Detection of pancreatic cancer by convolutional-neural-network-assisted spontaneous Raman spectroscopy with critical feature visualization

Raman Peak Features Matching: Enhancing Spectral Analysis through Feature Augmentation

Raman spectroscopy has emerged as a pivotal technology in modern scientific research and industrial applications, offering nondestructive, high-resolution analysis with robust molecular fingerprinting capabilities. The extraction of Raman spectral features is a critical step in spectral data analysis, directly influencing sample identification, classification, and quantitative outcomes. However, integrating important data features from machine learning models with context-specific biosignatures to derive meaningful insights into spectral analysis remains a significant challenge. Herein, the Raman Peak Feature Matching (RPFM) method is proposed, which matches protein peak features with salient breast cell data features extracted from the machine learning models. Feature augmentation is subsequently applied to the matching-retained breast cell features, thereby enhancing spectral analysis capabilities. The RPFM method is applied to breast cell spectra for feature augmentation with a reclassification accuracy of 97.12% using a linear support vector machine model, achieving an 8.34% improvement over the model's performance without feature augmentation. The RPFM method has also been successfully implemented in generalized linear logistic regression and tree-based eXtreme gradient boosting, demonstrating its versatility across diverse machine learning algorithms. The RPFM method leverages data-driven machine learning models while compensating for the inability to take into account specific specialized background knowledge. This methodology significantly advances the accuracy and efficacy of spectral analysis in biological and medical applications, offering a novel framework for machine learning algorithms to perform augmented Raman spectral analysis.

Machine Learning Interpretation of Optical Spectroscopy Using Peak-Sensitive Logistic Regression

Optical spectroscopy, a noninvasive molecular sensing technique, offers valuable insights into material characterization, molecule identification, and biosample analysis. Despite the informativeness of high-dimensional optical spectra, their interpretation remains a challenge. Machine learning methods have gained prominence in spectral analyses, efficiently unveiling analyte compositions. However, these methods still face challenges in interpretability, particularly in generating clear feature importance maps that highlight the spectral features specific to each class of data. These limitations arise from feature noise, model complexity, and the lack of optimization for spectroscopy. In this work, we introduce a machine learning algorithm─logistic regression with peak-sensitive elastic-net regularization (PSE-LR)─tailored for spectral analysis. PSE-LR enables classification and interpretability by producing a peak-sensitive feature importance map, achieving an F1-score of 0.93 and a feature sensitivity of 1.0. Its performance is compared with other methods, including k-nearest neighbors (KNN), elastic-net logistic regression (E-LR), support vector machine (SVM), principal component analysis followed by linear discriminant analysis (PCA-LDA), XGBoost, and neural network (NN). Applying PSE-LR to Raman and photoluminescence (PL) spectra, we detected the receptor-binding domain (RBD) of SARS-CoV-2 spike protein in ultralow concentrations, identified neuroprotective solution (NPS) in brain samples, recognized WS2 monolayer and WSe2/WS2 heterobilayer, analyzed Alzheimer's disease (AD) brains, and suggested potential disease biomarkers. Our findings demonstrate PSE-LR's utility in detecting subtle spectral features and generating interpretable feature importance maps. It is beneficial for the spectral characterization of materials, molecules, and biosamples and applicable to other spectroscopic methods. This work also facilitates the development of nanodevices such as nanosensors and miniaturized spectrometers based on nanomaterials.

Interpretable Multiscale Convolutional Neural Network for Classification and Feature Visualization of Weak Raman Spectra of Biomolecules at Cell Membranes

Raman spectroscopy in biological applications faces challenges due to complex spectra, characterized by peaks of varying widths and significant biological background noise. Convolutional neural networks (CNNs) are widely used for spectrum classification due to their ability to capture local peak features. In this study, we introduce a multiscale CNN designed to detect weak biomolecule signals and differentiate spectra with features that cannot be statistically distinguished. The approach is further enhanced by a new visualization technique tailored for multiscale spectral analysis, providing clear insights into classification results. Using the classification of cholera toxin B subunit (CTB)-treated versus untreated cell membrane samples, whose spectra cannot be statistically differentiated, the optimized multiscale CNN achieved superior performance compared to traditional machine learning methods and existing multiscale CNNs, with accuracy (99.22%), sensitivity (99.27%), specificity (99.16%), and precision (99.20%). Our new visualization method, based on gradients of activation maps with respect to class scores, generates saliency scores that capture sample variations, with decision-making relying on consistently identified peak features. By visualizing the effects of different kernel sizes, Grad-AM highlights features at varying scales, aligning closely with spectral features and enhancing CNN interpretability in complex biomolecular analysis. These advancements demonstrate the potential of our method to improve spectral analysis and reveal previously hidden peaks in complex biological environments.

Raman spectroscopy based diagnosis of pancreatic ductal adenocarcinoma

Pancreatic ductal adenocarcinoma is currently the 12th most frequent form of cancer worldwide, characterized by a very low 5-year survival rate. Although several therapeutic approaches have been proposed to treat this form of pancreatic cancer, surgical resection is still commonly recognized as the most effective technique to slow down the disease progression and maximize the 5-year survival rate. Analogously, one critical issue is the ability of current diagnostic methodologies to distinguish between irregular growth of the tumor mass and surrounding inflammatory tissues. In this pilot study, we apply Raman spectroscopy, supported by a series of machine learning techniques, to distinguish among healthy, pancreatitis and ductal adenocarcinoma tissues, respectively, for a total of 15 cases. Raman spectroscopy is a label-free, non-destructive spectral technique exploiting Raman scattering. In turn, by applying a combination of principal component analysis and random forest classifier on the Raman spectral dataset, we achieved a maximum accuracy of up to ∼ 96%. Our findings clearly indicate that Raman spectroscopy could become a powerful spectral technique to support pathologists in improving pancreatic cancer diagnosis.

