Rapid identification of cervical adenocarcinoma and cervical squamous cell carcinoma tissue based on Raman spectroscopy combined with multiple machine learning algorithms

Alterations in lipid metabolism accompanied by changes in protein and carotenoid content as spectroscopic markers of human T cell activation

This work aims to understand better the mechanism of cellular processes accompanying the activation of human T cells and to develop a novel, fast, label-free approach to identify molecular biomarkers for this process. The standard methodology for confirming the activation state of T cells is based on flow cytometry and using antibodies recognizing activation markers. The method provide high specificity detection but may be susceptible to background staining or non-specific secondary antibody reactions. Here, we evaluated the potential of Raman-based molecular imaging in distinguishing non-activated and activated human T cells. Confocal Raman microscopy was performed on T cells followed by chemometrics to obtain comprehensive molecular information, while Stimulated Raman Scattering imaging was used to quickly provide high-resolution images of selected cellular components of activated and non-activated cells. For the first time, carotenoids, lipids, and proteins were shown to be important biomarkers of T-cell activation. We found that T-cell activation was accompanied by lipid accumulation and loss of carotenoid content. Our findings on the biochemical, morphological, and structural changes associated with activated mature T cells provide insights into the molecular changes that occur during therapeutic manipulation of the immune response. The methodology for identifying activated T cells is based on a novel imaging method and supervised and unsupervised chemometrics. It unambiguously identifies specific and unique molecular changes without the need for staining, fixation, or any other sample preparation.

Spatial distribution and source identification of potentially toxic elements in Yellow River Delta soils, China: An interpretable machine-learning approach

Identifying the driving factors and quantifying the sources of potentially toxic elements (PTEs) are essential for protecting the ecological environment of the Yellow River Delta. In this study, data from 201 surface soil samples and 16 environmental variables were collected, and the random forest (RF) and Shapley additive explanations (SHAP) methods were then combined to explore the key factors affecting soil PTEs. An innovative t-distributed random neighbor embedding-RF-SHAP model was then constructed, based on the absolute principal component score and multivariate linear regression model, to quantitatively determine PTE sources. Although average PTE concentrations did not exceed the risk control values, PTE distributions exhibited significant differences. It was found that sodium, soil organic matter, and phosphorus contents were the three most important factors affecting PTEs, and human activities and natural environmental factors both influence PTE contents by altering the soil properties. The proposed model successfully determined PTE sources in the soil, outperforming the original linear regression model with a significantly lower RMSE. Source analysis revealed that the parent material was the main contributor to soil PTEs, accounting for more than half of the total PTE content. Industrial and agricultural activities also contributed to an increase in soil PTEs, with average contributions of 19.91 % and 17.44 %, respectively. Unknown sources accounted for 10.83 % of the total PTE content. Thus, the proposed model provides innovative perspectives on source parsing. These findings provide valuable scientific insights for policymakers seeking to develop effective environmental protection measures and improve the quality of saline-alkali land in the Yellow River Delta.

For cervical cancer diagnosis: Tissue Raman spectroscopy and multi-level feature fusion with SENet attention mechanism

Cervical cancer ranks among the most prevalent forms of gynecological malignancies. Timely identification of cervical lesions and prompt intervention can effectively prevent the development of cervical cancer or enhance patients' chances of survival. In this study, we propose an innovative method based on Raman spectroscopy, i.e., a multi-level SENet attention mechanism feature fusion architecture (MAFA) for rapid diagnosis of cervical cancer and precancerous lesions. The convolution process of this architecture can extract features from shallow to deep layers, and the attention mechanism is added to achieve the fusion of features from different layers. The added attention mechanism can automatically determine the importance of each layer feature channel and assign weight values to that layer according to the importance of each layer to achieve the purpose of focusing the model on certain waveform features and improve the targeting of model learning. We collected Raman spectra of 212 cervical tissues containing cervical cancer and its precancerous lesions.The experimental results show that MAFA can effectively improve the diagnostic accuracy of VGGNet, GoogLeNet and ResNet models in the validation of Raman spectral data of cervical tissue. Among them, ResNet performed the best, with the highest average accuracy, precision, recall and F1-Score of 82.36%, 84.00%, 82.35% and 82.26%, respectively, when no feature fusion was performed. The evaluation metrics improved by 4.91%, 3.97%, 4.97%, and 5.06%, respectively, after using the MAFA; they also improved by 4.16%, 2.90%, 4.17%, and 4.32%, respectively, compared with the model that directly performs feature fusion without using the attention mechanism. Therefore, the MAFA proposed in this study is better than that of the neural network that directly fuses the features of each convolutional layer. The experimental results show that the performance of the MAFA proposed in this paper is significantly higher than that of traditional deep learning algorithms, indicating that the present architecture can effectively improve the diagnostic accuracy of deep learning networks for cervical cancer.

