Spectral classification for diagnosis involving numerous pathologies in a complex clinical setting: A neuro-oncology example

Extraction of Reduced Infrared Biomarker Signatures for the Stratification of Patients Affected by Parkinson’s Disease: An Untargeted Metabolomic Approach

An untargeted Fourier transform infrared (FTIR) metabolomic approach was employed to study metabolic changes and disarrangements, recorded as infrared signatures, in Parkinson’s disease (PD). Herein, the principal aim was to propose an efficient sequential classification strategy based on SELECT-LDA, which enabled optimal stratification of three main categories: PD patients from subjects with Alzheimer’s disease (AD) and healthy controls (HC). Moreover, sub-categories, such as PD at the early stage (PDI) from PD in the advanced stage (PDD), and PDD vs. AD, were stratified. Every classification step with selected wavenumbers achieved 90.11% to 100% correct assignment rates in classification and internal validation. Therefore, selected metabolic signatures from new patients could be used as input features for screening and diagnostic purposes.

Raman hyperspectral imaging coupled to three-dimensional discriminant analysis: Classification of meningiomas brain tumour grades

Meningiomas remains a clinical dilemma. They are the commonest "benign" types of brain tumours and, although being typically benign, they are divided into three WHO grades categories (I, II and III) which are associated with the tumour growth rate and likelihood of recurrence. Recurrence depends on extend of surgery as well as histopathological diagnosis. There is a marked variation amongst surgeons in the follow-up arrangements for their patients even within the same unit which has a significant clinical, and financial implication. Knowing the tumour grade rapidly is an important factor to predict surgical outcomes and adequate patient treatment. Clinical follow up sometimes is haphazard and not based on clear evidence. Spectrochemical techniques are a powerful tool for cancer diagnostics. Raman hyperspectral imaging is able to generate spatially-distributed spectrochemical signatures with great sensitivity. Using this technique, 95 brain tissue samples (66 meningiomas WHO grade I, 24 meningiomas WHO grade II and 5 meningiomas that reoccurred) were analysed in order to discriminate grade I and grade II samples. Newly-developed three-dimensional discriminant analysis algorithms were used to process the hyperspectral imaging data in a 3D fashion. Three-dimensional principal component analysis quadratic discriminant analysis (3D-PCA-QDA) was able to distinguish grade I and grade II meningioma samples with 96% test accuracy (100% sensitivity and 95% specificity). This technique is here shown to be a high-throughput, reagent-free, non-destructive, and can give accurate predictive information regarding the meningioma tumour grade, hence, having enormous clinical potential with regards to being developed for intra-operative real-time assessment of disease.

Artificial neural network in the discrimination of lung cancer based on infrared spectroscopy

Given the increasing prevalence of lung cancer worldwide, an auxiliary diagnostic method is needed alongside the microscopic examination of biopsy samples, which is dependent on the skills and experience of pathologists. Thus, this study aimed to advance lung cancer diagnosis by developing five (5) artificial neural network (NN) models that can discriminate malignant from benign samples based on infrared spectral data of lung tumors (n = 122; 56 malignant, 66 benign). NNs were benchmarked with classical machine learning (CML) models. Stratified 10-fold cross-validation was performed to evaluate the NN models, and the performance metrics—area under the curve (AUC), accuracy (ACC) positive predictive value (PPV), negative predictive value (NPV), specificity rate (SR), and recall rate (RR)—were averaged for comparison. All NNs were able to outperform the CML models, however, support vector machine is relatively comparable to NNs. Among the NNs, CNN performed best with an AUC of 92.28% ± 7.36%, ACC of 98.45% ± 1.72%, PPV of 96.62% ± 2.30%, NPV of 90.50% ± 11.92%, SR of 96.01% ± 3.09%, and RR of 89.21% ± 12.93%. In conclusion, NNs can be potentially used as a computational tool in lung cancer diagnosis based on infrared spectroscopy of lung tissues.

Infrared Spectroscopy of Blood

The magnitude of infectious diseases in the twenty-first century created an urgent need for point-of-care diagnostics. Critical shortages in reagents and testing kits have had a large impact on the ability to test patients with a suspected parasitic, bacteria, fungal, and viral infections. New point-of-care tests need to be highly sensitive, specific, and easy to use and provide results in rapid time. Infrared spectroscopy, coupled to multivariate and machine learning algorithms, has the potential to meet this unmet demand requiring minimal sample preparation to detect both pathogenic infectious agents and chronic disease markers in blood. This focal point article will highlight the application of Fourier transform infrared spectroscopy to detect disease markers in blood focusing principally on parasites, bacteria, viruses, cancer markers, and important analytes indicative of disease. Methodologies and state-of-the-art approaches will be reported and potential confounding variables in blood analysis identified. The article provides an up to date review of the literature on blood diagnosis using infrared spectroscopy highlighting the recent advances in this burgeoning field.

ATR-FTIR spectroscopy as adjunct method to the microscopic examination of hematoxylin and eosin-stained tissues in diagnosing lung cancer

Lung cancer remains the leading cause of cancer-related death worldwide. Since prognosis and treatment outcomes rely on fast and accurate diagnosis, there is a need for more cost-effective, sensitive, and specific method for lung cancer detection. Thus, this study aimed to determine the ability of ATR-FTIR in discriminating malignant from benign lung tissues and evaluate its concordance with H&E staining. Three (3) 5μm-thick sections were cut from formalin fixed paraffin embedded (FFPE) cell or tissue blocks from patients with lung lesions. The outer sections were H&E-stained and sent to two (2) pathologists to confirm the histopathologic diagnosis. The inner section was deparaffinized by standard xylene method and then subjected to ATR-FTIR analysis. Distinct spectral profiles that distinguished (p<0.05) one sample from another, called the "fingerprint region", were observed in five (5) peak patterns representing the amides, lipids, and nucleic acids. Principal component analysis and hierarchical cluster analysis evidently clustered the benign from malignant tissues. ATR-FTIR showed 97.73% sensitivity, 92.45% specificity, 94.85% accuracy, 91.49% positive predictive value and 98.00% negative predictive value in discriminating benign from malignant lung tissue. Further, strong agreement was observed between histopathologic readings and ATR-FTIR analysis. This study shows the potential of ATR-FTIR spectroscopy as a potential adjunct method to the gold standard, the microscopic examination of hematoxylin and eosin (H&E)-stained tissues, in diagnosing lung cancer.