AI-Assisted Detection for Early Screening of Acute Myeloid Leukemia Using Infrared Spectra and Clinical Biochemical Reports of Blood

Early detection and accurate diagnosis of leukemia pose significant challenges due to the disease's complexity and the need for minimally invasive methods. Acute myeloid leukemia (AML) accounts for most cases of adult leukemia, and our goal is to screen out some AML from adults. In this work, we introduce an AI-enhanced system designed to facilitate early screening and diagnosis of AML among adults. Our approach combines the infrared absorption spectra of serum measured with attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR), which identifies distinctive molecular signatures in lyophilized serum, together with standard clinical blood biochemical test results. We developed a multi-modality spectral transformer network (MSTNetwork) to generate latent space feature vectors from these datasets. Subsequently, these vectors were assessed using a linear discriminant analysis (LDA) algorithm to estimate the likelihood of acute myeloid leukemia. By analyzing blood samples from leukemia patients and the negative control (including non-leukemia patients and healthy individuals), we achieved rapid and accurate prediction and identification of acute myeloid leukemia among adults. Compared to conventional methods relying solely on either FTIR spectra or biochemical indicators of blood, our multi-modality classification system demonstrated higher accuracy and sensitivity, ultimately achieving an accuracy of 98% and a sensitivity of 98%, improving the sensitivity by 12% (compared with using only biochemical indicators) or over 6% (compared with using only FTIR spectra). Our multi-modality classification system is also very robust as it gave much smaller standard deviations of the accuracy and sensitivity. Beyond improving early detection, this work also contributes to a more sustainable and intelligent healthcare sector.

Label-Free Prediction of Tumor Metastatic Potential via Ramanome

Assessing metastatic potential is crucial for cancer treatment strategies. However, current methods are time-consuming, labor-intensive, and have limited sample accessibility. Therefore, this study aims to investigate the urgent need for rapid and accurate approaches by proposing a Ramanome-based metastasis index (RMI) using machine learning of single-cell Raman spectra to rapidly and accurately assess tumor cell metastatic potential. Validation with various cultured tumor cells and a mouse orthotopic model of pancreatic ductal adenocarcinoma show a Kendall rank correlation coefficient of 1 compared to Transwell experiments and histopathological assessments. Significantly, lipid-related Raman peaks are most influential in determining RMI. The lipidomic analysis confirmed strong correlations between metastatic potential and phosphatidylcholine, phosphatidylethanolamine, cholesteryl ester, ceramide, and bis(monoacylglycero)phosphate, crucial in cell membrane composition or signal transduction. Therefore, RMI is a valuable tool for predicting tumor metastatic potential and providing insights into metastasis mechanisms.

Enhanced cancer classification and critical feature visualization using Raman spectroscopy and convolutional neural networks

Cell misuse and cross-contamination pose a significant threat to the accuracy of cell research outcomes, often leading to the wasteful expenditure of time, manpower, and material resources. Consequently, the accurate identification of cell lines is paramount. However, traditional identification methods, which often involve staining and culturing procedures, are not only time-consuming but also laborious. This underscores the need for a novel approach that enables rapid and automated cell line identification, thereby enhancing research efficiency and accuracy. Raman spectroscopy, renowned for its label-free, rapid, and noninvasive nature, offers invaluable molecular insights into samples, making it a widely utilized technique in the biological field. In this study, the identification of one normal and five cancer cell lines was achieved using a sparrow search algorithm-convolutional neural networks (SSA-CNN), considering both the full spectra and fingerprint region perspectives. The SSA-CNN model demonstrated exceptional performance, not just in binary classification, but also in accurately distinguishing among six cell lines. It achieved the highest accuracy (around 95 %), and the lowest standard error (≤3%), for both the full spectra and fingerprint region. Based on the highly accurate SSA-CNN model, proposed the application of gradient-weighted class activation mapping (Grad-CAM) to visualize the Raman feature peaks. Upon comparing the visualized Raman features with reported biomarkers, found that not only were common biomolecules such as glucose, proteins, and liquids visualized, but specific feature peaks also aligned with reported biomarkers. The aforementioned results clearly demonstrated that the proposed strategy not only classifies cancer cell lines with remarkable accuracy but also served as a valuable tool for the discovery of novel biomarkers.

Raman Spectral Feature Enhancement Framework for Complex Multiclassification Tasks

Raman spectroscopy enables label-free clinical diagnosis in a single step. However, identifying an individual carrying a specific disease from people with a multi-disease background is challenging. To address this, we developed a Raman spectral implicit feature augmentation with a Raman Intersection, Union, and Subtraction augmentation strategy (RIUS). RIUS expands the data set without requiring additional labeled data by leveraging set operations at the feature level, significantly enhancing model performance across various applications. On a challenging 30-class bacterial classification task, RIUS demonstrated a substantial improvement, increasing the accuracy of ResNet by 2.1% and that of SE-ResNet by 1.4%, achieving accuracies of 85.7% and 87.1%, respectively, on the Bacteria-ID-4 Data set, where RIUS improved ResNet and SE-ResNet accuracies by 13.6% and 14.5%, respectively, with only ten samples per category. When the sample size was reduced, accuracy gains increased to 31.7% and 38.3%, demonstrating the method's robustness across different sample volumes. Compared to basic augmentation, our method exhibited superior performance across various sample volumes and demonstrated exceptional adaptability to different levels of complexity. RIUS exhibited superior performance, particularly in complex settings. Moreover, cluster analysis validated the effectiveness of the implicit feature augmentation module and the consistency between theoretical design and experimental results. We further validated our approach using clinical serum samples from 70 breast cancer patients and 70 controls, achieving an AUC of 0.94 and a sensitivity of 92.9%. Our approach enhances the potential for precisely identifying diseases in complex settings and offers plug-and-play enhancement for existing classification models.

