Ensemble Deep-Learning-Based Prognostic and Prediction for Recurrence of Sporadic Odontogenic Keratocysts on Hematoxylin and Eosin Stained Pathological Images of Incisional Biopsies.

(1) Background: Odontogenic keratocysts (OKCs) are enigmatic developmental cysts that deserve special attention due to their heterogeneous appearance in histopathological characteristics and high recurrence rate. Despite several nomenclatures for classification, clinicians still confront challenges in its diagnosis and predicting its recurrence. This paper proposes an ensemble deep-learning-based prognostic and prediction algorithm, for the recurrence of sporadic odontogenic keratocysts, on hematoxylin and eosin stained pathological images of incisional biopsies before treatment. (2) Materials and Methods: In this study, we applied a deep-learning algorithm to an ensemble approach integrated with DenseNet-121, Inception-V3, and Inception-Resnet-V3 classifiers. Around 1660 hematoxylin and eosin stained pathologically annotated digital images of OKC-diagnosed (60) patients were supplied to train and predict recurrent OKCs. (3) Results: The presence of SEH (p = 0.004), an incomplete epithelial lining, (p = 0.023), and a corrugated surface (p = 0.049) were the most significant histological parameters distinguishing recurrent and non-recurrent OKCs. Amongst the classifiers, DenseNet-121 showed 93% accuracy in predicting recurrent OKCs. Furthermore, integrating and training the traditional ensemble model showed an accuracy of 95% and an AUC of 0.9872, with an execution time of 192.9 s. In comparison, our proposed model showed 97% accuracy with an execution time of 154.6 s. (4) Conclusions: Considering the outcome of our novel ensemble model, based on accuracy and execution time, the presented design could be embedded into a computer-aided design system for automation of risk stratification of odontogenic keratocysts.

Efficacy of Csaba stain to demonstrate mature and immature mast cells in oral inflammatory lesions: An in-vitro study.

Background: Mast cells (MCs) are immune cells of the myeloid lineage and are present in connective tissues throughout the body. Mastocytosis regulates many physiologic processes and affects the pathogenesis of allergic conditions, anaphylactic reactions, autoimmune disorders and leukemias. Toluidine blue is commonly employed as a special stain for MCs that uniformly imparts blue color to both immature and mature cells. Csaba stain that distinguishes mature from immature MCs has not been widely explored. However, its use in differentiating mature and immature cells has not been reported in the literature. The identification of mature and immature MCs may provide a major clue for the diagnosis of any unrecognized systemic pathologies. Objectives: To evaluate the staining efficacy of Csaba stain, toluidine blue and Leishman's stains in the identification of MCsTo compare the effectiveness of Csaba stain, toluidine blue and Leishman's stains to identify MCs in inflammatory pathologic lesions. Materials and Methods: Fifty sections of inflammatory lesions were subjected to Csaba stain, toluidine blue and Leishman's stains each for studying MCs. The staining efficacy of the three stains was compared for parameters such as homogeneity, specificity, staining intensity, granular staining property and differentiation between mature and immature cells. Results: The Csaba, toluidine blue and Leishman's stains showed statistically insignificant P = 0.50, 0.95, 0.29, 0.48 for homogeneity, specificity, staining intensity and granular staining property respectively, but Csaba stain showed statistically significant P = 0.0001* in differentiating mature from immature cells. Conclusion: Csaba stain is more effective in differentiating mature from immature MCs compared to the other special stains.

Behavioral and Psychosocial Risk Factors that Lead Individuals to Initiate and/or Maintain Betel Quid Chewing in Developed and Developing Countries: A Systematic Review.

