Quantitative Risk Stratification of Oral Leukoplakia with Exfoliative Cytology

Abstract

Exfoliative cytology has been widely used for early diagnosis of oral squamous cell carcinoma (OSCC). Test outcome is reported as “negative”, “atypical” (defined as abnormal epithelial changes of uncertain diagnostic significance), and “positive” (defined as definitive cellular evidence of epithelial dysplasia or carcinoma). The major challenge is how to properly manage the “atypical” patients in order to diagnose OSCC early and prevent OSCC. In this study, we collected exfoliative cytology data, histopathology data, and clinical data of normal subjects (n=102), oral leukoplakia (OLK) patients (n=82), and OSCC patients (n=93), and developed a data analysis procedure for quantitative risk stratification of OLK patients. This procedure involving a step called expert-guided data transformation and reconstruction (EdTAR) which allows automatic data processing and reconstruction and reveals informative signals for subsequent risk stratification. Modern machine learning techniques were utilized to build statistical prediction models on the reconstructed data. Among the several models tested using resampling methods for parameter pruning and performance evaluation, Support Vector Machine (SVM) was found to be optimal with a high sensitivity (median>0.98) and specificity (median>0.99). With the SVM model, we constructed an oral cancer risk index (OCRI) which may potentially guide clinical follow-up of OLK patients. One OLK patient with an initial OCRI of 0.88 developed OSCC after 40 months of follow-up. In conclusion, we have developed a statistical method for qualitative risk stratification of OLK patients. This method may potentially improve cost-effectiveness of clinical follow-up of OLK patients, and help design clinical chemoprevention trial for high-risk populations.

Quantitative prediction of oral cancer risk in patients with oral leukoplakia

“…As a minimally invasive and inexpensive method, exfoliative cytology has long been used for qualitative detection of cervical cancer and oral cancer [ 20 ]. This approach has advantages over other methods mainly because cellular morphology tends to be relatively stable compared to molecular markers [ 10 ]. It has been well established that DNA aneuploidy could predict malignancy prior to histopathology [ 21 , 22 ].…”

“…The exfoliative cytology and histopathology were conducted in the same way as in our previous study [ 10 ]. In brief, exfoliative cells were collected by using Cervibrush (Motic, China) and stored in a fixative (Motic, China).…”

“…Unfortunately, this invasive approach depends on incisional biopsy and cannot be repeated during follow-up due to poor patient acceptance. Several other tools are also used to assess OLK lesions [ 10 ]: visual assessment of the physicochemical properties (e.g., toluidine blue staining, fluorescence spectroscopy) which is easy to use but less specific [ 11 – 13 ]; laboratory assessment of cellular markers (e.g., exfoliative cytology, micronucleus analysis) with higher sensitivity and specificity [ 14 – 17 ]; laboratory assessment of molecular markers (i.e., immunohistochemistry, gene microarray) which requires high-quality biopsy samples and are often quite expensive [ 18 ].…”

“…However, exfoliative cytology currently only provides qualitative assessment, instead of quantitative assessment, of cancer risk in OLK patients. In our previous study, we developed a statistical model and oral cancer risk index (OCRI) for quantitative risk of stratification of OLK patients [ 10 ]. At the time of sampling, we expected OCRI may inform us of OSCC which may be further validated by histopathology of incisional biopsy.…”

The role of exfoliative cytology and molecular biology in oral potentially malignant disorders

“…Recently, few authors have combined all the techniques mentioned above right from cellular detection of atypical cells to molecular methods described in this section of stratify the risk of oral leukoplakic patients using expert-guided data transformation and reconstruction and support vector machine. [41,42] Application of Raman spectroscopy in early detection of oral cancer using exfoliative cytology has also been recently reported. [43]…”