Rapid and accurate bacteria identification through deep-learning-based two-dimensional Raman spectroscopy

Surface-enhanced Raman spectroscopy (SERS) offers a distinctive vibrational fingerprint of the molecules and has led to widespread applications in medical diagnosis, biochemistry, and virology. With the rapid development of artificial intelligence (AI) technology, AI-enabled Raman spectroscopic techniques, as a promising avenue for biosensing applications, have significantly boosted bacteria identification. By converting spectra into images, the dataset is enriched with more detailed information, allowing AI to identify bacterial isolates with enhanced precision. However, previous studies usually suffer from a trade-off between high-resolution spectrograms for high-accuracy identification and short training time for data processing. Here, we present an efficient bacteria identification strategy that combines deep learning models with a spectrogram encoding algorithm based on wavelet packet transform and Gramian angular field techniques. In contrast to the direct analysis of raw Raman spectra, our approach utilizes wavelet packet transform techniques to compress the spectra by a factor of 1/15, while concurrently maintaining state-of-the-art accuracy by amplifying the subtle differences via Gramian angular field techniques. The results demonstrate that our approach can achieve a 99.64 % and a 90.55 % identification accuracy for two types of bacterial isolates and thirty types of bacterial isolates, respectively, while a 90 % reduction in training time compared to the conventional methods. To verify the model's stability, Gaussian noises were superimposed on the testing dataset, showing a specific generalization ability and superior performance. This algorithm has the potential for integration into on-site testing protocols and is readily updatable with new bacterial isolates. This study provides profound insights and contributes to the current understanding of spectroscopy, paving the way for accurate and rapid bacteria identification in diverse applications of environment monitoring, food safety, microbiology, and public health.

Early cancer detection using deep learning and medical imaging: A survey

Cancer, characterized by the uncontrolled division of abnormal cells that harm body tissues, necessitates early detection for effective treatment. Medical imaging is crucial for identifying various cancers, yet its manual interpretation by radiologists is often subjective, labour-intensive, and time-consuming. Consequently, there is a critical need for an automated decision-making process to enhance cancer detection and diagnosis. Previously, a lot of work was done on surveys of different cancer detection methods, and most of them were focused on specific cancers and limited techniques. This study presents a comprehensive survey of cancer detection methods. It entails a review of 99 research articles collected from the Web of Science, IEEE, and Scopus databases, published between 2020 and 2024. The scope of the study encompasses 12 types of cancer, including breast, cervical, ovarian, prostate, esophageal, liver, pancreatic, colon, lung, oral, brain, and skin cancers. This study discusses different cancer detection techniques, including medical imaging data, image preprocessing, segmentation, feature extraction, deep learning and transfer learning methods, and evaluation metrics. Eventually, we summarised the datasets and techniques with research challenges and limitations. Finally, we provide future directions for enhancing cancer detection techniques.

A double-branch convolutional neural network model for species identification based on multi-modal data

For species identification analysis, methods based on deep learning are becoming prevalent due to their data-driven and task-oriented nature. The most commonly used convolutional neural network (CNN) model has been well applied in Raman spectra recognition. However, when faced with similar molecules or functional groups, the features of overlapping peaks and weak peaks may not be fully extracted using the CNN model, which can potentially hinder accurate species identification. Based on these practical challenges, the fusion of multi-modal data can effectively meet the comprehensive and accurate analysis of actual samples when compared with single-modal data. In this study, we propose a double-branch CNN model by integrating Raman and image multi-modal data, named SI-DBNet. In addition, we have developed a one-dimensional convolutional neural network combining dilated convolutions and efficient channel attention mechanisms for spectral branching. The effectiveness of the model has been demonstrated using the Grad-CAM method to visualize the key regions concerned by the model. When compared to single-modal and multi-modal classification methods, our SI-DBNet model achieved superior performance with a classification accuracy of 98.8%. The proposed method provided a new reference for species identification based on multi-modal data fusion.

Self-immunological disease aid diagnosis with ConvSANet and Eu-clidean distance

BACKGROUND

Ankylosing spondylitis (AS), Osteoarthritis (OA), and Sjögren's syndrome (SS) are three prevalent autoimmune diseases. If left untreated, which can lead to severe joint damage and greatly limit mobility. Once the disease worsens, patients may face the risk of long-term disability, and in severe cases, even life-threatening consequences.

RESULT

In this study, the Raman spectral data of AS, OA, and SS are analyzed to auxiliary disease diagnosis. For the first time, the Euclidean distance(ED) upscaling technique was used for the conversation from one-dimensional(1D) disease spectral data to two-dimensional(2D) spectral images. A dual-attention mechanism network was then constructed to analyze these two-dimensional spectral maps for disease diagnosis. The results demonstrate that the dual-attention mechanism network achieves a diagnostic accuracy of 100 % when analyzing 2D ED spectrograms. Furthermore, a comparison and analysis with s-transforms(ST), short-time fourier transforms(STFT), recurrence maps(RP), markov transform field(MTF), and Gramian angle fields(GAF) highlight the significant advantage of the proposed method, as it significantly shortens the conversion time while supporting disease-assisted diagnosis. Mutual information(MI) was utilized for the first time to validate the 2D Raman spectrograms generated, including ED, ST, STFT, RP, MTF, and GAF spectrograms. This allowed for evaluation of the similarity between the original 1D spectral data and the generated 2D spectrograms.

SIGNIFICANT

The results indicate that utilizing ED to transform 1D spectral data into 2D images, coupled with the application of convolutional neural network(CNN) for analyzing 2D ED Raman spectrograms, holds great promise as a valuable tool in assisting disease diagnosis. The research demonstrated that the 2D spectrogram created with ED closely resembles the original 1D spectral data. This indicates that ED effectively captures key features and important information from the original data, providing a strong descript.

Employing Raman Spectroscopy and Machine Learning for the Identification of Breast Cancer

BACKGROUND

Breast cancer poses a significant health risk to women worldwide, with approximately 30% being diagnosed annually in the United States. The identification of cancerous mammary tissues from non-cancerous ones during surgery is crucial for the complete removal of tumors.

