy applications.

A Universal and Accurate Method for Easily Identifying Components in Raman Spectroscopy Based on Deep Learning

Raman spectroscopy has been widely used to provide the structural fingerprint for molecular identification. Due to interference from coexisting components, noise, baseline, and systematic differences between spectrometers, component identification with Raman spectra is challenging, especially for mixtures. In this study, a method entitled DeepRaman has been proposed to solve those problems by combining the comparison ability of a pseudo-Siamese neural network (pSNN) and the input-shape flexibility of spatial pyramid pooling (SPP). DeepRaman was trained, validated, and tested with 41,564 augmented Raman spectra from two databases (pharmaceutical material and S.T. Japan). It can achieve 96.29% accuracy, 98.40% true positive rate (TPR), and 94.36% true negative rate (TNR) on the test set. Another six data sets measured on different instruments were used to evaluate the performance of the proposed method from different aspects. DeepRaman can provide accurate identification results and significantly outperform the hit quality index (HQI) method and other deep learning models. In addition, it performs well in cases of different spectral complexity and low-content components. Once the model is established, it can be used directly on different data sets without retraining or transfer learning. Furthermore, it also obtains promising results for the analysis of surface-enhanced Raman spectroscopy (SERS) data sets and Raman imaging data sets. In summary, it is an accurate, universal, and ready-to-use method for component identification in various application scenarios.

A one-dimensional convolutional neural network based deep learning for high accuracy classification of transformation stages in esophageal squamous cell carcinoma tissue using micro-FTIR

Among the most frequently diagnosed cancers in developing countries, esophageal squamous cell carcinoma (ESCC) ranks among the top six causes of death. It would be beneficial if a rapid, accurate, and automatic ESCC diagnostic method could be developed to reduce the workload of pathologists and improve the effectiveness of cancer treatments. Using micro-FTIR spectroscopy, this study classified the transformation stages of ESCC tissues. Based on 6,352 raw micro-FTIR spectra, a one-dimensional convolutional neural network (1D-CNN) model was constructed to classify-five stages. Based on the established model, more than 93% accuracy was achieved at each stage, and the accuracy of identifying proliferation, low grade neoplasia, and ESCC cancer groups was achieved 99% for the test dataset. In this proof-of-concept study, the developed method can be applied to other diseases in order to promote the use of FTIR spectroscopy in cancer pathology.

A Critical Review on Artificial Intelligence-Based Microplastics Imaging Technology: Recent Advances, Hot-Spots and Challenges

Due to the rapid artificial intelligence technology progress and innovation in various fields, this research aims to use science mapping tools to comprehensively and objectively analyze recent advances, hot-spots, and challenges in artificial intelligence-based microplastic-imaging field from the Web of Science (2019-2022). By text mining and visualization in the scientific literature we emphasized some opportunities to bring forward further explication and analysis by (i) exploring efficient and low-cost automatic quantification methods in the appearance properties of microplastics, such as shape, size, volume, and topology, (ii) investigating microplastics water-soluble synthetic polymers and interaction with other soil and water ecology environments via artificial intelligence technologies, (iii) advancing efficient artificial intelligence algorithms and models, even including intelligent robot technology, (iv) seeking to create and share robust data sets, such as spectral libraries and toxicity database and co-operation mechanism, (v) optimizing the existing deep learning models based on the readily available data set to balance the related algorithm performance and interpretability, (vi) facilitating Unmanned Aerial Vehicle technology coupled with artificial intelligence technologies and data sets in the mass quantities of microplastics. Our major findings were that the research of artificial intelligence methods to revolutionize environmental science was progressing toward multiple cross-cutting areas, dramatically increasing aspects of the ecology of plastisphere, microplastics toxicity, rapid identification, and volume assessment of microplastics. The above findings can not only determine the characteristics and track of scientific development, but also help to find suitable research opportunities to carry out more in-depth research with many problems remaining.

Raman Spectroscopy on Brain Disorders: Transition from Fundamental Research to Clinical Applications

Brain disorders such as brain tumors and neurodegenerative diseases (NDs) are accompanied by chemical alterations in the tissues. Early diagnosis of these diseases will provide key benefits for patients and opportunities for preventive treatments. To detect these sophisticated diseases, various imaging modalities have been developed such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). However, they provide inadequate molecule-specific information. In comparison, Raman spectroscopy (RS) is an analytical tool that provides rich information about molecular fingerprints. It is also inexpensive and rapid compared to CT, MRI, and PET. While intrinsic RS suffers from low yield, in recent years, through the adoption of Raman enhancement technologies and advanced data analysis approaches, RS has undergone significant advancements in its ability to probe biological tissues, including the brain. This review discusses recent clinical and biomedical applications of RS and related techniques applicable to brain tumors and NDs.

