Quantitative risk stratification of oral leukoplakia with exfoliative cytology

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.

Artificial Intelligence-based methods in head and neck cancer diagnosis: an overview

BACKGROUND

This paper reviews recent literature employing Artificial Intelligence/Machine Learning (AI/ML) methods for diagnostic evaluation of head and neck cancers (HNC) using automated image analysis.

METHODS

Electronic database searches using MEDLINE via OVID, EMBASE and Google Scholar were conducted to retrieve articles using AI/ML for diagnostic evaluation of HNC (2009-2020). No restrictions were placed on the AI/ML method or imaging modality used.

RESULTS

In total, 32 articles were identified. HNC sites included oral cavity (n = 16), nasopharynx (n = 3), oropharynx (n = 3), larynx (n = 2), salivary glands (n = 2), sinonasal (n = 1) and in five studies multiple sites were studied. Imaging modalities included histological (n = 9), radiological (n = 8), hyperspectral (n = 6), endoscopic/clinical (n = 5), infrared thermal (n = 1) and optical (n = 1). Clinicopathologic/genomic data were used in two studies. Traditional ML methods were employed in 22 studies (69%), deep learning (DL) in eight studies (25%) and a combination of these methods in two studies (6%).

CONCLUSIONS

There is an increasing volume of studies exploring the role of AI/ML to aid HNC detection using a range of imaging modalities. These methods can achieve high degrees of accuracy that can exceed the abilities of human judgement in making data predictions. Large-scale multi-centric prospective studies are required to aid deployment into clinical practice.

[Advances in the application of machine learning in maxillofacial cysts and tumors]

The application of artificial intelligence in medicine has gradually received attention along with its development. Many studies have shown that machine learning has a wide range of applications in stomatology, especially in the clinical diagnosis and treatment of maxillofacial cysts and tumors. This article reviews the application of machine learning in maxillofacial cyst and tumor to provide a new method for the diagnosis of oral and maxillofacial diseases.

V. A, Rana MH, Gurpur P, Skandarajah A, D’Ambrosio M, Ramanjinappa RD, Mohan SP, Raghavan N, Kandasarma U, N. S, Raghavan S, Hedne N, Koch F, Fletcher DA, Selvam S, Kollegal M, N. PB, Ladic L, Suresh A, Pandya HJ, Kuriakose MA. A smart tele-cytology point-of-care platform for oral cancer screening

Early detection of oral cancer necessitates a minimally invasive, tissue-specific diagnostic tool that facilitates screening/surveillance. Brush biopsy, though minimally invasive, demands skilled cyto-pathologist expertise. In this study, we explored the clinical utility/efficacy of a tele-cytology system in combination with Artificial Neural Network (ANN) based risk-stratification model for early detection of oral potentially malignant (OPML)/malignant lesion. A portable, automated tablet-based tele-cytology platform capable of digitization of cytology slides was evaluated for its efficacy in the detection of OPML/malignant lesions (n = 82) in comparison with conventional cytology and histology. Then, an image pre-processing algorithm was established to segregate cells, ANN was trained with images (n = 11,981) and a risk-stratification model developed. The specificity, sensitivity and accuracy of platform/ stratification model were computed, and agreement was examined using Kappa statistics. The tele-cytology platform, Cellscope, showed an overall accuracy of 84–86% with no difference between tele-cytology and conventional cytology in detection of oral lesions (kappa, 0.67–0.72). However, OPML could be detected with low sensitivity (18%) in accordance with the limitations of conventional cytology. The integration of image processing and development of an ANN-based risk stratification model improved the detection sensitivity of malignant lesions (93%) and high grade OPML (73%), thereby increasing the overall accuracy by 30%. Tele-cytology integrated with the risk stratification model, a novel strategy established in this study, can be an invaluable Point-of-Care (PoC) tool for early detection/screening in oral cancer. This study hence establishes the applicability of tele-cytology for accurate, remote diagnosis and use of automated ANN-based analysis in improving its efficacy.

Current evidence on DNA aneuploidy cytology in noninvasive detection of oral cancer

DNA-aneuploidy cytology as a promising noninvasive tool in diagnosing oral precancer and cancer has been proposed in 2015. In this letter, we identified 9 studies on DNA aneuploidy cytology with special emphasis on using fresh tissue sample in detection of oral precancer and cancer. Evidence was updated as follows, for detection of OSCC in general oral lesions, the pooled sensitivity and specificity was 84.8 and 99.0 respectively; for discrimination of dysplasia and OSCC form oral lesions, the sensitivity and specificity was 75.7 and 76.8 respectively. On the whole, current evidence on the theme is not robust, and multicenter prospective studies are needed to consolidate the evidence.