RESULTS

Our study innovatively utilized machine learning techniques (Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN)) alongside Raman spectroscopy to streamline and hasten the differentiation of normal and late-stage cancerous mammary tissues in mice. The classification accuracy rates achieved by these models were 94.47% for RF, 96.76% for SVM, and 97.58% for CNN, respectively. To our best knowledge, this study was the first effort in comparing the effectiveness of these three machine-learning techniques in classifying breast cancer tissues based on their Raman spectra. Moreover, we innovatively identified specific spectral peaks that contribute to the molecular characteristics of the murine cancerous and non-cancerous tissues.

CONCLUSIONS

Consequently, our integrated approach of machine learning and Raman spectroscopy presents a non-invasive, swift diagnostic tool for breast cancer, offering promising applications in intraoperative settings.

Adversarial training collaborating hybrid convolution-transformer network for automatic identification of reactive lymphocytes in peripheral blood

Reactive lymphocytes may indicate diseases such as viral infections. Identifying these abnormal lymphocytes is crucial for disease diagnosis. Currently, reactive lymphocytes are mainly manually identified by pathological experts with microscopes and morphological knowledge, which is time-consuming and laborious. Some studies have used convolutional neural networks (CNNs) to identify peripheral blood leukocytes, but there are limitations in the small receptive field of the model. Our model introduces a transformer based on CNN, expands the receptive field of the model, and enables it to extract global features more efficiently. We also enhance the generalization ability of the model through virtual adversarial training (VAT) without changing the parameters of the model. Finally, our model achieves an overall accuracy of 93.66% on the test set, and the accuracy of reactive lymphocytes also reaches 88.03%. This work takes another step toward the efficient identification of reactive lymphocytes.

Quantitative analysis of the quality constituents of Lonicera japonica Thunberg based on Raman spectroscopy

Quantitative analysis of the quality constituents of Lonicera japonica (Jinyinhua [JYH]) using a feasible method provides important information on its evaluation and applications. Limitations of sample pretreatment, experimental site, and analysis time should be considered when identifying new methods. In response to these considerations, Raman spectroscopy combined with deep learning was used to establish a quantitative analysis model to determine the quality of JYH. Chlorogenic acid and total flavonoids were identified as analysis targets via network pharmacology. High performance liquid chromatograph and ultraviolet spectroscopy were used to construct standard curves for quantitative analysis. Raman spectra of JYH extracts (1200) were collected. Subsequently, models were built using partial least squares regression, Support Vector Machine, Back Propagation Neural Network, and One-dimensional Convolutional Neural Network (1D-CNN). Among these, the 1D-CNN model showed superior prediction capability and had higher accuracy (R2 = 0.971), and lower root mean square error, indicating its suitability for rapid quantitative analysis.

Detection of lung cancer through SERS analysis of serum

Early detection and postoperative assessment are crucial for improving overall survival among lung cancer patients. Here, we report a non-invasive technique that integrates Raman spectroscopy with machine learning for the detection of lung cancer. The study encompassed 88 postoperative lung cancer patients, 73 non-surgical lung cancer patients, and 68 healthy subjects. The primary aim was to explore variations in serum metabolism across these cohorts. Comparative analysis of average Raman spectra was conducted, while principal component analysis was employed for data visualization. Subsequently, the augmented dataset was used to train convolutional neural networks (CNN) and Resnet models, leading to the development of a diagnostic framework. The CNN model exhibited superior performance, as verified by the receiver operating characteristic curve. Notably, postoperative patients demonstrated an increased likelihood of recurrence, emphasizing the crucial need for continuous postoperative monitoring. In summary, the integration of Raman spectroscopy with CNN-based classification shows potential for early detection and postoperative assessment of lung cancer.

Serum analysis based on SERS combined with 2D convolutional neural network and Gramian angular field for breast cancer screening

Breast cancer is a significant cause of death among women worldwide. It is crucial to quickly and accurately diagnose breast cancer in order to reduce mortality rates. While traditional diagnostic techniques for medical imaging and pathology samples have been commonly used in breast cancer screening, they still have certain limitations. Surface-enhanced Raman spectroscopy (SERS) is a fast, highly sensitive and user-friendly method that is often combined with deep learning techniques like convolutional neural networks. This combination helps identify unique molecular spectral features, also known as "fingerprint", in biological samples such as serum. Ultimately, this approach is able to accurately screen for cancer. The Gramian angular field (GAF) algorithm can convert one-dimensional (1D) time series into two-dimensional (2D) images. These images can be used for data visualization, pattern recognition and machine learning tasks. In this study, 640 serum SERS from breast cancer patients and healthy volunteers were converted into 2D spectral images by Gramian angular field (GAF) technique. These images were then used to train and test a two-dimensional convolutional neural network-GAF (2D-CNN-GAF) model for breast cancer classification. We compared the performance of the 2D-CNN-GAF model with other methods, including one-dimensional convolutional neural network (1D-CNN), support vector machine (SVM), K-nearest neighbor (KNN) and principal component analysis-linear discriminant analysis (PCA-LDA), using various evaluation metrics such as accuracy, precision, sensitivity, F1-score, receiver operating characteristic (ROC) curve and area under curve (AUC) value. The results showed that the 2D-CNN model outperformed the traditional models, achieving an AUC value of 0.9884, an accuracy of 98.13%, sensitivity of 98.65% and specificity of 97.67% for breast cancer classification. In this study, we used conventional nano-silver sol as the SERS-enhanced substrate and a portable laser Raman spectrometer to obtain the serum SERS data. The 2D-CNN-GAF model demonstrated accurate and automatic classification of breast cancer patients and healthy volunteers. The method does not require augmentation and preprocessing of spectral data, simplifying the processing steps of spectral data. This method has great potential for accurate breast cancer screening and also provides a useful reference in more types of cancer classification and automatic screening.

A novel method for detection of pancreatic Ductal Adenocarcinoma using explainable machine learning

BACKGROUND AND OBJECTIVE

Pancreatic Ductal Adenocarcinoma (PDAC) is a form of pancreatic cancer that is one of the primary causes of cancer-related deaths globally, with less than 10 % of the five years survival rate. The prognosis of pancreatic cancer has remained poor in the last four decades, mainly due to the lack of early diagnostic mechanisms. This study proposes a novel method for detecting PDAC using explainable and supervised machine learning from Raman spectroscopic signals.