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

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

Optical imaging for early detection of cervical cancer: state of the art and perspectives

Significance

Cervical cancer is one of the major causes of death in females worldwide. HPV infection is the key cause of uncontrolled cell growth leading to cervical cancer. About 90% of cervical cancer is preventable because of the slow progression of the disease, giving a window of about 10 years for the precancerous lesion to be recognized and treated.

Aim

The present challenges for cervical cancer diagnosis are interobserver variation in clinicians' interpretation of visual inspection with acetic acid/visual inspection with Lugol's iodine, cost of cytology-based screening, and lack of skilled clinicians. The optical modalities can assist in qualitatively and quantitatively analyzing the tissue to differentiate between cancerous and surrounding normal tissues.

Approach

This work is on the recent advances in optical techniques for cervical cancer diagnosis, which promise to overcome the above-listed challenges faced by present screening techniques.

Results

The optical modalities provide substantial measurable information in addition to the conventional colposcopy and Pap smear test to clinically aid the diagnosis.

Conclusions

Recent optical modalities on fluorescence, multispectral imaging, polarization-sensitive imaging, microendoscopy, Raman spectroscopy, especially with the portable design and assisted by artificial intelligence, have a significant scope in the diagnosis of premalignant cervical cancer in future.

Determination of esophageal squamous cell carcinoma and gastric adenocarcinoma on raw tissue using Raman spectroscopy

BACKGROUND

Cancer detection is a global research focus, and novel, rapid, and label-free techniques are being developed for routine clinical practice. This has led to the development of new tools and techniques from the bench side to routine clinical practice. In this study, we present a method that uses Raman spectroscopy (RS) to detect cancer in unstained formalin-fixed, resected specimens of the esophagus and stomach. Our method can record a clear Raman-scattered light spectrum in these specimens, confirming that the Raman-scattered light spectrum changes because of the histological differences in the mucosal tissue.

AIM

To evaluate the use of Raman-scattered light spectrum for detecting endoscop-ically resected specimens of esophageal squamous cell carcinoma (SCC) and gastric adenocarcinoma (AC).

METHODS

We created a Raman device that is suitable for observing living tissues, and attempted to acquire Raman-scattered light spectra in endoscopically resected specimens of six esophageal tissues and 12 gastric tissues. We evaluated formalin-fixed tissues using this technique and captured shifts at multiple locations based on feasibility, ranging from six to 19 locations 200 microns apart in the vertical and horizontal directions. Furthermore, a correlation between the obtained Raman scattered light spectra and histopathological diagnosis was performed.

RESULTS

We successfully obtained Raman scattered light spectra from all six esophageal and 12 gastric specimens. After data capture, the tissue specimens were sent for histopathological analysis for further processing because RS is a label-free methodology that does not cause tissue destruction or alterations. Based on data analysis of molecular-level substrates, we established cut-off values for the diagnosis of esophageal SCC and gastric AC. By analyzing specific Raman shifts, we developed an algorithm to identify the range of esophageal SCC and gastric AC with an accuracy close to that of histopathological diagnoses.

CONCLUSION

Our technique provides qualitative information for real-time morphological diagnosis. However, further in vivo evaluations require an excitation light source with low human toxicity and large amounts of data for validation.

Advancing cervical cancer diagnosis and screening with spectroscopy and machine learning

INTRODUCTION

In the UK alone, the incidence of cervical cancer is increasing, hence an urgent need for early and rapid detection of cancer before it develops. Spectroscopy in conjunction with machine learning offers a disruptive technology that promises to be pick up cancer early as compared to the current diagnostic techniques used.