Variants in FAT1 and COL9A1 genes in male population with or without substance use to assess the risk factors for oral malignancy

A number of genetic variants were suggested to be associated with oral malignancy, few variants can be replicated. The aim of this study was to identify significant variants that enhanced personal risk prediction for oral malignancy. A total of 360 patients diagnosed with oral squamous cell carcinoma, 486 controls and 17 newly diagnosed patients with OPMD including leukoplakia or oral submucous fibrosis were recruited. Fifteen tagSNPs which were derived from somatic mutations were genotyped and examined in associations with the occurrence of oral malignancy. Environmental variables along with the SNPs data were used to developed risk predictive models for oral malignancy occurrence. The stepwise model analysis was conducted to fit the best model in an economically efficient way. Two tagSNPs, rs28647489 in FAT1 gene and rs550675 in COL9A1 gene, were significantly associated with the risk of oral malignancy. The sensitivity and specificity were 85.7% and 85.5%, respectively (area under the receiver operating characteristic curve (AUC) was 0.91) for predicting oral squamous cell carcinoma occurrence with the combined genetic variants, betel-quid, alcohol and age. The AUC for OPMD was only 0.69. The predictive probability of squamous cell carcinoma occurrence for genetic risk score without substance use increased from 10% up to 43%; with substance use increased from 73% up to 92%. Genetic variants with or without substance use may enhance risk prediction for oral malignancy occurrence in male population. The prediction model may be useful as a clinical index for oral malignancy occurrence and its risk assessments.

Quantitative prediction of oral cancer risk in patients with oral leukoplakia

Exfoliative cytology has been widely used for early diagnosis of oral squamous cell carcinoma. We have developed an oral cancer risk index using DNA index value to quantitatively assess cancer risk in patients with oral leukoplakia, but with limited success. In order to improve the performance of the risk index, we collected exfoliative cytology, histopathology, and clinical follow-up data from two independent cohorts of normal, leukoplakia and cancer subjects (training set and validation set). Peaks were defined on the basis of first derivatives with positives, and modern machine learning techniques were utilized to build statistical prediction models on the reconstructed data. Random forest was found to be the best model with high sensitivity (100%) and specificity (99.2%). Using the Peaks-Random Forest model, we constructed an index (OCRI2) as a quantitative measurement of cancer risk. Among 11 leukoplakia patients with an OCRI2 over 0.5, 4 (36.4%) developed cancer during follow-up (23 ± 20 months), whereas 3 (5.3%) of 57 leukoplakia patients with an OCRI2 less than 0.5 developed cancer (32 ± 31 months). OCRI2 is better than other methods in predicting oral squamous cell carcinoma during follow-up. In conclusion, we have developed an exfoliative cytology-based method for quantitative prediction of cancer risk in patients with oral leukoplakia.

Cytological study of DNA content and nuclear morphometric analysis for aid in the diagnosis of high-grade dysplasia within oral leukoplakia

OBJECTIVE

To quantitatively examine the DNA content and nuclear morphometric status of oral leukoplakia (OL) and investigate its association with the degree of dysplasia in a cytologic study.

STUDY DESIGN

Oral cytobrush biopsy was carried out to obtain exfoliative epithelial cells from lesions before scalpel biopsy at the same location in a blinded series of 70 patients with OL. Analysis of nuclear morphometry and DNA content status using image cytometry was performed with oral smears stained with the Feulgen-thionin method.

RESULTS

Nuclear morphometric analysis revealed significant differences in DNA content amount, DNA index, nuclear area, nuclear radius, nuclear intensity, sphericity, entropy, and fractal dimension (all P < .01) between low-grade and high-grade dysplasia. DNA content analysis identified 34 patients with OL (48.6%) with DNA content abnormality. Nonhomogeneous lesion (P = .018) and high-grade dysplasia (P = .008) were significantly associated with abnormal DNA content. Importantly, the positive correlation between the degree of oral dysplasia and DNA content status was significant (P = .004, correlation coefficient = 0.342).

CONCLUSION

Cytology analysis of DNA content and nuclear morphometric status using image cytometry may support their use as a screening and monitoring tool for OL progression.