Data consistency and classification model transferability across biomedical Raman spectroscopy systems

The role of persistent high-risk human papillomavirus (HPV) infection in the development of cervical precancer and cancer is now well accepted, and HPV testing has recently been introduced for primary cervical screening. However, the low specificity of HPV DNA testing can result in large numbers of women with an HPV-positive result, and additional triage approaches are needed to avoid over-referral to colposcopy and overtreatment. The aim of this study was to assess Raman spectroscopy as a potential triage test to discriminate between transient and persistent HPV infection. HPV DNA status and mRNA status were confirmed in ThinPrep® cervical samples (n = 60) using the Cobas 4800 and APTIMA HPV test, respectively. Raman spectra were recorded from single-cell nuclei and subjected to partial least squares discriminant analysis (PLSDA). In addition, the PLSDA classification model was validated using a blinded independent test set (n = 14). Sensitivity of 85% and specificity of 92% were achieved for the classification of transient and persistent HPV infection, and this increased to 90% sensitivity and 100% specificity when mean sample spectra were used instead of individual cellular spectra. This study showed that Raman spectroscopy has potential as a triage test for HPV-positive women to identify persistent HPV infection.

Download Full-text

Multi-centre Raman spectral mapping of oesophageal cancer tissues: a study to assess system transferability

Faraday Discussions ◽

10.1039/c5fd00183h ◽

2016 ◽

Vol 187 ◽

pp. 87-103 ◽

Cited By ~ 9

Author(s):

M. Isabelle ◽

J. Dorney ◽

A. Lewis ◽

G. R. Lloyd ◽

O. Old ◽

...

Keyword(s):

Raman Spectroscopy ◽

Clinical Information ◽

Diagnostic Methods ◽

Classification Model ◽

Training Dataset ◽

Clinical Implementation ◽

Tissue Samples ◽

Wide Range ◽

Offset Correction ◽

Spectrometer System

The potential for Raman spectroscopy to provide early and improved diagnosis on a wide range of tissue and biopsy samples in situ is well documented. The standard histopathology diagnostic methods of reviewing H&E and/or immunohistochemical (IHC) stained tissue sections provides valuable clinical information, but requires both logistics (review, analysis and interpretation by an expert) and costly processing and reagents. Vibrational spectroscopy offers a complimentary diagnostic tool providing specific and multiplexed information relating to molecular structure and composition, but is not yet used to a significant extent in a clinical setting. One of the challenges for clinical implementation is that each Raman spectrometer system will have different characteristics and therefore spectra are not readily compatible between systems. This is essential for clinical implementation where classification models are used to compare measured biochemical or tissue spectra against a library training dataset. In this study, we demonstrate the development and validation of a classification model to discriminate between adenocarcinoma (AC) and non-cancerous intraepithelial metaplasia (IM) oesophageal tissue samples, measured on three different Raman instruments across three different locations. Spectra were corrected using system transfer spectral correction algorithms including wavenumber shift (offset) correction, instrument response correction and baseline removal. The results from this study indicate that the combined correction methods do minimize the instrument and sample quality variations within and between the instrument sites. However, more tissue samples of varying pathology states and greater tissue area coverage (per sample) are needed to properly assess the ability of Raman spectroscopy and system transferability algorithms over multiple instrument sites.

Download Full-text

Raman spectroscopy as a non-invasive diagnostic technique for endometriosis

Scientific Reports ◽

10.1038/s41598-019-56308-y ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 4

Author(s):

Ugur Parlatan ◽

Medine Tuna Inanc ◽

Bahar Yuksel Ozgor ◽

Engin Oral ◽

Ercan Bastu ◽

...

Keyword(s):