METHODS

An insightful feature set consisting of statistical, peak, and extended empirical mode decomposition features is selected using the support vector machine recursive feature elimination method integrated with a correlation bias reduction. Explicable features successfully identified mutations in Kirsten rat sarcoma viral oncogene homolog (KRAS) and tumor suppressor protein53 (TP53) in the fingerprint region for the first time in the literature. PDAC and normal pancreas are classified using K-nearest neighbor, linear discriminant analysis, and support vector machine classifiers.

RESULTS

This study achieved a classification accuracy of 98.5% using a nonlinear support vector machine. Our proposed method reduced test time by 28.5 % and saved 85.6 % memory utilization, which reduces complexity significantly and is more accurate than the state-of-the-art method. The generalization of the proposed method is assessed by fifteen-fold cross-validation, and its performance is evaluated using accuracy, specificity, sensitivity, and receiver operating characteristic curves.

CONCLUSIONS

In this study, we proposed a method to detect and define the fingerprint region for PDAC using explainable machine learning. This simple, accurate, and efficient method for PDAC detection in mice could be generalized to examine human pancreatic cancer and provide a basis for precise chemotherapy for early cancer treatment.

RaT: Raman Transformer for highly accurate melanoma detection with critical features visualization

Melanoma is an important cause of death from skin cancer. Early and accurate diagnosis can effectively reduce mortality. But the current diagnosis relies on the experience of pathologists, increasing the rate of misdiagnosis. In this paper, Raman Transformer (RaT) model is proposed by combining Raman spectroscopy and a Transformer encoder to distinguish the Raman spectra of melanoma and normal tissue. To make the spectral data more suitable for the Transformer encoder, we split the Raman spectrum into segments and map them into block vectors, which are then input into the Transformer encoder and classified using the multi-head self-attention mechanism and the Multilayer Perceptron (MLP). The RaT model achieves 99.69% accuracy, 99.61% sensitivity, and 99.82% specificity, which is higher than the classical principal component analysis with the neural network (PCA + NNET) method. In addition, we visualize and explain the fingerprint peaks found by the RaT model and their corresponding biological information. Our proposed RaT model provides a novel and reliable method for processing Raman spectral data, which is expected to help distinguish melanoma from normal cells, diagnose other diseases, and save human lives.

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.

Unveiling breast cancer risk profiles: a survival clustering analysis empowered by an online web application

Aim: To develop a shiny app for doctors to investigate breast cancer treatments through a new approach by incorporating unsupervised clustering and survival information. Materials & methods: Analysis is based on the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset, which contains 1726 subjects and 22 variables. Cox regression was used to identify survival risk factors for K-means clustering. Logrank tests and C-statistics were compared across different cluster numbers and Kaplan-Meier plots were presented. Results & conclusion: Our study fills an existing void by introducing a unique combination of unsupervised learning techniques and survival information on the clinician side, demonstrating the potential of survival clustering as a valuable tool in uncovering hidden structures based on distinct risk profiles.

Combined analytical approach empowers precise spectroscopic interpretation of subcellular components of pancreatic cancer cells

The lack of specific and sensitive early diagnostic options for pancreatic cancer (PC) results in patients being largely diagnosed with late-stage disease, thus inoperable and burdened with high mortality. Molecular spectroscopic methodologies, such as Raman or infrared spectroscopies, show promise in becoming a leader in screening for early-stage cancer diseases, including PC. However, should such technology be introduced, the identification of differentiating spectral features between various cancer types is required. This would not be possible without the precise extraction of spectra without the contamination by necrosis, inflammation, desmoplasia, or extracellular fluids such as mucous that surround tumor cells. Moreover, an efficient methodology for their interpretation has not been well defined. In this study, we compared different methods of spectral analysis to find the best for investigating the biomolecular composition of PC cells cytoplasm and nuclei separately. Sixteen PC tissue samples of main PC subtypes (ductal adenocarcinoma, intraductal papillary mucinous carcinoma, and ampulla of Vater carcinoma) were collected with Raman hyperspectral mapping, resulting in 191,355 Raman spectra and analyzed with comparative methodologies, specifically, hierarchical cluster analysis, non-negative matrix factorization, T-distributed stochastic neighbor embedding, principal components analysis (PCA), and convolutional neural networks (CNN). As a result, we propose an innovative approach to spectra classification by CNN, combined with PCA for molecular characterization. The CNN-based spectra classification achieved over 98% successful validation rate. Subsequent analyses of spectral features revealed differences among PC subtypes and between the cytoplasm and nuclei of their cells. Our study establishes an optimal methodology for cancer tissue spectral data classification and interpretation that allows precise and cognitive studies of cancer cells and their subcellular components, without mixing the results with cancer-surrounding tissue. As a proof of concept, we describe findings that add to the spectroscopic understanding of PC.

Diagnoses in multiple types of cancer based on serum Raman spectroscopy combined with a convolutional neural network: Gastric cancer, colon cancer, rectal cancer, lung cancer

Cancer is one of the major diseases that seriously threaten human health. Timely screening is beneficial to the cure of cancer. There are some shortcomings in current diagnosis methods, so it is very important to find a low-cost, fast, and nondestructive cancer screening technology. In this study, we demonstrated that serum Raman spectroscopy combined with a convolutional neural network model can be used for the diagnosis of four types of cancer including gastric cancer, colon cancer, rectal cancer, and lung cancer. Raman spectra database containing four types of cancer and healthy controls was established and a one-dimensional convolutional neural network (1D-CNN) was constructed. The classification accuracy of the Raman spectra combined with the 1D-CNN model was 94.5%. A convolutional neural network (CNN) is regarded as a black box, and the learning mechanism of the model is not clear. Therefore, we tried to visualize the CNN features of each convolutional layer in the diagnosis of rectal cancer. Overall, Raman spectroscopy combined with the CNN model is an effective tool that can be used to distinguish different cancer from healthy controls.

