Detection of breast cancer by ATR-FTIR spectroscopy using artificial neural networks

Metastasis diagnosis using attenuated total reflection-Fourier transform infra-red (ATR-FTIR) spectroscopy

The suitability of Fourier transform infrared spectroscopy as a metastasis prognostic tool has not been reported for some cancer types. Our main aim was to show spectroscopic differences between live un-preprocessed cancer cells of different metastatic levels. Spectra of four cancer cell pairs, including colon cancer (SW480, SW620); human melanoma (WM115, WM266.4); murine melanoma (B16F01, B16F10); and breast cancer (MCF7, MDA-MB-231); each pair having the same genetic background, but different metastatic level were analyzed in the regions 1400-1700 cm-1 and 3100-3500 cm-1 using Principal Component Analysis, curve fitting, multifractal dimension and receiver operating characteristic (ROC) curves. The results show spectral markers I1540/I1473, I1652/I1473, [Formula: see text], and multifractal dimension of the spectral images are significantly different for the cells based on their metastatic levels. ROC curve analysis showed good diagnostic performance of the spectral markers in separating cells based on metastatic degree, with areas under the ROC curves having 95% confidence interval lower limits greater than 0.5 for most instances. These spectral features can be important in predicting the probability of metastasis in primary tumors, providing useful guidance for treatment planning. Our markers are effective in differentiating metastatic levels without sample fixation or drying and therefore could be compactible for future use in in-vivo procedures involving spectroscopic cancer diagnosis.

Surface-enhanced Raman spectroscopy of the filtrate portions of the blood serum samples of breast cancer patients obtained by using 30 kDa filtration device

Raman spectroscopy is reliable tool for analyzing and exploring early disease diagnosis related to body fluids, such as blood serum, which contain low molecular weight fraction (LMWF) and high molecular weight fraction (HMWF) proteins. The disease biomarkers consist of LMWF which are dominated by HMWF hence their analysis is difficult. In this study, in order to overcome this issue, centrifugal filter devices of 30 kDa were used to obtain filtrate and residue portions obtained from whole blood serum samples of control and breast cancer diagnosed patients. The filtrate portions obtained in this way are expected to contain the marker proteins of breast cancer of the size below this filter size. These may include prolactin, Microphage migration inhabitation factor (MIF), γ-Synuclein, BCSG1, Leptin, MUC1, RS/DJ-1 present in the centrifuged blood serum (filtrate portions) which are then analyzed by the SERS technique to recognize the SERS spectral characteristics associated with the progression of breast cancer in the samples of different stages as compared to the healthy ones. The key intention of this study is to achieve early-stage breast cancer diagnosis through the utilization of Surface Enhanced Raman Spectroscopy (SERS) after the centrifugation of healthy and breast cancer serum samples with Amicon ultra-filter devices of 30 kDa. The silver nanoparticles with high plasmon resonance are used as a substrate for SERS analysis. Principal Component Analysis (PCA) and Partial Least Discriminant Analysis (PLS-DA) models are utilized as spectral classification tools to assess and predict rapid, reliable, and non-destructive SERS-based analysis. Notably, they were particularly effective in distinguishing between different SERS spectral groups of the cancerous and non-cancerous samples. By comparing all these spectral data sets to each other PLSDA shows the 79 % accuracy, 76 % specificity, and 81 % sensitivity in samples with AUC value of AUC = 0.774 SERS has proven to be a valuable technique for the rapid identification of the SERS spectral features of blood serum and its filtrate fractions from both healthy individuals and those with breast cancer, aiding in disease diagnosis.

Optimization and characterization of hybrid bio-briquettes produced from the mixture of sawdust, sugarcane bagasse, and paddy straw

Biomass briquetting is a viable densification technique that converts waste biomass materials into useful products and alternative energy. This work explores the characteristics and optimization of hybrid bio-briquette production by combining crop residues (paddy straw) and solid biomass materials (sawdust and sugarcane bagasse). A total number of 20 briquettes were fabricated with three input factors: sawdust (SD), sugarcane bagasse (SB), and paddy straw (PS) based on the faced-centered central composite design (FCCCD) approach in the laboratory to investigate the calorific value (CV) and ash content (AC). The bomb calorimeter technique was used to evaluate the briquette's calorific value and ash content. The proposed work focused on optimizing the briquette input parameters (SD, SB, and PS) and output responses (CV and AC) using analysis of variance (ANOVA) and response surface methodology (RSM) and hybrid artificial neural network-integrated with multi-objective genetic algorithms (ANN-MOGA). This study shows that the MOGA-ANN-based model results in the best value of CV (17.07 MJ/kg) and AC (1.95%) with optimal input parameters SD (39.99 g), SB (29.02 g), and PS (69.02 g). The optimal results observed from the MOGA-ANN model have also been validated experimentally. The Fourier transform infrared (FTIR) spectroscopy investigation reveals that biomass briquettes are the sustainable and environment-friendly option of fossil fuels for power generation and indoor cooking. The study suggests a strategy for minimizing agro-waste, which may be converted into future fuel in the form of briquettes.

