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

Meta-Analysis of the Efficacy of Raman Spectroscopy and Machine-Learning-Based Identification of Glioma Tissue

Intraoperative Raman spectroscopy (RS) has been identified as a potential tool for surgeons to rapidly and noninvasively differentiate between diseased and normal tissue. Since the previous meta-analysis on the subject was published in 2016, improvements in both spectroscopy equipment and machine learning models used to process spectra may have led to an increase in RS efficacy. Therefore, we decided to conduct a meta-analysis to determine the efficacy of RS when differentiating between glioma tissue and normal brain tissue. Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were followed while conducting this meta-analysis. A search was conducted on PubMed and Web of Science for prospective and retrospective studies published between 2016 and 2022 using intraoperative RS and standard histology methods to differentiate between glioma and normal brain tissue. Meta-analyses of log odds ratios, sensitivity, and specificity were conducted in JASP using the random-effects model with restricted maximum likelihood estimation. A total of 9 studies met our inclusion criteria, comprising 673 patients and 8319 Raman spectra. Meta-analysis of log diagnostic odds ratios revealed high heterogeneity (I2 = 79.83%) and yielded a back-transformed diagnostic odds ratio of 76.71 (95% confidence interval: 39.57-148.71). Finally, meta-analysis for sensitivity and specificity of RS for glioma tissue showed high heterogeneity (I2 = 99.37% and 98.21%, respectively) and yielded an overall sensitivity of 95.3% (95% confidence interval: 91.0%-99.6%) and an overall specificity of 71.2% (95% confidence interval: 54.8%-87.6%). Calculation of a summary receiver operating curve yielded an overall area under the curve of 0.9265. Raman spectroscopy represents a promising tool for surgeons to quickly and accurately differentiate between healthy brain tissue and glioma tissue.

In situ brain tumor detection using a Raman spectroscopy system-results of a multicenter study

Safe and effective brain tumor surgery aims to remove tumor tissue, not non-tumoral brain. This is a challenge since tumor cells are often not visually distinguishable from peritumoral brain during surgery. To address this, we conducted a multicenter study testing whether the Sentry System could distinguish the three most common types of brain tumors from brain tissue in a label-free manner. The Sentry System is a new real time, in situ brain tumor detection device that merges Raman spectroscopy with machine learning tissue classifiers. Nine hundred and seventy-six in situ spectroscopy measurements and colocalized tissue specimens were acquired from 67 patients undergoing surgery for glioblastoma, brain metastases, or meningioma to assess tumor classification. The device achieved diagnostic accuracies of 91% for glioblastoma, 97% for brain metastases, and 96% for meningiomas. These data show that the Sentry System discriminated tumor containing tissue from non-tumoral brain in real time and prior to resection.

Optical Methods for Brain Tumor Detection: A Systematic Review

Background: In brain tumor surgery, maximal tumor resection is typically desired. This is complicated by infiltrative tumor cells which cannot be visually distinguished from healthy brain tissue. Optical methods are an emerging field that can potentially revolutionize brain tumor surgery through intraoperative differentiation between healthy and tumor tissues. Methods: This study aimed to systematically explore and summarize the existing literature on the use of Raman Spectroscopy (RS), Hyperspectral Imaging (HSI), Optical Coherence Tomography (OCT), and Diffuse Reflectance Spectroscopy (DRS) for brain tumor detection. MEDLINE, Embase, and Web of Science were searched for studies evaluating the accuracy of these systems for brain tumor detection. Outcome measures included accuracy, sensitivity, and specificity. Results: In total, 44 studies were included, covering a range of tumor types and technologies. Accuracy metrics in the studies ranged between 54 and 100% for RS, 69 and 99% for HSI, 82 and 99% for OCT, and 42 and 100% for DRS. Conclusions: This review provides insightful evidence on the use of optical methods in distinguishing tumor from healthy brain tissue.