AREAS COVERED

This review article explores the different spectroscopy techniques that have been used for the analysis of cervical cancer. Along with the extensive description of spectroscopic techniques, the various machine learning techniques are also described as well as the applications that have been explored in the diagnosis of cervical cancer. This review delimits the literature specifically associated with cervical cancer studies performed solely with the use of a spectroscopy technique, and machine learning.

EXPERT OPINION

Although there are several methods and techniques to detect cervical cancer, the clinical sector requires to introduce new diagnostic technologies that help improving the quality of life of patient. These innovative technologies involve spectroscopy as a qualitative method and machine learning as a quantitative method. In this article, both the techniques and methodologies that allow and promise to be a new screening tool for the detection of cervical cancer is covered.

APTw combined with mDixon-Quant imaging to distinguish the differentiation degree of cervical squamous carcinoma

Background

To investigate the value of amide proton transfer weighted (APTw) imaging combined with modified Dixon fat quantification (mDixon-Quant) imaging in determining the degree of differentiation of cervical squamous carcinoma (CSC) against histopathologic.

Methods

Magnetic resonance imaging (MRI) data were collected from 52 CSC patients. According to histopathologic results, patients were divided into the poorly differentiated group (37 cases) and the well/moderately differentiated group (15 cases). The APTw value by APTw imaging and the fat fraction (FF) and transverse relaxation rate R 2 * values by mDixon-Quant were independently measured by two radiologists. Intra-class correlation coefficients (ICCs) were used to test the consistency of APTw, FF, and R 2 * values measured by the two observers. The Mann-Whitney U test was used to analyze the difference in each parameter between the two groups. Logistic regression analysis was used to assess the association between the degree of differentiation on histopathology and imaging parameters by APTw and mDixon Quant. The ROC curve was used to evaluate the diagnostic efficacy of various parameters and their combination in distinguishing the degree of CSC differentiation on histopathology. The DeLong test was used to access the differences among the area under the ROC curves (AUCs). The Pearson correlation coefficient was used to evaluate the correlation between APTw and mDixon-Quant imaging parameters.

Results

The APTw means were 2.95 ± 0.78% and 2.05 (1.85, 2.65)% in the poorly and well/moderately differentiated groups, respectively. The R 2 * values were 26.62 (21.99, 33.31)/s and 22.93 ± 6.09/s in the poorly and well/moderately differentiated groups, respectively (P < 0.05). The AUCs of APTw, R 2 * , and their combination were 0.762, 0.686, and 0.843, respectively. The Delong test suggested statistical significance between R 2 * and the combination of APTw and R 2 * . R 2 * values showed a significant correlation with APTw values in the poorly differentiated group.

Conclusions

APTw combined with mDixon-Quant can be used to efficiently distinguish the differention degrees of CSC diagnosed on histopathology.

Infrared spectrochemical findings on intermittent fasting-associated gross molecular modifications in rat myocardium

Cardiovascular diseases are among the primary life-threatening conditions affecting human society. Intermittent fasting is shown to be functional in the prevention of cardiovascular diseases, however, the information on fasting-associated modifications in myocardial biomolecules is limited. This study aimed to determine the impact of 18-h intermittent fasting administered for five weeks on 12 months-old rats using supervised linear discriminant analysis and support vector machine algorithms constructed on spectrochemical data obtained from myocardial tissues. These algorithms revealed gross biomolecular modifications, while quantitative analyses demonstrated higher amounts of saturated lipids (19%), triglycerides (11%), and lipids (56%), in addition to enhancement in membrane dynamics (18%). The concentrations of nucleic acids and glucose are increased by 52%, while the glycogen content is diminished by 61%. The protein carbonylation/oxidation is reduced by 38%, whereas a 35% increase in protein content was measured. Phosphorylated proteins have been calculated to be at higher concentrations in the 13-62% range. The study findings demonstrated significant molecular changes in the myocardium of rats subjected to intermittent fasting.