Fiber optic probe-based ATR-FTIR spectroscopy for rapid breast cancer detection: A pilot study

Breast cancer diagnosis is crucial for timely treatment and improved outcomes. This paper proposes a novel approach for rapid breast cancer diagnosis using optical fiber probe-based attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy from 750 to 4000 cm-1 . The technique enables direct analysis of tissue samples, eliminating the need for microtome sectioning and staining, thus saving time and resources. By capturing molecular fingerprint information, various machine-learning models were used to analyze the spectroscopic data to classify cancerous and non-cancerous tissues accurately. Comparing deparaffinized and paraffinized samples reveals the impact of sample preparation and experimental methods. The study demonstrates a strong correlation between the cancerous nature of a sample and its ATR-FTIR spectrum, suggesting its potential for breast cancer diagnosis (sensitivity of 74.2% and specificity of 78.3%). The proposed approach holds promise for integration into clinical operations, providing a rapid method for preliminary breast cancer diagnosis.

A Review of Machine Learning Methods Recently Applied to FTIR Spectroscopy Data for the Analysis of Human Blood Cells

Machine learning (ML) is a broad term encompassing several methods that allow us to learn from data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision-making. This paper presents a review of articles that discuss the use of Fourier transform infrared (FTIR) spectroscopy and ML for human blood analysis between the years 2019-2023. The literature review was conducted to identify published research of employed ML linked with FTIR for distinction between pathological and healthy human blood cells. The articles' search strategy was implemented and studies meeting the eligibility criteria were evaluated. Relevant data related to the study design, statistical methods, and strengths and limitations were identified. A total of 39 publications in the last 5 years (2019-2023) were identified and evaluated for this review. Diverse methods, statistical packages, and approaches were used across the identified studies. The most common methods included support vector machine (SVM) and principal component analysis (PCA) approaches. Most studies applied internal validation and employed more than one algorithm, while only four studies applied one ML algorithm to the data. A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of ML methods. There is a need to ensure that multiple ML approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that the discrimination of human blood cells is being made with the highest efficient evidence.

Molecular Fingerprint Detection Using Raman and Infrared Spectroscopy Technologies for Cancer Detection: A Progress Review

Molecular vibrations play a crucial role in physical chemistry and biochemistry, and Raman and infrared spectroscopy are the two most used techniques for vibrational spectroscopy. These techniques provide unique fingerprints of the molecules in a sample, which can be used to identify the chemical bonds, functional groups, and structures of the molecules. In this review article, recent research and development activities for molecular fingerprint detection using Raman and infrared spectroscopy are discussed, with a focus on identifying specific biomolecules and studying the chemical composition of biological samples for cancer diagnosis applications. The working principle and instrumentation of each technique are also discussed for a better understanding of the analytical versatility of vibrational spectroscopy. Raman spectroscopy is an invaluable tool for studying molecules and their interactions, and its use is likely to continue to grow in the future. Research has demonstrated that Raman spectroscopy is capable of accurately diagnosing various types of cancer, making it a valuable alternative to traditional diagnostic methods such as endoscopy. Infrared spectroscopy can provide complementary information to Raman spectroscopy and detect a wide range of biomolecules at low concentrations, even in complex biological samples. The article concludes with a comparison of the techniques and insights into future directions.