Raman Spectroscopy ◽

Diagnostic Technique ◽

Principal Component ◽

Classification Model ◽

Support Vector ◽

Serum Samples ◽

K Nearest Neighbors ◽

Non Invasive ◽

Unseen Data ◽

Invasive Method

AbstractEndometriosis is a condition in which the endometrium, the layer of tissue that usually covers the inside of the uterus, grows outside the uterus. One of its severe effects is sub-fertility. The exact reason for endometriosis is still unknown and under investigation. Tracking the symptoms is not sufficient for diagnosing the disease. A successful diagnosis can only be made using laparoscopy. During the disease, the amount of some molecules (i.e., proteins, antigens) changes in the blood. Raman spectroscopy provides information about biochemicals without using dyes or external labels. In this study, Raman spectroscopy is used as a non-invasive diagnostic method for endometriosis. The Raman spectra of 94 serum samples acquired from 49 patients and 45 healthy individuals were compared for this study. Principal Component Analysis (PCA), k- Nearest Neighbors (kNN), and Support Vector Machines (SVM) were used in the analysis. According to the results (using 80 measurements for training and 14 measurements for the test set), it was found that kNN-weighted gave the best classification model with sensitivity and specificity values of 80.5% and 89.7%, respectively. Testing the model with unseen data yielded a sensitivity value of 100% and a specificity value of 100%. To the best of our knowledge, this is the first study in which Raman spectroscopy was used in combination with PCA and classification algorithms as a non-invasive method applied on blood sera for the diagnosis of endometriosis.

Download Full-text

Rapid intraoperative molecular genetic classification of gliomas using Raman spectroscopy

Neuro-Oncology Advances ◽

10.1093/noajnl/vdz008 ◽

2019 ◽

Vol 1 (1) ◽

Cited By ~ 1

Author(s):

Laurent James Livermore ◽

Martin Isabelle ◽

Ian Mac Bell ◽

Connor Scott ◽

John Walsby-Tickle ◽

...

Keyword(s):

Raman Spectroscopy ◽

Molecular Genetic ◽

Classification Model ◽

Wild Type ◽

Genetic Classification ◽

Fresh Tissue ◽

Tissue Samples ◽

Genetic Subtypes ◽

Classification Of Gliomas

Abstract Background The molecular genetic classification of gliomas, particularly the identification of isocitrate dehydrogenase (IDH) mutations, is critical for clinical and surgical decision-making. Raman spectroscopy probes the unique molecular vibrations of a sample to accurately characterize its molecular composition. No sample processing is required allowing for rapid analysis of tissue. The aim of this study was to evaluate the ability of Raman spectroscopy to rapidly identify the common molecular genetic subtypes of diffuse glioma in the neurosurgical setting using fresh biopsy tissue. In addition, classification models were built using cryosections, formalin-fixed paraffin-embedded (FFPE) sections and LN-18 (IDH-mutated and wild-type parental cell) glioma cell lines. Methods Fresh tissue, straight from neurosurgical theatres, underwent Raman analysis and classification into astrocytoma, IDH-wild-type; astrocytoma, IDH-mutant; or oligodendroglioma. The genetic subtype was confirmed on a parallel section using immunohistochemistry and targeted genetic sequencing. Results Fresh tissue samples from 62 patients were collected (36 astrocytoma, IDH-wild-type; 21 astrocytoma, IDH-mutated; 5 oligodendroglioma). A principal component analysis fed linear discriminant analysis classification model demonstrated 79%–94% sensitivity and 90%–100% specificity for predicting the 3 glioma genetic subtypes. For the prediction of IDH mutation alone, the model gave 91% sensitivity and 95% specificity. Seventy-nine cryosections, 120 FFPE samples, and LN18 cells were also successfully classified. Meantime for Raman data collection was 9.5 min in the fresh tissue samples, with the process from intraoperative biopsy to genetic classification taking under 15 min. Conclusion These data demonstrate that Raman spectroscopy can be used for the rapid, intraoperative, classification of gliomas into common genetic subtypes.

Download Full-text

Characterization of the COPD Salivary Fingerprint through Surface Enhanced Raman Spectroscopy: A Pilot Study

Diagnostics ◽

10.3390/diagnostics11030508 ◽

2021 ◽

Vol 11 (3) ◽

pp. 508

Author(s):

Cristiano Carlomagno ◽

Alice Gualerzi ◽

Silvia Picciolini ◽

Francesca Rodà ◽

Paolo Innocente Banfi ◽

...

