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

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2133
Author(s):  
Rong Wang ◽  
Aparna Naidu ◽  
Yong Wang

The Fourier transform infrared (FTIR) imaging technique was used in a transmission model for the evaluation of twelve oral hyperkeratosis (HK), eleven oral epithelial dysplasia (OED), and eleven oral squamous cell carcinoma (OSCC) biopsy samples in the fingerprint region of 1800–950 cm−1. A series of 100 µm × 100 µm FTIR imaging areas were defined in each sample section in reference to the hematoxylin and eosin staining image of an adjacent section of the same sample. After outlier removal, signal preprocessing, and cluster analysis, a representative spectrum was generated for only the epithelial tissue in each area. Two representative spectra were selected from each sample to reflect intra-sample heterogeneity, which resulted in a total of 68 representative spectra from 34 samples for further analysis. Exploratory analyses using Principal component analysis and hierarchical cluster analysis showed good separation between the HK and OSCC spectra and overlaps of OED spectra with either HK or OSCC spectra. Three machine learning discriminant models based on partial least squares discriminant analysis (PLSDA), support vector machines discriminant analysis (SVMDA), and extreme gradient boosting discriminant analysis (XGBDA) were trained using 46 representative spectra from 12 HK and 11 OSCC samples. The PLSDA model achieved 100% sensitivity and 100% specificity, while both SVM and XGBDA models generated 95% sensitivity and 96% specificity, respectively. The PLSDA discriminant model was further used to classify the 11 OED samples into HK-grade (6), OSCC-grade (4), or borderline case (1) based on their FTIR spectral similarity to either HK or OSCC cases, providing a potential risk stratification strategy for the precancerous OED samples. The results of the current study support the application of the FTIR-machine learning technique in early oral cancer detection.

Cancers ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3185
Author(s):  
Seiko Tatehara ◽  
Kazuhito Satomura

Oral health promotion and examinations have contributed to the early detection of oral cancer and oral potentially malignant disorders, leading to the adaptation of minimally invasive therapies and subsequent improvements in the prognosis/maintenance of the quality of life after treatments. However, the accurate detection of early-stage oral cancer and oral epithelial dysplasia is particularly difficult for conventional oral examinations because these lesions sometimes resemble benign lesions or healthy oral mucosa tissues. Although oral biopsy has been considered the gold standard for accurate diagnosis, it is deemed invasive for patients. For this reason, most clinicians are looking forward to the development of non-invasive diagnostic technologies to detect and distinguish between cancerous and benign lesions. To date, several non-invasive adjunctive fluorescence-based detection systems have improved the accuracy of the detection and diagnosis of oral mucosal lesions. Autofluorescence-based systems can detect lesions as a loss of autofluorescence through irradiation with blue-violet lights. Photodynamic diagnosis using 5-aminolevulinic acid (ALA-PDD) shows the presence of very early oral cancers and oral epithelial dysplasia as a red fluorescent area. In this article, currently used fluorescence-based diagnostic methods are introduced and discussed from a clinical point of view.


2005 ◽  
Vol 63 (4) ◽  
pp. 513-520 ◽  
Author(s):  
Susan Reisine ◽  
Douglas E. Morse ◽  
Walter J. Psoter ◽  
Ellen Eisenberg ◽  
Donald Cohen ◽  
...  

2013 ◽  
Vol 5 ◽  
pp. BIC.S12951 ◽  
Author(s):  
Ahmad A. AbdulMajeed ◽  
Camile S. Farah

Many attempts have been made to identify objective molecular biomarkers to diagnose and prognosticate oral epithelial dysplasia (OED) because histopathological interpretation is subjective and lacks sensitivity. The majority of these efforts describe changes in gene expression at protein level in OED as determined by immunohistochemistry (IHC). However, the literature on these putative markers of oral cancer progression is vast and varied. The main purpose of this article is to review current knowledge on biomarkers of protein expression for OED by IHC approaches. We further discuss these findings in terms of the proposed essential hallmarks of cancer cells to better understand their role in oral oncogenesis.


2019 ◽  
Vol 8 (10) ◽  
pp. 1744 ◽  
Author(s):  
Juan C. de Vicente ◽  
Paula Donate-Pérez del Molino ◽  
Juan P. Rodrigo ◽  
Eva Allonca ◽  
Francisco Hermida-Prado ◽  
...  

Potentially malignant oral lesions, mainly leukoplakia, are common. Malignant transformation varies widely, even in the absence of histological features such as dysplasia. Hence, there is a need for novel biomarker-based systems to more accurately predict the risk of cancer progression. The pluripotency transcription factor SOX2 is frequently overexpressed in cancers, including oral squamous cell carcinoma (OSCC), thereby providing a link between malignancy and stemness. This study investigates the clinical relevance of SOX2 protein expression in early stages of oral carcinogenesis as a cancer risk biomarker, and also its impact on prognosis and disease outcome at late stages of OSCC progression. SOX2 expression was evaluated by immunohistochemistry in 55 patients with oral epithelial dysplasia, and in 125 patients with OSCC, and correlated with clinicopathological data and outcomes. Nuclear SOX2 expression was detected in four (7%) cases of oral epithelial dysplasia, using a cut-off of 10% stained nuclei, and in 16 (29%) cases when any positive nuclei was evaluated. Univariate analysis showed that SOX2 expression and histopathological grading were significantly associated with oral cancer risk; and both were found to be significant independent predictors in the multivariate analysis. Nuclear SOX2 expression was also found in 49 (39%) OSCC cases, was more frequent in early tumor stages and N0 cases, and was associated with a better survival. In conclusion, SOX2 expression emerges as an independent predictor of oral cancer risk in patients with oral leukoplakia. These findings underscore the relevant role of SOX2 in early oral tumorigenesis rather than in tumor progression.


2007 ◽  
Vol 18 (9) ◽  
pp. 919-929 ◽  
Author(s):  
Douglas E. Morse ◽  
Walter J. Psoter ◽  
Deborah Cleveland ◽  
Donald Cohen ◽  
Mireseyed Mohit-Tabatabai ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document