Advanced electrocatalytic materials based biosensors for cancer cell detection – A review

Herein, we have highlighted the latest developments on biosensors for cancer cell detection. Electrochemical (EC) biosensors offer several advantages such as high sensitivity, selectivity, rapid analysis, portability, low‐cost, etc. Generally, biosensors could be classified into other basic categories such as immunosensors, aptasensors, cytosensors, electrochemiluminescence (ECL), and photo‐electrochemical (PEC) sensors. The significance of the EC biosensors is that they could detect several biomolecules in human body including cholesterol, glucose, lactate, uric acid, DNA, blood ketones, hemoglobin, and others. Recently, various EC biosensors have been developed by using electrocatalytic materials such as silver sulfide (Ag2S), black phosphene (BPene), hexagonal carbon nitrogen tube (HCNT), carbon dots (CDs)/cobalt oxy‐hydroxide (CoOOH), cuprous oxide (Cu2O), polymer dots (PDs), manganese oxide (MnO2), graphene derivatives, and gold nanoparticles (Au‐NPs). In some cases, these newly developed biosensors could be able to detect cancer cells with a limit of detection (LOD) of 1 cell/mL. In addition, many remaining challenges have to be addressed and validated by testing more real samples and confirm that these EC biosensors are more accurate and reliable to measure cancer cells in the blood and salivary samples.

Practices, Potential, and Perspectives for Detecting Predisease Using Raman Spectroscopy

Raman spectroscopy shows great potential for practical clinical applications. By analyzing the structure and composition of molecules through real-time, non-destructive measurements of the scattered light from living cells and tissues, it offers valuable insights. The Raman spectral data directly link to the molecular composition of the cells and tissues and provides a "molecular fingerprint" for various disease states. This review focuses on the practical and clinical applications of Raman spectroscopy, especially in the early detection of human diseases. Identifying predisease, which marks the transition from a healthy to a disease state, is crucial for effective interventions to prevent disease onset. Raman spectroscopy can reveal biological processes occurring during the transition states and may eventually detect the molecular dynamics in predisease conditions.

Original and liposome-modified indocyanine green-assisted fluorescence study with animal models

Medical diagnosis heavily relies on the use of bio-imaging techniques. One such technique is the use of ICG-based biological sensors for fluorescence imaging. In this study, we aimed to improve the fluorescence signals of ICG-based biological sensors by incorporating liposome-modified ICG. The results from dynamic light scattering and transmission electron microscopy showed that MLM-ICG was successfully fabricated with a liposome diameter of 100-300 nm. Fluorescence spectroscopy showed that MLM-ICG had the best properties among the three samples (Blank ICG, LM-ICG, and MLM-ICG), as samples immersed in MLM-ICG solution achieved the highest fluorescence intensity. The NIR camera imaging also showed a similar result. For the rat model, the best period for fluorescence tests was between 10 min and 4 h, where most organs reached their maximum fluorescence intensity except for the liver, which continued to rise. After 24 h, ICG was excreted from the rat's body. The study also analyzed the spectra properties of different rat organs, including peak intensity, peak wavelength, and FWHM. In conclusion, the use of liposome-modified ICG provides a safe and optimized optical agent, which is more stable and efficient than non-modified ICG. Incorporating liposome-modified ICG in fluorescence spectroscopy could be an effective way to develop novel biosensors for disease diagnosis.

A multi-view co-training network for semi-supervised medical image-based prognostic prediction

Prognostic prediction has long been a hotspot in disease analysis and management, and the development of image-based prognostic prediction models has significant clinical implications for current personalized treatment strategies. The main challenge in prognostic prediction is to model a regression problem based on censored observations, and semi-supervised learning has the potential to play an important role in improving the utilization efficiency of censored data. However, there are yet few effective semi-supervised paradigms to be applied. In this paper, we propose a semi-supervised co-training deep neural network incorporating a support vector regression layer for survival time estimation (Co-DeepSVS) that improves the efficiency in utilizing censored data for prognostic prediction. First, we introduce a support vector regression layer in deep neural networks to deal with censored data and directly predict survival time, and more importantly to calculate the labeling confidence of each case. Then, we apply a semi-supervised multi-view co-training framework to achieve accurate prognostic prediction, where labeling confidence estimation with prior knowledge of pseudo time is conducted for each view. Experimental results demonstrate that the proposed Co-DeepSVS has a promising prognostic ability and surpasses most widely used methods on a multi-phase CT dataset. Besides, the introduction of SVR layer makes the model more robust in the presence of follow-up bias.

A classification model for detection of ductal carcinoma in situ by Fourier transform infrared spectroscopy based on deep structured semantic model

At present, deep learning is widely used in spectral data processing. Deep learning requires a large amount of data for training, while the collection of biological serum spectra is limited by sample numbers and labor costs, so it is impractical to obtain a large amount of serum spectral data for disease detection. In this study, we propose a spectral classification model based on the deep structured semantic model (DSSM) and successfully apply it to Fourier Transform Infrared (FT-IR) spectroscopy for ductal carcinoma in situ (DCIS) detection. Compared with the traditional deep learning model, we match the spectral data into positive and negative pairs according to whether the spectra are from the same category. The DSSM structure is constructed by extracting features according to the spectral similarity of spectra pairs. This new construction model increases the data amount used for model training and reduces the dimension of spectral data. Firstly, the FT-IR spectra are paired. The spectra pairs are labeled as positive pairs if they come from the same category, and the spectra pairs are labeled as negative pairs if they come from different categories. Secondly, two spectra in each spectra pair are put into two deep neural networks of the DSSM structure separately. Then the spectral similarity between the output feature maps of two deep neural networks is calculated. The DSSM structure is trained by maximizing the conditional likelihood of the spectra pairs from the same category. Thirdly, after the training of DSSM is done, the training set and testing set are input into two deep neural networks separately. The output feature maps of the training set are put into the reference library. Lastly, the k-nearest neighbor (KNN) model is used for classification according to Euclidean distances between the output feature map of each unknown sample to the reference library. The category of the unknown sample is judged according to the categories of k nearest samples. We also use principal component analysis (PCA) to reduce dimension for comparison. The accuracies of the KNN model, principal component analysis-k nearest neighbor (PCA-KNN) model, and deep structured semantic model-k nearest neighbor (DSSM-KNN) model are 78.8%, 72.7%, and 97.0%, which proves that our proposed model has higher accuracy.