Keyword(s):

Raman Spectroscopy ◽

Pilot Study ◽

Principal Component ◽

Surface Enhanced Raman Spectroscopy ◽

Biological Species ◽

Classification Model ◽

Chronic Obstructive ◽

Linear Discriminant ◽

Surface Enhanced ◽

Surface Enhanced Raman

Chronic Obstructive Pulmonary Disease (COPD) is a debilitating pathology characterized by reduced lung function, breathlessness and rapid and unrelenting decrease in quality of life. The severity rate and the therapy selection are strictly dependent on various parameters verifiable after years of clinical observations, missing a direct biomarker associated with COPD. In this work, we report the methodological application of Surface Enhanced Raman Spectroscopy combined with Multivariate statistics for the analysis of saliva samples collected from 15 patients affected by COPD and 15 related healthy subjects in a pilot study. The comparative Raman analysis allowed to determine a specific signature of the pathological saliva, highlighting differences in determined biological species, already studied and characterized in COPD onset, compared to the Raman signature of healthy samples. The unsupervised principal component analysis and hierarchical clustering revealed a sharp data dispersion between the two experimental groups. Using the linear discriminant analysis, we created a classification model able to discriminate the collected signals with accuracies, specificities, and sensitivities of more than 98%. The results of this preliminary study are promising for further applications of Raman spectroscopy in the COPD clinical field.

Download Full-text

A Novel and Rapid Serum Detection Technology for Non-Invasive Screening of Gastric Cancer Based on Raman Spectroscopy Combined With Different Machine Learning Methods

Frontiers in Oncology ◽

10.3389/fonc.2021.665176 ◽

2021 ◽

Vol 11 ◽

Author(s):

Mengya Li ◽

Haiyan He ◽

Guorong Huang ◽

Bo Lin ◽

Huiyan Tian ◽

...

Keyword(s):

Machine Learning ◽

Gastric Cancer ◽

Raman Spectroscopy ◽

Raman Spectra ◽

Classification Model ◽

Support Vector ◽

Learning Methods ◽

Machine Learning Methods ◽

Unseen Data ◽

Raman Spectral Data

Gastric cancer (GC) is the fifth most common cancer in the world and a serious threat to human health. Due to its high morbidity and mortality, a simple, rapid and accurate early screening method for GC is urgently needed. In this study, the potential of Raman spectroscopy combined with different machine learning methods was explored to distinguish serum samples from GC patients and healthy controls. Serum Raman spectra were collected from 109 patients with GC (including 35 in stage I, 14 in stage II, 35 in stage III, and 25 in stage IV) and 104 healthy volunteers matched for age, presenting for a routine physical examination. We analyzed the difference in serum metabolism between GC patients and healthy people through a comparative study of the average Raman spectra of the two groups. Four machine learning methods, one-dimensional convolutional neural network, random forest, support vector machine, and K-nearest neighbor were used to explore identifying two sets of Raman spectral data. The classification model was established by using 70% of the data as a training set and 30% as a test set. Using unseen data to test the model, the RF model yielded an accuracy of 92.8%, and the sensitivity and specificity were 94.7% and 90.8%. The performance of the RF model was further confirmed by the receiver operating characteristic (ROC) curve, with an area under the curve (AUC) of 0.9199. This exploratory work shows that serum Raman spectroscopy combined with RF has great potential in the machine-assisted classification of GC, and is expected to provide a non-destructive and convenient technology for the screening of GC patients.

Download Full-text

Classification Model for Skin Cancer Diagnosis in Vitro Using Raman Spectroscopy

10.1063/1.3482595 ◽

2010 ◽

Author(s):

Benito Bodanese ◽

Landulfo Silveira ◽

Regiane Albertini ◽

Renato A. Za^ngaro ◽

Marcos T. T. Pacheco ◽

...

Keyword(s):

Raman Spectroscopy ◽

Skin Cancer ◽

Cancer Diagnosis ◽

Classification Model

Download Full-text

Fibre Optic SERS Probes For Remote Sensing

10.32920/ryerson.14643651.v1 ◽

2021 ◽

Author(s):

Aditya H. Pandya

Keyword(s):