Prediction of WHO grade and methylation class of aggressive meningiomas: Extraction of diagnostic information from infrared spectroscopic data

Background

Infrared (IR) spectroscopy allows intraoperative, optical brain tumor diagnosis. Here, we explored it as a translational technology for the identification of aggressive meningioma types according to both, the WHO CNS grading system and the methylation classes (MC).

Methods

Frozen sections of 47 meningioma were examined by IR spectroscopic imaging and different classification approaches were compared to discern samples according to WHO grade or MC.

Results

IR spectroscopic differences were more pronounced between WHO grade 2 and 3 than between MC intermediate and MC malignant, although similar spectral ranges were affected. Aggressive types of meningioma exhibited reduced bands of carbohydrates (at 1024 cm-1) and nucleic acids (at 1080 cm-1), along with increased bands of phospholipids (at 1240 and 1450 cm-1). While linear discriminant analysis was able to discern spectra of WHO grade 2 and 3 meningiomas (AUC 0.89), it failed for MC (AUC 0.66). However, neural network classifiers were effective for classification according to both WHO grade (AUC 0.91) and MC (AUC 0.83), resulting in the correct classification of 20/23 meningiomas of the test set.

Conclusions

IR spectroscopy proved capable of extracting information about the malignancy of meningiomas, not only according to the WHO grade, but also for a diagnostic system based on molecular tumor characteristics. In future clinical use, physicians could assess the goodness of the classification by considering classification probabilities and cross-measurement validation. This might enhance the overall accuracy and clinical utility, reinforcing the potential of IR spectroscopy in advancing precision medicine for meningioma characterization.

Influence of measurement mode on the results of glioblastoma multiforme analysis with the FTIR microspectroscopy

Fourier Transform Infrared (FTIR) microspectroscopy is well known for its effectiveness in spectral and biochemical analyses of various materials. It enables to determine the sample biochemical composition by assigning detected frequencies, characteristic for functional groups of main biological macromolecules. In analysis of tissue sections one of two measurement modes, namely transmission and transflection, is usually applied. The first one has relatively straightforward geometry, hence it is considered to be more precise and accurate. However, IR-transparent media are very fragile and expensive. Transflection does not require expensive substrates, but is more prone to disruptive influence of Mie scattering as well as electric field standing wave effect. The excessive comparison of spectra' characteristics, obtained via both measurement modes, was performed in this paper. By the means of Mann-Whitney non-parametrical U test and PCA, the comparison of results obtained with both modes and assessment of usefulness of IR spectra obtained with transmission and transflection modes to differentiate between healthy and GBM-affected tissue, were performed. The main objective of the presented research is to compare the results of FTIR analysis of unfixed biological samples performed with transflection and transmission mode. In frame of the study we demonstrated the discrepancies between results of biochemical analysis performed based on data obtained with transmission and transflection. Such observation suggests that caution should be taken in drawing conclusions from the results obtained with transflection geometry, as its more prone to disruptive effects. Despite that, IR spectra developed with both modes allowed to distinguish GBM area from healthy tissue, which proves their diagnostic potential. Especially, application of the ME-EMSC correction of spectra before PCA enhances the performance of both methods to distinguish the analysed tissue areas.

A new approach for clinical translation of infrared spectroscopy: exploitation of the signature of glioblastoma for general brain tumor recognition

PURPOSE

Infrared (IR) spectroscopy has the potential for tumor delineation in neurosurgery. Previous research showed that IR spectra of brain tumors are generally characterized by reduced lipid-related and increased protein-related bands. Therefore, we propose the exploitation of these common spectral changes for brain tumor recognition.

METHODS

Attenuated total reflection IR spectroscopy was performed on fresh specimens of 790 patients within minutes after resection. Using principal component analysis and linear discriminant analysis, a classification model was developed on a subset of glioblastoma (n = 135) and non-neoplastic brain (n = 27) specimens, and then applied to classify the IR spectra of several types of brain tumors.

