Advancing cervical cancer diagnosis and screening with spectroscopy and machine learning

Non-invasive diagnostic test for lung cancer using biospectroscopy and variable selection techniques in saliva samples

Lung cancer is one of the most commonly occurring malignant tumours worldwide. Although some reference methods such as X-ray, computed tomography or bronchoscope are widely used for clinical diagnosis of lung cancer, there is still a need to develop new methods for early detection of lung cancer. Especially needed are approaches that might be non-invasive and fast with high analytical precision and statistically reliable. Herein, we developed a swab "dip" test in saliva whereby swabs were analysed using attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy harnessed to principal component analysis-quadratic discriminant analysis (QDA) and variable selection techniques employing successive projections algorithm (SPA) and genetic algorithm (GA) for feature selection/extraction combined with QDA. A total of 1944 saliva samples (56 designated as lung-cancer positive and 1888 designed as controls) were obtained in a lung cancer-screening programme being undertaken in North-West England. GA-QDA models achieved, for the test set, sensitivity and specificity values of 100.0% and 99.1%, respectively. Three wavenumbers (1422 cm-1, 1546 cm-1 and 1578 cm-1) were identified using the GA-QDA model to distinguish between lung cancer and controls, including ring C-C stretching, CN adenine, Amide II [δ(NH), ν(CN)] and νs(COO-) (polysaccharides, pectin). These findings highlight the potential of using biospectroscopy associated with multivariate classification algorithms to discriminate between benign saliva samples and those with underlying lung cancer.

Advances of machine learning-assisted small extracellular vesicles detection strategy

Detection of extracellular vesicles (EVs), particularly small EVs (sEVs), is of great significance in exploring their physiological characteristics and clinical applications. The heterogeneity of sEVs plays a crucial role in distinguishing different types of cells and diseases. Machine learning, with its exceptional data processing capabilities, offers a solution to overcome the limitations of conventional detection methods for accurately classifying sEV subtypes and sources. Principal component analysis, linear discriminant analysis, partial least squares discriminant analysis, XGBoost, support vector machine, k-nearest neighbor, and deep learning, along with some combined methods such as principal component-linear discriminant analysis, have been successfully applied in the detection and identification of sEVs. This review focuses on machine learning-assisted detection strategies for cell identification and disease prediction via sEVs, and summarizes the integration of these strategies with surface-enhanced Raman scattering, electrochemistry, inductively coupled plasma mass spectrometry and fluorescence. The performance of different machine learning-based detection strategies is compared, and the advantages and limitations of various machine learning models are also evaluated. Finally, we discuss the merits and limitations of the current approaches and briefly outline the perspective of potential research directions in the field of sEV analysis based on machine learning.

Wavelet scattering transform and entropy features in fluorescence spectral signal analysis for cervical cancer diagnosis

Cervical cancer is a prevalent malignant tumor within the female reproductive system and is regarded as a prominent cause of female mortality on a global scale. Timely and precise detection of various phases of cervical cancer holds the potential to substantially enhance both the rate of successful treatment and the duration of patient survival. Fluorescence spectroscopy is a highly sensitive method for detecting the biochemical changes that arise during cancer progression. In our study, fluorescence spectral data is collected from a diverse group of 110 subjects. The potential of the scattering transform technique for the purpose of cancer detection is explored. The processed signal undergoes an initial decomposition into scattering coefficients using the wavelet scattering transform (WST). Subsequently, the scattering coefficients are subjected to computation for fuzzy entropy, dispersion entropy, phase entropy, and spectral entropy, for effectively characterizing the fluorescence spectral signals. These combined features generated through the proposed approach are then fed to 1D convolutional neural network (CNN) classifier to classify them into normal, pre-cancerous, and cancerous categories, thereby evaluating the effectiveness of the proposed methodology. We obtained mean classification accuracy of 97% using 5-fold cross-validation. This demonstrates the potential of combining WST and entropic features for analyzing fluorescence spectroscopy signals using 1D CNN classifier that enables early cancer detection in contrast to prevailing diagnostic methods.

Cervical pre-cancer classification using entropic features and CNN: In vivo validation with a handheld fluorescence probe

Cervical cancer is one of the most prevalent forms of cancer, with a lengthy latent period and a gradual onset phase. Conventional techniques are found to be severely lacking in real time detection of disease progression which can greatly enhance the cure rate. Due to their high sensitivity and specificity, optical techniques are emerging as reliable tools, particularly in case of cancer. It has been seen that biochemical changes are better highlighted through intrinsic fluorescence devoid of interference from absorption and scattering. Its effectiveness in in-vivo conditions is affected by the fact that the intrinsic spectral signatures vary from patient to patient, as well as in different population groups. Here, we overcome this limitation by collectively enumerating the subtle changes in the spectral profiles and correlations through an information theory based entropic approach, which significantly amplifies the minute spectral variations. In conjunction with artificial intelligence (AI)/machine learning (ML) tools, it yields high specificity and sensitivity with a small dataset from patients in clinical conditions, without artificial augmentation. We have used an in-house developed handheld probe (i-HHP) for extracting intrinsic fluorescence spectra of human cervix from 110 different subjects drawn from diverse population groups. The average classification accuracy of the proposed methodology using 10-fold cross validation is 93.17%. A combination of polarised fluorescence spectra from i-HHP and the proposed classifier is proven to be minimally invasive with the ability to diagnose patients in real time. This paves the way for effective use of relatively smaller sized sensitive fluorescence data with advanced AI/ML tools for early cervical cancer detection in clinics.

Complete characterization of RNA biomarker fingerprints using a multi-modal ATR-FTIR and SERS approach for label-free early breast cancer diagnosis

Breast cancer is a prevalent form of cancer worldwide, and the current standard screening method, mammography, often requires invasive biopsy procedures for further assessment. Recent research has explored microRNAs (miRNAs) in circulating blood as potential biomarkers for early breast cancer diagnosis. In this study, we employed a multi-modal spectroscopy approach, combining attenuated total reflection Fourier transform infrared (ATR-FTIR) and surface-enhanced Raman scattering (SERS) to comprehensively characterize the full-spectrum fingerprints of RNA biomarkers in the blood serum of breast cancer patients. The sensitivity of conventional FTIR and Raman spectroscopy was enhanced by ATR-FTIR and SERS through the utilization of a diamond ATR crystal and silver-coated silicon nanopillars, respectively. Moreover, a wider measurement wavelength range was achieved with the multi-modal approach than with a single spectroscopic method alone. We have shown the results on 91 clinical samples, which comprised 44 malignant and 47 benign cases. Principal component analysis (PCA) was performed on the ATR-FTIR, SERS, and multi-modal data. From the peak analysis, we gained insights into biomolecular absorption and scattering-related features, which aid in the differentiation of malignant and benign samples. Applying 32 machine learning algorithms to the PCA results, we identified key molecular fingerprints and demonstrated that the multi-modal approach outperforms individual techniques, achieving higher average validation accuracy (95.1%), blind test accuracy (91.6%), specificity (94.7%), sensitivity (95.5%), and F-score (94.8%). The support vector machine (SVM) model showed the best area under the curve (AUC) characterization value of 0.9979, indicating excellent performance. These findings highlight the potential of the multi-modal spectroscopy approach as an accurate, reliable, and rapid method for distinguishing between malignant and benign breast tumors in women. Such a label-free approach holds promise for improving early breast cancer diagnosis and patient outcomes.