Clinical translational application of Raman spectroscopy to advance Benchside biochemical characterization to bedside diagnosis of esophageal diseases

Label-Free Surface-Enhanced Raman Spectroscopy with Machine Learning for the Diagnosis of Thyroid Cancer by Using Fine-Needle Aspiration Liquid Samples

The incidence of thyroid cancer is increasing worldwide. Fine-needle aspiration (FNA) cytology is widely applied with the use of extracted biological cell samples, but current FNA cytology is labor-intensive, time-consuming, and can lead to the risk of false-negative results. Surface-enhanced Raman spectroscopy (SERS) combined with machine learning algorithms holds promise for cancer diagnosis. In this study, we develop a label-free SERS liquid biopsy method with machine learning for the rapid and accurate diagnosis of thyroid cancer by using thyroid FNA washout fluids. These liquid supernatants are mixed with silver nanoparticle colloids, and dispersed in quartz capillary for SERS measurements to discriminate between healthy and malignant samples. We collect Raman spectra of 36 thyroid FNA samples (18 malignant and 18 benign) and compare four classification models: Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA), Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN). The results show that the CNN algorithm is the most precise, with a high accuracy of 88.1%, sensitivity of 87.8%, and the area under the receiver operating characteristic curve of 0.953. Our approach is simple, convenient, and cost-effective. This study indicates that label-free SERS liquid biopsy assisted by deep learning models holds great promise for the early detection and screening of thyroid cancer.

System transferability of Raman-based oesophageal tissue classification using modern machine learning to support multi-centre clinical diagnostics

BACKGROUND

The clinical potential of Raman spectroscopy is well established but has yet to become established in routine oncology workflows. One barrier slowing clinical adoption is a lack of evidence demonstrating that data taken on one spectrometer transfers across to data taken on another spectrometer to provide consistent diagnoses.

METHODS

We investigated multi-centre transferability using human oesophageal tissue. Raman spectra were taken across three different centres with different spectrometers of the same make and model. By using a common protocol, we aimed to minimise the difference in machine learning performance between centres.

RESULTS

61 oesophageal samples from 51 patients were interrogated by Raman spectroscopy at each centre and classified into one of five pathologies. The overall accuracy and log-loss did not significantly vary when a model trained upon data from any one centre was applied to data taken at the other centres. Computational methods to correct for the data during pre-processing were not needed.

CONCLUSION

We have found that when using the same make and model of spectrometer, together with a common protocol, across different centres it is possible to achieve system transferability without the need for additional computational instrument correction.

On-chip Raman spectroscopy of live single cells for the staging of oesophageal adenocarcinoma progression

The absence of early diagnosis contributes to oesophageal cancer being the sixth most common cause of global cancer-associated deaths, with a 5-year survival rate of < 20%. Barrett's oesophagus is the main pre-cancerous condition to adenocarcinoma development, characterised by the morphological transition of oesophageal squamous epithelium to metaplastic columnar epithelium. Early tracking and treatment of oesophageal adenocarcinoma could dramatically improve with diagnosis and monitoring of patients with Barrett's Oesophagus. Current diagnostic methods involve invasive techniques such as endoscopies and, with only a few identified biomarkers of disease progression, the detection of oesophageal adenocarcinoma is costly and challenging. In this work, single-cell Raman spectroscopy was combined with microfluidic techniques to characterise the development of oesophageal adenocarcinoma through the progression of healthy epithelial, Barrett's oesophagus and oesophageal adenocarcinoma cell lines. Principal component analysis and linear discriminant analysis were used to classify the different stages of cancer progression. with the ability to differentiate between healthy and cancerous cells with an accuracy of 97%. Whilst the approach could also separate the dysplastic stages from healthy or cancer with high accuracy-the intra-class separation was approximately 68%. Overall, these results highlight the potential for rapid and reliable diagnostic/prognostic screening of Barrett's Oesophagus patients.

Hyperspectral Raman Imaging for Automated Recognition of Human Renal Amyloid

In the clinical setting, routine identification of the main types of tissue amyloid deposits, light-chain amyloid (AL) and serum amyloid A (AA), is based on histochemical staining; rarer types of amyloid require mass spectrometry analysis. Raman spectroscopic imaging is an analytical tool, which can be used to chemically map, and thus characterize, the molecular composition of fluid and solid tissue. In this proof-of-concept study, we tested the feasibility of applying Raman spectroscopy combined with artificial intelligence to detect and characterize amyloid deposits in unstained frozen tissue sections from kidney biopsies with pathologic diagnosis of AL and AA amyloidosis and control biopsies with no amyloidosis (NA). Raman hyperspectral images, mapped in a 2D grid-like fashion over the tissue sections, were obtained. Three machine learning-assisted analysis models of the hyperspectral images could accurately distinguish AL (types λ and κ), AA, and NA 93-100% of the time. Although very preliminary, these findings illustrate the potential of Raman spectroscopy as a technique to identify, and possibly, subtype renal amyloidosis.