Fourier-transform infrared spectroscopy: a universal optical sensing technique with auspicious application prospects in the diagnosis and management of autoimmune diseases

Autoimmune diseases (AIDs) are poorly understood clinical syndromes due to breakdown of immune tolerance towards specific types of self-antigens. They are generally associated with an inflammatory response mediated by lymphocytes T, autoantibodies or both. Ultimately, chronic inflammation culminates in tissue damages and clinical manifestations. AIDs affect 5% of the world population, and they represent the main cause of fatality in young to middle-aged females. In addition, the chronic nature of AIDs has a devastating impact on the patient's quality of life. It also places a heavy burden on the health care system. Establishing a rapid and accurate diagnosis is considered vital for an ideal medical management of these autoimmune disorders. However, for some AIDs, this task might be challenging. Vibrational spectroscopies, and more particularly Fourier-transform infrared (FTIR) spectroscopy, have emerged as universal analytical techniques with promising applications in the diagnosis of various types of malignancies and metabolic and infectious diseases. The high sensitivity of these optical sensing techniques and their minimal requirements for test reagents qualify them to be ideal analytical techniques. The aim of the current review is to explore the potential applications of FTIR spectroscopy in the diagnosis and management of most common AIDs. It also aims to demonstrate how this technique has contributed to deciphering the biochemical and physiopathological aspects of these chronic inflammatory diseases. The advantages that can be offered by this optical sensing technique over the traditional and gold standard methods used in the diagnosis of these autoimmune disorders have also been extensively discussed.

Label-Free Physical-Analytical Techniques Reveal Epigenetic Modifications of Breast Cancer Chromosomes

Epigenetic dysregulation including DNA methylation and histone modifications is being increasingly recognized as a promising biomarker for the diagnosis and prognosis of cancer. Herein, we devised a label-free analytical toolbox comprising IR, UV-vis, CD spectroscopy, and cyclic voltammetry, which is capable to differentiate significantly hyper-methylated breast cancer chromosomes from the normal breast epithelial counterparts.

Impaired Extracellular Proteostasis in Patients with Heart Failure

BACKGROUND

Proteostasis impairment and the consequent increase of amyloid burden in the myocardium have been associated with heart failure (HF) development and poor prognosis. A better knowledge of the protein aggregation process in biofluids could assist the development and monitoring of tailored interventions.

AIM

To compare the proteostasis status and protein's secondary structures in plasma samples of patients with HF with preserved ejection fraction (HFpEF), patients with HF with reduced ejection fraction (HFrEF), and age-matched individuals.

METHODS

A total of 42 participants were enrolled in 3 groups: 14 patients with HFpEF, 14 patients with HFrEF, and 14 age-matched individuals. Proteostasis-related markers were analyzed by immunoblotting techniques. Fourier Transform Infrared (FTIR) Spectroscopy in Attenuated Total Reflectance (ATR) was applied to assess changes in the protein's conformational profile.

RESULTS

Patients with HFrEF showed an elevated concentration of oligomeric proteic species and reduced clusterin levels. ATR-FTIR spectroscopy coupled with multivariate analysis allowed the discrimination of HF patients from age-matched individuals in the protein amide I absorption region (1700-1600 cm^-1), reflecting changes in protein conformation, with a sensitivity of 73 and a specificity of 81%. Further analysis of FTIR spectra showed significantly reduced random coils levels in both HF phenotypes. Also, compared to the age-matched group, the levels of structures related to fibril formation were significantly increased in patients with HFrEF, whereas the β-turns were significantly increased in patients with HFpEF.

CONCLUSION

Both HF phenotypes showed a compromised extracellular proteostasis and different protein conformational changes, suggesting a less efficient protein quality control system.

Dual Classification Approach for the Rapid Discrimination of Metabolic Syndrome by FTIR

Metabolic syndrome is a complex of interrelated risk factors for cardiovascular disease and diabetes. Thus, new point-of-care diagnostic tools are essential for unambiguously distinguishing MetS patients, providing results in rapid time. Herein, we evaluated the potential of Fourier transform infrared spectroscopy combined with chemometric tools to detect spectra markers indicative of metabolic syndrome. Around 105 plasma samples were collected and divided into two groups according to the presence of at least three of the five clinical parameters used for MetS diagnosis. A dual classification approach was studied based on selecting the most important spectral variable and classification methods, linear discriminant analysis (LDA) and SIMCA class modelling, respectively. The same classification methods were applied to measured clinical parameters at our disposal. Thus, the classification's performance on reduced spectra fingerprints and measured clinical parameters were compared. Both approaches achieved excellent discrimination results among groups, providing almost 100% accuracy. Nevertheless, SIMCA class modelling showed higher classification performance between MetS and no MetS for IR-reduced variables compared to clinical variables. We finally discuss the potential of this method to be used as a supportive diagnostic or screening tool in clinical routines.