Customizable Machine-Learning Models for Rapid Microplastic Identification Using Raman Microscopy

Raman spectroscopy is commonly used in microplastics identification, but equipment variations yield inconsistent data structures that disrupt the development of communal analytical tools. We report a strategy to overcome the issue using a database of high-resolution, full-window Raman spectra. This approach enables customizable analytical tools to be easily created─a feature we demonstrate by creating machine-learning classification models using open-source random-forest, K-nearest neighbors, and multi-layer perceptron algorithms. These models yield >95% classification accuracy when trained on spectroscopic data with spectroscopic data downgraded to 1, 2, 4, or 8 cm^-1 spacings in Raman shift. The accuracy can be maintained even in non-ideal conditions, such as with spectroscopic sampling rates of 1 kHz and when microplastic particles are outside the focal plane of the laser. This approach enables the creation of classification models that are robust and adaptable to varied spectrometer setups and experimental needs.

Cascaded Deep Convolutional Neural Networks as Improved Methods of Preprocessing Raman Spectroscopy Data

Machine learning has had a significant impact on the value of spectroscopic characterization tools, particularly in biomedical applications, due to its ability to detect latent patterns within complex spectral data. However, it often requires extensive data preprocessing, including baseline correction and denoising, which can lead to an unintentional bias during classification. To address this, we developed two deep learning methods capable of fully preprocessing raw Raman spectroscopy data without any human input. First, cascaded deep convolutional neural networks (CNN) based on either ResNet or U-Net architectures were trained on randomly generated spectra with augmented defects. Then, they were tested using simulated Raman spectra, surface-enhanced Raman spectroscopy (SERS) imaging of chemical species, low resolution Raman spectra of human bladder cancer tissue, and finally, classification of SERS spectra from human placental extracellular vesicles (EVs). Both approaches resulted in faster training and complete spectral preprocessing in a single step, with more speed, defect tolerance, and classification accuracy compared to conventional methods. These findings indicate that cascaded CNN preprocessing is ideal for biomedical Raman spectroscopy applications in which large numbers of heterogeneous spectra with diverse defects need to be automatically, rapidly, and reproducibly preprocessed.

Identification and Quantification of Microplastics in the Marine Environment Using the Laser Direct Infrared (LDIR) Technique

Here, we evaluate for the first time the performances of the newly developed laser direct infrared (LDIR) technique and propose an optimization of the initial protocol for marine microplastics (MPs) analysis. Our results show that an 8 μm porosity polycarbonate filter placed on a Kevley slide enables preconcentration and efficient quantification of MPs, as well as polymer and size determination of reference plastic pellets of polypropylene (PP), polyethylene (PE), polystyrene (PS), polyvinyl chloride (PVC), and polyethylene terephthalate (PET), with recoveries ranging from 80-100% and negligible blank values for particle sizes ranging from 200 to 500 μm. A spiked experiment using seawater, sediment, mussels, and fish stomach samples showed that the method responded linearly with significant slopes (R² ranging from 0.93-1.0; p < 0.001, p < 0.01). Overall, 11 polymer types were identified with limited handling and an analysis time of ca. 3 h for most samples and 6 h for complex samples. Application of this technique to Mediterranean marine samples (seawater, sediment, fish stomachs and mussels) indicated MP concentrations and size distribution consistent with the literature. A high predominance of PVC (sediment, fish stomachs) and PE and PP (seawater, mussels) was observed in the analyzed samples.