Design and Synthesis of SERS Materials for In Vivo Molecular Imaging and Biosensing

Surface-enhanced Raman scattering (SERS) is a feasible and ultra-sensitive method for biomedical imaging and disease diagnosis. SERS is widely applied to in vivo imaging due to the development of functional nanoparticles encoded by Raman active molecules (SERS nanoprobes) and improvements in instruments. Herein, the recent developments in SERS active materials and their in vivo imaging and biosensing applications are overviewed. Various SERS substrates that have been successfully used for in vivo imaging are described. Then, the applications of SERS imaging in cancer detection and in vivo intraoperative guidance are summarized. The role of highly sensitive SERS biosensors in guiding the detection and prevention of diseases is discussed in detail. Moreover, its role in the identification and resection of microtumors and as a diagnostic and therapeutic platform is also reviewed. Finally, the progress and challenges associated with SERS active materials, equipment, and clinical translation are described. The present evidence suggests that SERS could be applied in clinical practice in the future.

Novel Insights Into Tissue-Specific Biochemical Alterations in Pediatric Eosinophilic Esophagitis Using Raman Spectroscopy

INTRODUCTION:

Elucidating esophageal biochemical composition in eosinophilic esophagitis (EoE) can offer novel insights into its pathogenesis, which remains unclear. Using Raman spectroscopy, we profiled and compared the biochemical composition of esophageal samples obtained from children with active (aEoE) and inactive EoE (iEoE) with non-EoE controls, examined the relationship between spectral markers and validated EoE activity indices.

METHODS:

In vitro Raman spectra from children with aEoE (n = 8; spectra = 51) and iEoE (n = 6; spectra = 48) and from non-EoE controls (n = 10; spectra = 75) were acquired. Mann-Whitney test was used to assess the differences in their Raman intensities (median [interquartile range]) and identify spectral markers. Spearman correlation was used to evaluate the relationship between spectral markers and endoscopic and histologic activity indices.

RESULTS:

Raman peaks attributable to glycogen content (936/1,449 cm⁻¹) was lower in children with aEoE (0.20 [0.18–0.21]) compared with that in non-EoE controls (0.24 [0.23–0.29]). Raman intensity of proteins (1,660/1,209 cm⁻¹) was higher in children with aEoE compared with that in non-EoE controls (3.20 [3.07–3.50] vs 2.91 [2.59–3.05]; P = 0.01), whereas that of lipids (1,301/1,260 cm⁻¹) was higher in children with iEoE (1.56 [1.49–1.63]) compared with children with aEoE (1.40 [1.30–1.48]; P = 0.02). Raman peaks attributable to glycogen and lipid inversely correlated with eosinophilic inflammation and basal zone hyperplasia. Raman mapping substantiated our findings.

DISCUSSION:

This is the first study to identify spectral traits of the esophageal samples related to EoE activity and tissue pathology and to profile tissue-level biochemical composition associated with pediatric EoE. Future research to determine the role of these biochemical alterations in development and clinical course of EoE can advance our understanding of EoE pathobiology.

The Potential of Raman Spectroscopy in the Diagnosis of Dysplastic and Malignant Oral Lesions

Simple Summary

Raman spectroscopy, a light scattering technique that provides the biochemical fingerprint of a sample, was used on samples taken from patients with cancer and precancerous lesions. This information was then used to build a classifier to identify cancer and the precancerous phases. The ability to distinguish cancerous tissue from normal and precancerous tissue is diagnostically crucial as it can alter the patients’ prognosis and management. Moreover, as cellular changes are often present at the tumour margin, the ability to distinguish these changes from cancer can help in preserving more of the tissue and maintaining aesthetics and functionality for the patient.

Abstract

Early diagnosis, treatment and/or surveillance of oral premalignant lesions are important in preventing progression to oral squamous cell carcinoma (OSCC). The current gold standard is through histopathological diagnosis, which is limited by inter- and intra-observer errors and sampling errors. The objective of this work was to use Raman spectroscopy to discriminate between benign, mild, moderate and severe dysplasia and OSCC in formalin fixed paraffin preserved (FFPP) tissues. The study included 72 different pathologies from which 17 were benign lesions, 20 mildly dysplastic, 20 moderately dysplastic, 10 severely dysplastic and 5 invasive OSCC. The glass substrate and paraffin wax background were digitally removed and PLSDA with LOPO cross-validation was used to differentiate the pathologies. OSCC could be differentiated from the other pathologies with an accuracy of 70%, while the accuracy of the classifier for benign, moderate and severe dysplasia was ~60%. The accuracy of the classifier was lowest for mild dysplasia (~46%). The main discriminating features were increased nucleic acid contributions and decreased protein and lipid contributions in the epithelium and decreased collagen contributions in the connective tissue. Smoking and the presence of inflammation were found to significantly influence the Raman classification with respective accuracies of 76% and 94%.