Oral Cancer Discrimination and Novel Oral Epithelial Dysplasia Stratification Using FTIR Imaging and Machine Learning

Oral squamous cell carcinoma identification by FTIR spectroscopy of oral biofluids

OBJECTIVES

This case study evaluated the efficacy of mid-infrared spectroscopy on the identification of oral squamous cell carcinoma, following the assessment of unstimulated whole saliva.

STUDY DESIGN AND METHODS

The trial follows a matched case-control design. Saliva samples were characterized through mid-infrared spectroscopy, and chemometric tools were applied to distinguish between case and control participants, further identifying the spectral regions that played a pivotal role in the successful identification of oral squamous cell carcinoma.

RESULTS

Mid-infrared spectroscopy was capable to discriminate between cancer patients and matched controls with 100% of correct predictions. Additionally, the spectral regions mostly contributing to the successful prediction were identified and found to be potentially associated with significant molecular changes crucial to the carcinogenic process.

CONCLUSION

The application of mid-infrared spectroscopy in saliva analysis may be regarded as an innovative, noninvasive, low cost, and sensitive technique contributing to the identification of oral squamous cell carcionma.

Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: A systematic review

BACKGROUND

Oral Potentially Malignant Disorders (OPMDs) refer to a heterogenous group of clinical presentations with heightened rate of malignant transformation. Identification of risk levels in OPMDs is crucial to determine the need for active intervention in high-risk patients and routine follow-up in low-risk ones. Machine learning models has shown tremendous potential in several areas of dentistry that strongly suggest its application to estimate rate of malignant transformation of precancerous lesions.

METHODS

A comprehensive literature search was performed on Pubmed/MEDLINE, Web of Science, Scopus, Embase, Cochrane Library database to identify articles including machine learning models and algorithms to predict malignant transformation in OPMDs. Relevant bibliographic data, study characteristics, and outcomes were extracted for eligible studies. Quality of the included studies was assessed through the IJMEDI checklist.

RESULTS

Fifteen articles were found suitable for the review as per the PECOS criteria. Amongst all studies, highest sensitivity (100%) was recorded for U-net architecture, Peaks Random forest model, and Partial least squares discriminant analysis (PLSDA). Highest specificity (100%) was noted for PLSDA. Range of overall accuracy in risk prediction was between 95.4% and 74%.

CONCLUSION

Machine learning proved to be a viable tool in risk prediction, demonstrating heightened sensitivity, automation, and improved accuracy for predicting transformation of OPMDs. It presents an effective approach for incorporating multiple variables to monitor the progression of OPMDs and predict their malignant potential. However, its sensitivity to dataset characteristics necessitates the optimization of input parameters to maximize the efficiency of the classifiers.

An Update on the Use of Artificial Intelligence in Digital Pathology for Oral Epithelial Dysplasia Research

INTRODUCTION

Oral epithelial dysplasia (OED) is a precancerous histopathological finding which is considered the most important prognostic indicator for determining the risk of malignant transformation into oral squamous cell carcinoma (OSCC). The gold standard for diagnosis and grading of OED is through histopathological examination, which is subject to inter- and intra-observer variability, impacting accurate diagnosis and prognosis. The aim of this review article is to examine the current advances in digital pathology for artificial intelligence (AI) applications used for OED diagnosis.

MATERIALS AND METHODS

We included studies that used AI for diagnosis, grading, or prognosis of OED on histopathology images or intraoral clinical images. Studies utilizing imaging modalities other than routine light microscopy (e.g., scanning electron microscopy), or immunohistochemistry-stained histology slides, or immunofluorescence were excluded from the study. Studies not focusing on oral dysplasia grading and diagnosis, e.g., to discriminate OSCC from normal epithelial tissue were also excluded.

RESULTS

A total of 24 studies were included in this review. Nineteen studies utilized deep learning (DL) convolutional neural networks for histopathological OED analysis, and 4 used machine learning (ML) models. Studies were summarized by AI method, main study outcomes, predictive value for malignant transformation, strengths, and limitations.

CONCLUSION

ML/DL studies for OED grading and prediction of malignant transformation are emerging as promising adjunctive tools in the field of digital pathology. These adjunctive objective tools can ultimately aid the pathologist in more accurate diagnosis and prognosis prediction. However, further supportive studies that focus on generalization, explainable decisions, and prognosis prediction are needed.

Exploration of macromolecular phenotype of human skeletal muscle in diabetes using infrared spectroscopy

Introduction

The global burden of diabetes mellitus is escalating, and more efficient investigative strategies are needed for a deeper understanding of underlying pathophysiological mechanisms. The crucial role of skeletal muscle in carbohydrate and lipid metabolism makes it one of the most susceptible tissues to diabetes-related metabolic disorders. In tissue studies, conventional histochemical methods have several technical limitations and have been shown to inadequately characterise the biomolecular phenotype of skeletal muscle to provide a holistic view of the pathologically altered proportions of macromolecular constituents.