Remote Sensing ◽

Raman Spectroscopy ◽

Optical Fiber ◽

Optical Fibers ◽

Surface Enhanced Raman Spectroscopy ◽

The Body ◽

Periodic Array ◽

Classification Model ◽

Nanoporous Silica ◽

Nanoporous Films

Surface Enhanced Raman Spectroscopy (SERS) enhances spontaneous Raman spectroscopy by the virtue of plasmon resonance of nanoparticles. Clinical application of SERS is challenging as nanoparticles remain in the body for long periods of time and a full toxicity analysis has yet to be extensively studied. In this study, Nanosphere lithography (NSL) was used to create optical fibers with nanoparticle enhanced tips for remote sensing using SERS. A custom designed RS collection setup was created for optimal collection of spectra from the optical fibers. It was found that an optical fiber with 0.5 numerical aperture (NA) allowed for better detection of Raman peaks while mitigating the fluorescence background of the optical fiber without any optical filters. Such a sensing platform can potentially be used to temporarily introduce nanoparticles into a sensing environment as it allows retracting the nanoparticles along with the tip. Nanoporous SERS platform has been fabricated using nanoporous silica glass with 7 nm and 17 nm pore diameters. An inexpensive fabrication approach of sputter deposition of Au layers was employed on prefabricated nanoporous silica glasses. 7 nm pore glasses provided larger enhancement than the glasses with 17 nm pores. A gold layer thickness of 25 nm was observed to produce largest enhancements. Nanoporous SERS substrates allow a larger effective SERS area compared to NSL based fabrication substrates and such nanoporous structures can be potentially fabricated on optical fiber tips for remote sensing. Finite Element Modeling (FEM) method was implemented for simulating single nanoparticles, an infinite periodic array of nanoparticles and nanoporous films using COMSOL Multiphysics software package. The extinction spectra obtained theoretically were found to match the experimental results for single nanoparticles. The maximum enhancement for the periodic array was two orders of magnitude larger than single particles while the integrated (average) enhancement was only two and a half times larger. Nanoporous films were also modelled using the FEM technique. Preliminary clinical data were collected from excised breast tissues for evaluating RS as a tool for cancer diagnostics. Spectral peaks from healthy tissues were found to be prominent than cancerous tissues and further experiments are needed to create a multivariate classification model for diagnostics.

Download Full-text

Discriminating Neoplastic and Normal Brain Tissues in Vitro Through Raman Spectroscopy: A Principal Components Analysis Classification Model

Photomedicine and Laser Surgery ◽

10.1089/pho.2012.3460 ◽

2013 ◽

Vol 31 (12) ◽

pp. 595-604 ◽

Cited By ~ 13

Author(s):

Ricardo Pinto Aguiar ◽

Landulfo Silveira ◽

Edgar Teixeira Falcão ◽

Marcos Tadeu Tavares Pacheco ◽

Renato Amaro Zângaro ◽

...

Keyword(s):

Raman Spectroscopy ◽

Principal Components Analysis ◽

Principal Components ◽

Classification Model ◽

Normal Brain ◽

Components Analysis ◽

Brain Tissues

Download Full-text

Classification of oil palm fresh fruit maturity based on carotene content from Raman spectra

Scientific Reports ◽

10.1038/s41598-021-97857-5 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Thinal Raj ◽

Fazida Hanim Hashim ◽

Aqilah Baseri Huddin ◽

Aini Hussain ◽

Mohd Faisal Ibrahim ◽

...

Keyword(s):

Raman Spectroscopy ◽

Oil Palm ◽

Fresh Fruit ◽

Classification Model ◽

Oil Yield ◽

Raman Peak ◽

Molecular Fingerprint ◽

Carotene Content ◽

Palm Fruit ◽

Palm Fruits

AbstractThe oil yield, measured in oil extraction rate per hectare in the palm oil industry, is directly affected by the ripening levels of the oil palm fresh fruit bunches at the point of harvesting. A rapid, non-invasive and reliable method in assessing the maturity level of oil palm harvests will enable harvesting at an optimum time to increase oil yield. This study shows the potential of using Raman spectroscopy to assess the ripeness level of oil palm fruitlets. By characterizing the carotene components as useful ripeness features, an automated ripeness classification model has been created using machine learning. A total of 46 oil palm fruit spectra consisting of 3 ripeness categories; under ripe, ripe, and over ripe, were analyzed in this work. The extracted features were tested with 19 classification techniques to classify the oil palm fruits into the three ripeness categories. The Raman peak averaging at 1515 cm−1 is shown to be a significant molecular fingerprint for carotene levels, which can serve as a ripeness indicator in oil palm fruits. Further signal analysis on the Raman peak reveals 4 significant sub bands found to be lycopene (ν1a), β-carotene (ν1b), lutein (ν1c) and neoxanthin (ν1d) which originate from the C=C stretching vibration of carotenoid molecules found in the peel of the oil palm fruit. The fine KNN classifier is found to provide the highest overall accuracy of 100%. The classifier employs 6 features: peak intensities of bands ν1a to ν1d and peak positions of bands ν1c and ν1d as predictors. In conclusion, the Raman spectroscopy method has the potential to provide an accurate and effective way in determining the ripeness of oil palm fresh fruits.

Download Full-text