Survival Prediction Model for Patients with Esophageal Squamous Cell Carcinoma Based on the Parameter-Optimized Deep Belief Network Using the Improved Archimedes Optimization Algorithm

Esophageal squamous cell carcinoma (ESCC) is one of the highest incidence and mortality cancers in the world. An effective survival prediction model can improve the quality of patients' survival. Therefore, a parameter-optimized deep belief network based on the improved Archimedes optimization algorithm is proposed in this paper for the survival prediction of patients with ESCC. Firstly, a combination of features significantly associated with the survival of patients is found by the minimum redundancy and maximum relevancy (MRMR) algorithm. Secondly, a DBN network is introduced to make predictions for survival of patients. Aiming at the problem that the deep belief network model is affected by parameters in the construction process, this paper uses the Archimedes optimization algorithm to optimize the learning rate α and batch size β of DBN. In order to overcome the problem that AOA is prone to fall into local optimum and low search accuracy, an improved Archimedes optimization algorithm (IAOA) is proposed. On this basis, a survival prediction model for patients with ESCC is constructed. Finally, accuracy comparison tests are carried out on IAOA-DBN, AOA-DBN, SSA-DBN, PSO-DBN, BES-DBN, IAOA-SVM, and IAOA-BPNN models. The results show that the IAOA-DBN model can effectively predict the five-year survival rate of patients and provide a reference for the clinical judgment of patients with ESCC.

Detection and classification of cervical cancer images using CEENET deep learning approach

Earlier detection of cervical cancer in women can save their lives before a chronic development. The accurate detection in cancer tissues of cervix in the human body is very important. In this article, cervical images were classified into either affected or healthy images using deep learning architecture. The proposed approach was designed with the modules of Edge detector, complex wavelet transform, feature derivation and Convolutional Neural Networks (CNN) architecture with segmentation. The edge pixels in the source cervical image were detected using Kirsch’s edge detector, the Complex Wavelet Transform (CWT) was there used to decompose the edge detected cervical images into number of sub bands. Local Derivative Pattern (LDP) and statistical features were computed from the decomposed sub bands and feature map was constructed using the computed features. The featured map along with the source cervical image was fed into the Cervical Ensemble Network (CEENET) model for classifying of cervical images into the classes healthy or cancer (affected).

Rapid identification of papillary thyroid carcinoma and papillary microcarcinoma based on serum Raman spectroscopy combined with machine learning models

Thyroid carcinoma is one kind of cancer with the highest diagnosis rate in the endocrine system, and its main histological subtype is papillary thyroid carcinoma (PTC) accounting for 80% of thyroid malignancies. In recent years, the incidence of thyroid cancer has increased exponentially, and its substantial increase was closely related to the overdiagnosis of papillary microcarcinoma (PMC). Therefore, early and accurate identification of PTC and PMC can prevent patients from being irreversibly damaged. This study aimed to identify PTC and PMC using Raman spectroscopy. We collected serum Raman spectra from 16 patients with PTC and 31 patients with PMC. Firstly, the collected imbalance data were preprocessed using the synthetic minority over-sampling technique (SMOTE). Then, the equalized data were dimensionality reduced by principal component analysis (PCA). Finally, the processed data were fed into the single decision tree (DT) classifier, as well as the random forest (RF) built on the idea of Boosting ensemble and the Adaptive Boosting (Adaboost) model built on the idea of Bagging ensemble for classification. The classification accuracy of the three models in the testing set were 75.38%, 81.54%, and 84.61%, respectively. Compared with the DT classifier, the accuracy of the models introducing the idea of ensemble learning was enhanced by 6.16% and 9.23%, respectively. The best model was the Adaboost. This result demonstrates that serum Raman spectroscopy combined with an ensemble learning algorithm was feasible in rapidly identifying PTC and PMC. At the same time, the method has great potential for application in the field of clinical diagnosis.