Materials and methods

In this pilot study, we examined the composition of five different human skeletal muscles from male donors diagnosed with type 2 diabetes and non-diabetic controls. We analysed the lipid, glycogen, and collagen content in the muscles in a traditional manner with histochemical assays using different staining techniques. This served as a reference for comparison with the unconventional analysis of tissue composition using Fourier-transform infrared spectroscopy as an alternative methodological approach.

Results

A thorough chemometric post-processing of the infrared spectra using a multi-stage spectral decomposition allowed the simultaneous identification of various compositional details from a vibrational spectrum measured in a single experiment. We obtained multifaceted information about the proportions of the different macromolecular constituents of skeletal muscle, which even allowed us to distinguish protein constituents with different structural properties. The most important methodological steps for a comprehensive insight into muscle composition have thus been set and parameters identified that can be used for the comparison between healthy and diabetic muscles.

Conclusion

We have established a methodological framework based on vibrational spectroscopy for the detailed macromolecular analysis of human skeletal muscle that can effectively complement or may even serve as an alternative to histochemical assays. As this is a pilot study with relatively small sample sets, we remain cautious at this stage in drawing definitive conclusions about diabetes-related changes in skeletal muscle composition. However, the main focus and contribution of our work has been to provide an alternative, simple and efficient approach for this purpose. We are confident that we have achieved this goal and have brought our methodology to a level from which it can be successfully transferred to a large-scale study that allows the effects of diabetes on skeletal muscle composition and the interrelationships between the macromolecular tissue alterations due to diabetes to be investigated.

Clinical Experience with Autofluorescence Guided Oral Squamous Cell Carcinoma Surgery

In our study, the effect of the use of autofluorescence (Visually Enhanced Lesion Scope-VELscope) on increasing the success rate of surgical treatment in oral squamous carcinoma (OSCC) was investigated. Our hypothesis was tested on a group of 122 patients suffering from OSCC, randomized into a study and a control group enrolled in our study after meeting the inclusion criteria. The preoperative checkup via VELscope, accompanied by the marking of the range of a loss of fluorescence in the study group, was performed before the surgery. We developed a unique mucosal tattoo marking technique for this purpose. The histopathological results after surgical treatment, i.e., the margin status, were then compared. In the study group, we achieved pathological free margin (pFM) in 55 patients, pathological close margin (pCM) in 6 cases, and we encountered no cases of pathological positive margin (pPM) in the mucosal layer. In comparison, the control group results revealed pPM in 7 cases, pCM in 14 cases, and pFM in 40 of all cases in the mucosal layer. This study demonstrated that preoperative autofluorescence assessment of the mucosal surroundings of OSCC increased the ability to achieve pFM resection 4.8 times in terms of lateral margins.

Label-Free Proteomics of Oral Mucosa Tissue to Identify Potential Biomarkers That Can Flag Predilection of Precancerous Lesions to Oral Cell Carcinoma: A Preliminary Study

Oral squamous cell carcinomas are mostly preceded by precancerous lesions such as leukoplakia and erythroplakia. Our study is aimed at identifying potential biomarker proteins in precancerous lesions of leukoplakia and erythroplakia that can flag their transformation to oral cancer. Four biological replicate samples from clinical phenotypes of healthy control, leukoplakia, erythroplakia, and oral carcinoma were annotated based on clinical screening and histopathological evaluation of buccal mucosa tissue. Differentially expressed proteins were delineated using a label-free quantitative proteomic experiment done on an Orbitrap Fusion Tribrid mass spectrometer in three technical replicate sets of samples. Raw files were processed using MaxQuant version 2.0.1.0, and downstream analysis was done via Perseus version 1.6.15.0. Validation included functional annotation based on biological processes and pathways using the ClueGO plug-in of Cytoscape. Hierarchical clustering and principal component analysis were performed using the ClustVis tool. Across control, leukoplakia, and cancer, L-lactate dehydrogenase A chain, plectin, and WD repeat-containing protein 1 were upregulated, whereas thioredoxin 1 and spectrin alpha chain, nonerythrocytic 1 were downregulated. Across control, erythroplakia, and cancer, L-lactate dehydrogenase A chain was upregulated whereas aldehyde dehydrogenase 2, peroxiredoxin 1, heat shock 70 kDa protein 1B, and spectrin alpha chain, nonerythrocytic 1 were downregulated. We found that proteins involved in leukoplakia were associated with alteration in cytoskeletal disruption and glycolysis, while in erythroplakia, they were associated with alteration in response to oxidative stress and glycolysis across phenotypes. Hierarchical clustering subgrouped half of precancerous samples under the main branch of the control and the remaining half under carcinoma. Similarly, principal component analysis identified segregated clusters of control, precancerous lesions, and cancer, but erythroplakia phenotypes, in particular, overlapped more with the cancer cluster. Qualitative and quantitative protein signatures across control, precancer, and cancer phenotypes explain possible functional outcomes that dictate malignant transformation to oral carcinoma.