Spectrochemical differentiation of meningioma tumours based on attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy

Meningiomas are the commonest types of tumours in the central nervous system (CNS). It is a benign type of tumour divided into three WHO grades (I, II and III) associated with tumour growth rate and likelihood of recurrence, where surgical outcomes and patient treatments are dependent on the meningioma grade and histological subtype. The development of alternative approaches based on attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy could aid meningioma grade determination and its biospectrochemical profiling in an automated fashion. Herein, ATR-FTIR in combination with chemometric techniques is employed to distinguish grade I, grade II and grade I meningiomas that re-occurred. Ninety-nine patients were investigated in this study where their formalin-fixed paraffin-embedded (FFPE) brain tissue samples were analysed by ATR-FTIR spectroscopy. Subsequent classification was performed via principal component analysis plus linear discriminant analysis (PCA-LDA) and partial least squares plus discriminant analysis (PLS-DA). PLS-DA gave the best results where grade I and grade II meningiomas were discriminated with 79% accuracy, 80% sensitivity and 73% specificity, while grade I versus grade I recurrence and grade II versus grade I recurrence were discriminated with 94% accuracy (94% sensitivity and specificity) and 97% accuracy (97% sensitivity and 100% specificity), respectively. Several wavenumbers were identified as possible biomarkers towards tumour differentiation. The majority of these were associated with lipids, protein, DNA/RNA and carbohydrate alterations. These findings demonstrate the potential of ATR-FTIR spectroscopy towards meningioma grade discrimination as a fast, low-cost, non-destructive and sensitive tool for clinical settings.

Graphical abstract

Discrimination of fresh frozen non-tumour and tumour brain tissue using spectrochemical analyses and a classification model

Introduction: In order for brain tumours to be successfully treated, maximal resection is beneficial. A method to detect infiltrative tumour edges intraoperatively, improving on current methods would be clinically useful. Vibrational spectroscopy offers the potential to provide a handheld, reagent-free method for tumour detection.Purpose: This study was designed to determine the ability of both Raman and Fourier-transform infrared (FTIR) spectroscopy towards differentiating between normal brain tissue, glioma or meningioma.Method: Unfixed brain tissue, which had previously only been frozen, comprising normal, glioma or meningioma tissue was placed onto calcium fluoride slides for analysis using Raman and attenuated total reflection (ATR)-FTIR spectroscopy. Matched haematoxylin and eosin slides were used to confirm tumour areas. Analyses were then conducted to generate a classification model.Results: This study demonstrates the ability of both Raman and ATR-FTIR spectroscopy to discriminate tumour from non-tumour fresh frozen brain tissue with 94% and 97.2% of cases correctly classified, with sensitivities of 98.8% and 100%, respectively. This decreases when spectroscopy is used to determine tumour type.Conclusion: The study demonstrates the ability of both Raman and ATR-FTIR spectroscopy to detect tumour tissue from non-tumour brain tissue with a high degree of accuracy. This demonstrates the ability of spectroscopy when targeted for a cancer diagnosis. However, further improvement would be required for a classification model to determine tumour type using this technology, in order to make this tool clinically viable.

Ex Vivo Raman Spectrochemical Analysis Using a Handheld Probe Demonstrates High Predictive Capability of Brain Tumour Status

With brain tumour incidence increasing, there is an urgent need for better diagnostic tools. Intraoperatively, brain tumours are diagnosed using a smear preparation reported by a neuropathologist. These have many limitations, including the time taken for the specimen to reach the pathology department and for results to be communicated to the surgeon. There is also a need to assist with resection rates and identifying infiltrative tumour edges intraoperatively to improve clearance. We present a novel study using a handheld Raman probe in conjunction with gold nanoparticles, to detect primary and metastatic brain tumours from fresh brain tissue sent for intraoperative smear diagnosis. Fresh brain tissue samples sent for intraoperative smear diagnosis were tested using the handheld Raman probe after application of gold nanoparticles. Derived Raman spectra were inputted into forward feature extraction algorithms to build a predictive model for sensitivity and specificity of outcome. These results demonstrate an ability to detect primary from metastatic tumours (especially for normal and low grade lesions), in which accuracy, sensitivity and specificity were respectively equal to 98.6%, 94.4% and 99.5% for normal brain tissue; 96.1%, 92.2% and 97.0% for low grade glial tumours; 90.3%, 89.7% and 90.6% for high grade glial tumours; 94.8%, 63.9% and 97.1% for meningiomas; 95.4%, 79.2% and 98.8% for metastases; and 99.6%, 88.9% and 100% for lymphoma, based on smear samples (κ = 0.87). Similar results were observed when compared to the final formalin-fixed paraffin embedded tissue diagnosis (κ = 0.85). Overall, our results have demonstrated the ability of Raman spectroscopy to match results provided by intraoperative smear diagnosis and raise the possibility of use intraoperatively to aid surgeons by providing faster diagnosis. Moving this technology into theatre will allow it to develop further and thus reach its potential in the clinical arena.