Industrial wastewater source tracing: The initiative of SERS spectral signature aided by a one-dimensional convolutional neural network

The spectral fingerprint is a significant concept in nontarget screening of environmental samples to direct identification efforts to relevant and important features. Surface-enhanced Raman scattering (SERS) has long been recognized as an optical method that can provide fingerprint-like chemical information at the single-molecule level. Here, the advanced one-dimensional convolutional neural network (1D-CNN) approach was applied to accurately identify the SERS spectral signature of industrial wastewaters for source tracing. A total of 66,000 SERS spectra were acquired from wastewaters of 22 factories across 10 industrial categories at three excitation wavelengths after data augmentation. The dataset was used to train a 1D-CNN model consisting of three convolutional layers to achieve adequate feature extraction of SERS spectra. As a proof-of-concept, multimixed wastewater samples were used to simulate practical pollution scenarios and evaluate the application potential of the model. The SERS-1D-CNN platform can identify the amount and factory information of wastewaters in multimixed samples, which achieves a recognition accuracy rate of 97.33%. The results suggest that even in a complex and unknown water environment, the 1D-CNN model can accurately identify industrial wastewaters in precollected datasets, exhibiting excellent potential in pollution source tracing.

Classification of pathogenic bacteria by Raman spectroscopy combined with variational auto-encoder and deep learning

Rapid and early identification of pathogens is critical to guide antibiotic therapy. Raman spectroscopy as a noninvasive diagnostic technique provides rapid and accurate detection of pathogens. Raman spectrum of single cells serves as the "fingerprint" of the cell, revealing its metabolic characteristics. Rapid identification of pathogens can be achieved by combining Raman spectroscopy and deep learning. Traditional classification techniques frequently require lots of data for training, which is time costing to collect Raman spectra. For trace samples and strains that are difficult to culture, it is difficult to provide an accurate classification model. In order to reduce the number of samples collected and improve the accuracy of the classification model, a new pathogen detection method integrating Raman spectroscopy, variational auto-encoder (VAE), and long short-term memory network (LSTM) is proposed in this paper. We collect the Raman signals of pathogens and input them to VAE for training. VAE will generate a large number of Raman spectral data that cannot be distinguished from the real spectrum, and the signal-to-noise ratio is higher than that of the real spectrum. These spectra are input into the LSTM together with the real spectrum for training, and a good classification model is obtained. The results of the experiments reveal that this method not only improves the average accuracy of pathogen classification to 96.9% but also reduces the number of Raman spectra collected from 1000 to 200. With this technology, the number of Raman spectra collected can be greatly reduced, so that strains that are difficult to culture or trace can be rapidly identified.

Accurate identification of living Bacillus spores using laser tweezers Raman spectroscopy and deep learning

Accurately, rapidly, and noninvasively identifying Bacillus spores can greatly contribute to controlling a plenty of infectious diseases. Laser tweezers Raman spectroscopy (LTRS) has confirmed to be a powerful tool for studying Bacillus spores at a single cell level. In this study, we constructed a single-cell Raman spectra dataset of living Bacillus spores and utilized deep learning approach to accurately, nondestructively identify Bacillus spores. The trained convolutional neural network (CNN) could efficiently extract tiny Raman spectra features of five spore species, and provide a prediction accuracy of specie identification as high as 100 %. Moreover, the spectral feature differences in three Raman bands at 660, 826, and 1017 cm^-1 were confirmed to mostly contribute to producing such high prediction accuracy. In addition, optimal CNN model was employed to monitor and identify sporulation process at different metabolic phases in one growth cycle. The obtained average prediction accuracy of metabolic phase identification was approximately 88 %. It can be foreseen that, LTRS combined with CNN approach have great potential for accurately identifying spore species and metabolic phases at a single cell level, and can be gradually extended to perform identification for many unculturable bacteria growing in soil, water, and food.

Variabilities in global DNA methylation and β-sheet richness establish spectroscopic landscapes among subtypes of pancreatic cancer

PURPOSE

Knowledge about pancreatic cancer (PC) biology has been growing rapidly in recent decades. Nevertheless, the survival of PC patients has not greatly improved. The development of a novel methodology suitable for deep investigation of the nature of PC tumors is of great importance. Molecular imaging techniques, such as Fourier transform infrared (FTIR) spectroscopy and Raman hyperspectral mapping (RHM) combined with advanced multivariate data analysis, were useful in studying the biochemical composition of PC tissue.

METHODS

Here, we evaluated the potential of molecular imaging in differentiating three groups of PC tumors, which originate from different precursor lesions. Specifically, we comprehensively investigated adenocarcinomas (ACs): conventional ductal AC, intraductal papillary mucinous carcinoma, and ampulla of Vater AC. FTIR microspectroscopy and RHM maps of 24 PC tissue slides were obtained, and comprehensive advanced statistical analyses, such as hierarchical clustering and nonnegative matrix factorization, were performed on a total of 211,355 Raman spectra. Additionally, we employed deep learning technology for the same task of PC subtyping to enable automation. The so-called convolutional neural network (CNN) was trained to recognize spectra specific to each PC group and then employed to generate CNN-prediction-based tissue maps. To identify the DNA methylation spectral markers, we used differently methylated, isolated DNA and compared the observed spectral differences with the results obtained from cellular nuclei regions of PC tissues.