RESULTS

The model correctly classified 82% (517/628) of specimens as "tumor" or "non-tumor", respectively. While the sensitivity was limited for infiltrative glioma, this approach recognized GBM (86%), other types of primary brain tumors (92%) and brain metastases (92%) with high accuracy and all non-tumor samples were correctly identified.

CONCLUSION

The concept of differentiation of brain tumors from non-tumor brain based on a common spectroscopic tumor signature will accelerate clinical translation of infrared spectroscopy and related technologies. The surgeon could use a single instrument to detect a variety of brain tumor types intraoperatively in future clinical settings. Our data suggests that this would be associated with some risk of missing infiltrative regions or tumors, but not with the risk of removing non-tumor brain.

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.

Vibrational Biospectroscopy: An Alternative Approach to Endometrial Cancer Diagnosis and Screening

Endometrial cancer (EC) is the sixth most common cancer and the fourth leading cause of death among women worldwide. Early detection and treatment are associated with a favourable prognosis and reduction in mortality. Unlike other common cancers, however, screening strategies lack the required sensitivity, specificity and accuracy to be successfully implemented in clinical practice and current diagnostic approaches are invasive, costly and time consuming. Such limitations highlight the unmet need to develop diagnostic and screening alternatives for EC, which should be accurate, rapid, minimally invasive and cost-effective. Vibrational spectroscopic techniques, Mid-Infrared Absorption Spectroscopy and Raman, exploit the atomic vibrational absorption induced by interaction of light and a biological sample, to generate a unique spectral response: a “biochemical fingerprint”. These are non-destructive techniques and, combined with multivariate statistical analysis, have been shown over the last decade to provide discrimination between cancerous and healthy samples, demonstrating a promising role in both cancer screening and diagnosis. The aim of this review is to collate available evidence, in order to provide insight into the present status of the application of vibrational biospectroscopy in endometrial cancer diagnosis and screening, and to assess future prospects.

Human serum mid-infrared spectroscopy combined with machine learning algorithms for rapid detection of gliomas

Glioma has a low cure rate and a high mortality rate. Therefore, correct diagnosis and treatment are essential for patients. This research aims to use mid-infrared spectroscopy combined with machine learning algorithms to identify patients with glioma. The glioma infrared spectra and the control group serum are smoothed and normalized, then the principal component analysis (PCA) algorithm is used to reduce the data dimensionality, and finally, the particle swarm optimization-support vector machine (PSO-SVM), backpropagation (BP) neural network and decision tree (DT) model are established. The classification accuracy of the three models was 92.00 %, 91.83 %, 87.20 %, and the AUC values were 0.919, 0.945, and 0.866, respectively. The results show that PCA-PSO-SVM has a better classification effect. This study shows that mid-infrared spectroscopy combined with machine learning algorithms has great potential in the application of non-invasive, rapid and accurate identification of glioma patients.

Glioma biopsies Classification Using Raman Spectroscopy and Machine Learning Models on Fresh Tissue Samples

Identifying tumor cells infiltrating normal-appearing brain tissue is critical to achieve a total glioma resection. Raman spectroscopy (RS) is an optical technique with potential for real-time glioma detection. Most RS reports are based on formalin-fixed or frozen samples, with only a few studies deployed on fresh untreated tissue. We aimed to probe RS on untreated brain biopsies exploring novel Raman bands useful in distinguishing glioma and normal brain tissue. Sixty-three fresh tissue biopsies were analyzed within few minutes after resection. A total of 3450 spectra were collected, with 1377 labelled as Healthy and 2073 as Tumor. Machine learning methods were used to classify spectra compared to the histo-pathological standard. The algorithms extracted information from 60 different Raman peaks identified as the most representative among 135 peaks screened. We were able to distinguish between tumor and healthy brain tissue with accuracy and precision of 83% and 82%, respectively. We identified 19 new Raman shifts with known biological significance. Raman spectroscopy was effective and accurate in discriminating glioma tissue from healthy brain ex-vivo in fresh samples. This study added new spectroscopic data that can contribute to further develop Raman Spectroscopy as an intraoperative tool for in-vivo glioma detection.