The Convergence of FTIR and EVs: Emergence Strategy for Non-Invasive Cancer Markers Discovery

In conjunction with imaging analysis, pathology-based assessments of biopsied tissue are the gold standard for diagnosing solid tumors. However, the disadvantages of tissue biopsies, such as being invasive, time-consuming, and labor-intensive, have urged the development of an alternate method, liquid biopsy, that involves sampling and clinical assessment of various bodily fluids for cancer diagnosis. Meanwhile, extracellular vesicles (EVs) are circulating biomarkers that carry molecular profiles of their cell or tissue origins and have emerged as one of the most promising biomarkers for cancer. Owing to the biological information that can be obtained through EVs' membrane surface markers and their cargo loaded with biomolecules such as nucleic acids, proteins, and lipids, EVs have become useful in cancer diagnosis and therapeutic applications. Fourier-transform infrared spectroscopy (FTIR) allows rapid, non-destructive, label-free molecular profiling of EVs with minimal sample preparation. Since the heterogeneity of EV subpopulations may result in complicated FTIR spectra that are highly diverse, computational-assisted FTIR spectroscopy is employed in many studies to provide fingerprint spectra of malignant and non-malignant samples, allowing classification with high accuracy, specificity, and sensitivity. In view of this, FTIR-EV approach carries a great potential in cancer detection. The progression of FTIR-based biomarker identification in EV research, the rationale of the integration of a computationally assisted approach, along with the challenges of clinical translation are the focus of this review.

Rapid and sensitive detection of esophageal cancer by FTIR spectroscopy of serum and plasma

Fourier transform infrared (FTIR) spectroscopy, as a platform technology for cancer detection, must be up to the challenge of clinical transformation. To this end, detection of esophageal squamous cell carcinoma (ESCC) was hereby explored using serum and plasma scrape-coated on barium fluoride (BaF₂) disk by transmission FTIR method, and the classification model was built using six multivariate statistical analyses, including support vector machine (SVM), principal component linear discriminant analysis (PC-LDA), decision tree (DT), k-nearest neighbor (KNN) classification, ensemble algorithms (EA) and partial least squares for discriminant analysis (PLS-DA). All statistical analyses methods demonstrated that late-stage cancer could be well classified from healthy people employing either serum or plasma with different anticoagulants. Resulting PC-LDA model differentiated late-stage cancer from normal group with an accuracy of 99.26%, a sensitivity of 98.53%, and a specificity of 100%. The accuracy and sensitivity reached 97.08% and 91.43%, respectively for early-stage cancer discrimination from normal group. This pilot exploration demonstrated that transmission FTIR provided a rapid, cost effective and sensitive method for ESCC diagnosis using either serum or plasma.

Predicting the Likelihood of Colorectal Cancer with Artificial Intelligence Tools Using Fourier Transform Infrared Signals Obtained from Tumor Samples

The early and accurate detection of colorectal cancer (CRC) significantly affects its prognosis and clinical management. However, current standard diagnostic procedures for CRC often lack sensitivity and specificity since most rely on visual examination. Hence, there is a need to develop more accurate methods for its diagnosis. Support vector machine (SVM) and feedforward neural network (FNN) models were designed using the Fourier transform infrared (FT-IR) spectral data of several colorectal tissues that were unanimously identified as either benign or malignant by different unrelated pathologists. The set of samples in which the pathologists had discordant readings were then analyzed using the AI models described above. Between the SVM and NN models, the NN model was able to outperform the SVM model based on their prediction confidence scores. Using the spectral data of the concordant samples as training set, the FNN was able to predict the histologically diagnosed malignant tissues (n = 118) at 59.9-99.9% confidence (average = 93.5%). Of the 118 samples, 84 (71.18%) were classified with an above average confidence score, 34 (28.81%) classified below the average confidence score, and none was misclassified. Moreover, it was able to correctly identify the histologically confirmed benign samples (n = 83) at 51.5-99.7% confidence (average = 91.64%). Of the 83 samples, 60 (72.29%) were classified with an above average confidence score, 22 (26.51%) classified below the average confidence score, and only 1 sample (1.20%) was misclassified. The study provides additional proof of the ability of attenuated total reflection (ATR) FT-IR enhanced by AI tools to predict the likelihood of CRC without dependence on morphological changes in tissues.

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Background

The impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.

Methods

PubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.

Results

ML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.

Conclusion

Overall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.