RESULTS

The results showed significant differences among cancer tissues of the studied PC groups. The main findings are the varying content of β-sheet-rich proteins within the PC cells and alterations in the relative DNA methylation level. Our CNN model efficiently differentiated PC groups with 94% accuracy. The usage of CNN in the classification task did not require Raman spectral data preprocessing and eliminated the need for extensive knowledge of statistical methodologies.

CONCLUSIONS

Molecular spectroscopy combined with CNN technology is a powerful tool for PC detection and subtyping. The molecular fingerprint of DNA methylation and β-sheet cytoplasmic proteins established by our results is different for the main PC groups and allowed the subtyping of pancreatic tumors, which can improve patient management and increase their survival. Our observations are of key importance in understanding the variability of PC and allow translation of the methodology into clinical practice by utilizing liquid biopsy testing.

Investigation of probability maps in deep-learning-based brain ventricle parcellation

Normal Pressure Hydrocephalus (NPH) is a brain disorder associated with ventriculomegaly. Accurate segmentation of the ventricle system into its sub-compartments from magnetic resonance images (MRIs) could help evaluate NPH patients for surgical intervention. In this paper, we modify a 3D U-net utilizing probability maps to perform accurate ventricle parcellation, even with grossly enlarged ventricles and post-surgery shunt artifacts, from MRIs. Our method achieves a mean dice similarity coefficient (DSC) on whole ventricles for healthy controls of 0.864 ± 0.047 and 0.961 ± 0.024 for NPH patients. Furthermore, with the benefit of probability maps, the proposed method provides superior performance on MRI with grossly enlarged ventricles (mean DSC value of 0.965 ± 0.027) or post-surgery shunt artifacts (mean DSC value of 0.964 ± 0.031). Results indicate that our method provides a high robust parcellation tool on the ventricular systems which is comparable to other state-of-the-art methods.

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.

Lock-in Raman difference spectroscopy

Shifted Excitation Raman Difference Spectroscopy (SERDS) is a non-destructive chemical analysis method capable of removing the fluorescence background and other disturbances from the Raman spectrum, thanks to the independence of the fluorescence with respect to the small difference in excitation wavelength. The spectrum difference is computed in a post-processing step. Here, we demonstrate the use of a lock-in camera to obtain an on-line analog SERDS spectra allowing longer exposure times and no saturation, leading to an improved Signal-to-Noise Ratio (SNR) and reduced data storage. Two configurations are presented: the first one uses a single laser and can remove excitation-independent disturbances, such as ambient light; the second employs two-wavelength shifted sources and removes fluorescence background similarly to SERDS. In both cases, we experimentally extrapolate the expected SNR improvement.

Emerging Applications of Deep Learning in Bone Tumors: Current Advances and Challenges

Deep learning is a subfield of state-of-the-art artificial intelligence (AI) technology, and multiple deep learning-based AI models have been applied to musculoskeletal diseases. Deep learning has shown the capability to assist clinical diagnosis and prognosis prediction in a spectrum of musculoskeletal disorders, including fracture detection, cartilage and spinal lesions identification, and osteoarthritis severity assessment. Meanwhile, deep learning has also been extensively explored in diverse tumors such as prostate, breast, and lung cancers. Recently, the application of deep learning emerges in bone tumors. A growing number of deep learning models have demonstrated good performance in detection, segmentation, classification, volume calculation, grading, and assessment of tumor necrosis rate in primary and metastatic bone tumors based on both radiological (such as X-ray, CT, MRI, SPECT) and pathological images, implicating a potential for diagnosis assistance and prognosis prediction of deep learning in bone tumors. In this review, we first summarized the workflows of deep learning methods in medical images and the current applications of deep learning-based AI for diagnosis and prognosis prediction in bone tumors. Moreover, the current challenges in the implementation of the deep learning method and future perspectives in this field were extensively discussed.

Multiple-Inputs Convolutional Neural Network for COVID-19 Classification and Critical Region Screening From Chest X-ray Radiographs: Model Development and Performance Evaluation

Background

The COVID-19 pandemic is becoming one of the largest, unprecedented health crises, and chest X-ray radiography (CXR) plays a vital role in diagnosing COVID-19. However, extracting and finding useful image features from CXRs demand a heavy workload for radiologists.

Objective

The aim of this study was to design a novel multiple-inputs (MI) convolutional neural network (CNN) for the classification of COVID-19 and extraction of critical regions from CXRs. We also investigated the effect of the number of inputs on the performance of our new MI-CNN model.

Methods

A total of 6205 CXR images (including 3021 COVID-19 CXRs and 3184 normal CXRs) were used to test our MI-CNN models. CXRs could be evenly segmented into different numbers (2, 4, and 16) of individual regions. Each region could individually serve as one of the MI-CNN inputs. The CNN features of these MI-CNN inputs would then be fused for COVID-19 classification. More importantly, the contributions of each CXR region could be evaluated through assessing the number of images that were accurately classified by their corresponding regions in the testing data sets.

Results

In both the whole-image and left- and right-lung region of interest (LR-ROI) data sets, MI-CNNs demonstrated good efficiency for COVID-19 classification. In particular, MI-CNNs with more inputs (2-, 4-, and 16-input MI-CNNs) had better efficiency in recognizing COVID-19 CXRs than the 1-input CNN. Compared to the whole-image data sets, the efficiency of LR-ROI data sets showed approximately 4% lower accuracy, sensitivity, specificity, and precision (over 91%). In considering the contributions of each region, one of the possible reasons for this reduced performance was that nonlung regions (eg, region 16) provided false-positive contributions to COVID-19 classification. The MI-CNN with the LR-ROI data set could provide a more accurate evaluation of the contribution of each region and COVID-19 classification. Additionally, the right-lung regions had higher contributions to the classification of COVID-19 CXRs, whereas the left-lung regions had higher contributions to identifying normal CXRs.

Conclusions

Overall, MI-CNNs could achieve higher accuracy with an increasing number of inputs (eg, 16-input MI-CNN). This approach could assist radiologists in identifying COVID-19 CXRs and in screening the critical regions related to COVID-19 classifications.