Serum Raman spectroscopy combined with Deep Neural Network for analysis and rapid screening of hyperthyroidism and hypothyroidism

Hyperthyroidism and hypothyroidism may cause a series of clinical complications have a high incidence, and early diagnosis is beneficial to treatment. Based on Raman spectroscopy and deep learning algorithms, we propose a rapid screening method to distinguish serum samples of hyperthyroidism patients, hypothyroidism patients and control subjects. We collected 99 serum samples, including 38 cases from hyperthyroidism patients, 32 cases from hypothyroidism patients and 29 cases from control subjects. By comparing and analyzing the Raman spectra of the three, we found differences in the peak intensity of the spectra, indicating that Raman spectra can be used for the subsequent identification of diseases. After collecting the spectral data, Vancouver Raman algorithm (VRA) was used to remove the fluorescence background of the data, and kernel principal component analysis (KPCA) was used to extract the spectral data features with a cumulative explained variance ratio of 0.9999. Then, five neural network models, the adjusted AlexNet, LSTM-CNN, IndRNNCNN, the adjusted GoogLeNet and the adjusted ResNet, were constructed for classifications. The total accuracy was 91%, 84%, 82%, 75% and 71% respectively. The results of our study show that it is feasible to use Raman spectroscopy combined with deep learning to distinguish hyperthyroidism, hypothyroidism and control subjects. After comparing the models, we found that as the neural network deepens and the complexity of the model increases, the classification effect of Raman spectroscopy gradually deteriorates, and we put forward three conjectures for this.

Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images

Traditional screening of cervical cancer type classification majorly depends on the pathologist's experience, which also has less accuracy. Colposcopy is a critical component of cervical cancer prevention. In conjunction with precancer screening and treatment, colposcopy has played an essential role in lowering the incidence and mortality from cervical cancer over the last 50 years. However, due to the increase in workload, vision screening causes misdiagnosis and low diagnostic efficiency. Medical image processing using the convolutional neural network (CNN) model shows its superiority for the classification of cervical cancer type in the field of deep learning. This paper proposes two deep learning CNN architectures to detect cervical cancer using the colposcopy images; one is the VGG19 (TL) model, and the other is CYENET. In the CNN architecture, VGG19 is adopted as a transfer learning for the studies. A new model is developed and termed as the Colposcopy Ensemble Network (CYENET) to classify cervical cancers from colposcopy images automatically. The accuracy, specificity, and sensitivity are estimated for the developed model. The classification accuracy for VGG19 was 73.3%. Relatively satisfied results are obtained for VGG19 (TL). From the kappa score of the VGG19 model, we can interpret that it comes under the category of moderate classification. The experimental results show that the proposed CYENET exhibited high sensitivity, specificity, and kappa scores of 92.4%, 96.2%, and 88%, respectively. The classification accuracy of the CYENET model is improved as 92.3%, which is 19% higher than the VGG19 (TL) model.

Prediction of tumor size in patients with invasive ductal carcinoma using FT-IR spectroscopy combined with chemometrics: a preliminary study

Precise detection of tumor size is essential for early diagnosis, treatment, and evaluation of the prognosis of breast cancer. However, there are some errors between the tumor size of breast cancer measured by conventional imaging methods and the pathological tumor size. Invasive ductal carcinoma (IDC) is a common pathological type of breast cancer. In this study, serum Fourier transform infrared spectroscopy (FT-IR) combined with chemometric methods was used to predict the maximum diameter and maximum vertical diameter of tumors in IDC patients. Three models were evaluated based on the pathological tumor size measured after surgery and included grid search support vector machine regression (GS-SVR), back propagation neural network optimized by genetic algorithm (GA-BP-ANN), and back propagation neural network optimized by particle swarm optimization (PSO-BP-ANN). The results show that three models can accurately predict tumor size. The GA-BP-ANN model provided the best fitting quality of the largest tumor diameter with the determination coefficients of 0.984 in test set. And the GS-SVR model provided the best fitting quality of the largest vertical tumor diameter with the determination coefficients of 0.982 in test set. The GS-SVR model had the highest prediction efficiency and the lowest time complexity of the models. The results indicate that serum FT-IR spectroscopy combined with chemometric methods can predict tumor size in IDC patients. In addition, compared with traditional imaging methods, we found that the experimental results of the three models are better than traditional imaging methods in terms of correlation and fitting degree. And the average fitting error of PSO-BP-ANN and GA-BP-ANN models was less than 0.3 mm. The minimally invasive detection method is expected to be developed into a new clinical diagnostic method for tumor size estimation to reduce the diagnostic trauma of patients and provide new diagnostic experience for patients. Graphical Abstract.