Advanced microplastic monitoring using Raman spectroscopy with a combination of nanostructure-based substrates

Micro(nano)plastic (MNP) pollutants have not only impacted human health directly, but are also associated with numerous chemical contaminants that increase toxicity in the natural environment. Most recent research about increasing plastic pollutants in natural environments have focused on the toxic effects of MNPs in water, the atmosphere, and soil. The methodologies of MNP identification have been extensively developed for actual applications, but they still require further study, including on-site detection. This review article provides a comprehensive update on the facile detection of MNPs by Raman spectroscopy, which aims at early diagnosis of potential risks and human health impacts. In particular, Raman imaging and nanostructure-enhanced Raman scattering have emerged as effective analytical technologies for identifying MNPs in an environment. Here, the authors give an update on the latest advances in plasmonic nanostructured materials-assisted SERS substrates utilized for the detection of MNP particles present in environmental samples. Moreover, this work describes different plasmonic materials-including pure noble metal nanostructured materials and hybrid nanomaterials-that have been used to fabricate and develop SERS platforms to obtain the identifying MNP particles at low concentrations. Plasmonic nanostructure-enhanced materials consisting of pure noble metals and hybrid nanomaterials can significantly enhance the surface-enhanced Raman scattering (SERS) spectra signals of pollutant analytes due to their localized hot spots. This concise topical review also provides updates on recent developments and trends in MNP detection by means of SERS using a variety of unique materials, along with three-dimensional (3D) SERS substrates, nanopipettes, and microfluidic chips. A novel material-assisted spectral Raman technique and its effective application are also introduced for selective monitoring and trace detection of MNPs in indoor and outdoor environments.

Research on the Comprehensive Evaluation Method for the Automatic Recognition of Raman Spectrum under Multidimensional Constraint

Raman spectrum contains abundant substance information with fingerprint characteristics. However, due to the huge variety of substances and their complex characteristic information, it is difficult to recognize the Raman spectrum accurately. Starting from dimensions like the Raman shift, the relative peak intensity, and the overall hit ratio of characteristic peaks, we extracted and recognized the characteristics in the Raman spectrum and analyzed these characteristics from local and global perspectives and then proposed a comprehensive evaluation method for the recognition of Raman spectrum on the basis of the data fusion of the recognition results under multidimensional constraint. Based on the common spectrum database of the normal Raman and surface-enhanced Raman of thousands of substances, we analyzed the performance of the evaluation method. It shows that even for the identification of spectra from instruments of low technical specifications, the automatic recognition rate of the sample can reach 98% and above, a great improvement compared with that of the common identification algorithms, which proves the effectiveness of the comprehensive evaluation method under multidimensional constraint.

Accurate Tumor Subtype Detection with Raman Spectroscopy via Variational Autoencoder and Machine Learning

Accurate diagnosis of cancer subtypes is a great guide for the development of surgical plans and prognosis in the clinic. Raman spectroscopy, combined with the machine learning algorithm, has been demonstrated to be a powerful tool for tumor identification. However, the analysis and classification of Raman spectra for biological samples with complex compositions are still challenges. In addition, the signal-to-noise ratio of the spectra also influences the accuracy of the classification. Herein, we applied the variational autoencoder (VAE) to Raman spectra for downscaling and noise reduction simultaneously. We validated the performance of the VAE algorithm at the cellular and tissue levels. VAE successfully downscaled high-dimensional Raman spectral data to two-dimensional (2D) data for three subtypes of non-small cell lung cancer cells and two subtypes of kidney cancer tissues. Gaussian naïve bayes was applied to subtype discrimination with the 2D data after VAE encoding at both the cellular and tissue levels, significantly outperforming the discrimination results using original spectra. Therefore, the analysis of Raman spectroscopy based on VAE and machine learning has great potential for rapid diagnosis of tumor subtypes.

Dual-Principal Component Analysis of the Raman Spectrum Matrix to Automatically Identify and Visualize Microplastics and Nanoplastics

As emerging contaminants, microplastics are challenging to characterize, particularly when their size is at the nanoscale. While imaging technology has received increasing attention recently, such as Raman imaging, decoding the scanning spectrum matrix can be difficult to achieve result digitally and automatically via software and usually requires the involvement of personal experience and expertise. Herewith, we show a dual-principal component analysis (PCA) approach, where (i) the first round of PCA analysis focuses on the raw spectrum data from the Raman scanning matrix and generates two new matrices, with one containing the spectrum profile to yield the PCA spectrum and the other containing the PCA intensity to be mapped as an image; (ii) the second round of PCA analysis merges the spectrum from the first round of PCA with the standard spectra of eight common plastics, to generate a correlation matrix. From the correlation value, we can digitally assign the principal components from the first round of PCA analysis to the plastics toward imaging, akin to dataset indexing. We also demonstrate the effect of the data pretreatment and the wavenumber variations. Overall, this dual-PCA approach paves the way for machine learning to analyze microplastics and particularly nanoplastics.