BACKGROUND: Betel quid (BQ) is the fourth most commonly used psychoactive substance and its use is highly prevalent among southeast Asian countries due to the influence of psychosocial, behavioral, and environmental factors. As a result, even young children and women are becoming addicted and find it difficult to achieve long-term abstinence. Systematic research addressing the influence of behavioral and psychosocial factors on BQ chewing is scarce, hence pointing to the need for understanding the interplay of these factors to develop tailored intervention strategies for BQ cessation. OBJECTIVE: The objective of this systematic review is to assess various behavioral and psychosocial risk factors from pre-existing literature that lead individuals to initiate and/or maintain BQ chewing in developed and developing countries. MATERIALS AND METHODS: The electronic retrieval systems and databases PUBMED [MEDLINE], EMBASE, SCOPUS, WEB OF SCIENCE, GOOGLE SCHOLAR, and SCIENCE DIRECT were searched independently by two authors for relevant articles from January 2011 to July 2021 using combinations of keywords. Primary studies published in English focusing on the behavioral and psychosocial risk factors for BQ chewing were included. RESULTS: Out of the initial 264 articles searched, 12 articles met the selection criteria. Included studies addressed the influence of behavioral and psychosocial factors toward the initiation and/or maintenance of BQ chewing. Included studies reported that dependent BQ was not able to quit BQ chewing due to habituation, addiction, and withdrawal symptoms. Few social BQ chewers in Southeast Asian countries were not willing to initiate quitting as they considered AN as an important social and cultural identifier and claimed that they could not resist chewing in a peer group, and it has become part of their social life. CONCLUSION: In the future, studies should take into consideration behavioral and psychosocial risk factors, which are major barriers toward successful quitting. These factors should be integrated into areca nut cessation guidelines, and there is a need to develop more comprehensive culture-specific intervention approaches to achieve long-term abstinence.

Deep Learning-Based Microscopic Diagnosis of Odontogenic Keratocysts and Non-Keratocysts in Haematoxylin and Eosin-Stained Incisional Biopsies.

BACKGROUND: The goal of the study was to create a histopathology image classification automation system that could identify odontogenic keratocysts in hematoxylin and eosin-stained jaw cyst sections. METHODS: From 54 odontogenic keratocysts, 23 dentigerous cysts, and 20 radicular cysts, about 2657 microscopic pictures with 400× magnification were obtained. The images were annotated by a pathologist and categorized into epithelium, cystic lumen, and stroma of keratocysts and non-keratocysts. Preprocessing was performed in two steps; the first is data augmentation, as the Deep Learning techniques (DLT) improve their performance with increased data size. Secondly, the epithelial region was selected as the region of interest. RESULTS: Four experiments were conducted using the DLT. In the first, a pre-trained VGG16 was employed to classify after-image augmentation. In the second, DenseNet-169 was implemented for image classification on the augmented images. In the third, DenseNet-169 was trained on the two-step preprocessed images. In the last experiment, two and three results were averaged to obtain an accuracy of 93% on OKC and non-OKC images. CONCLUSIONS: The proposed algorithm may fit into the automation system of OKC and non-OKC diagnosis. Utmost care was taken in the manual process of image acquisition (minimum 28-30 images/slide at 40× magnification covering the entire stretch of epithelium and stromal component). Further, there is scope to improve the accuracy rate and make it human bias free by using a whole slide imaging scanner for image acquisition from slides.

A Histopathology-based Assessment of Biological Behavior in Oral Hyalinizing Extraosseous Lesions by Differential Stains.

AIM: The assessment of hyalinization to determine aggressive behavior in oral pathological lesions is a scarcely researched field that requires further exploration. The current study aims to predict the biological behavior of oral hyalinizing extraosseous lesions (OHEOL) by employing four differential stains with clinicopathologic correlation. MATERIALS AND METHODS: The study was performed on retrospectively diagnosed formalin-fixed paraffin-embedded cases of salivary gland tumors (SGTs) (n = 13), benign soft tissue (BST) lesions (n = 24), and oral submucous fibrosis (OSMF) (n = 53). The hematoxylin and eosin-stained sections were analyzed for the severity of hyalinization (SOH). Differential stains periodic acid Schiff (PAS), Alcian blue, safranin O, and picrosirius red with polarizing microscopy were used to assess the components of hyalinized tissue. The SOH was correlated with differential staining characteristics and clinicopathologic features to analyze possible correlation with aggressive potential in BST, advancement of disease in OSMF, and recurrence in SGT. RESULTS: Intensity of picrosirius red stain significantly correlated with SOH of SGTs (p = 0.044). The intensity of PAS stain (p = 0.040), picrosirius red polarizing greenish-yellow color (p = 0.002), and pattern of distribution of picrosirius red (p = 0.023) significantly correlated with recurrence of SGTs. The intensity of differential stains increased with the SOH in BST lesions indicating their correlation with SOH. The intensity (p = 0.008) and pattern (p = 0.010) of Alcian blue staining and intensity of safranin O stain (p = 0.003) significantly correlated with SOH in OSMF. Picrosirius red polarizing color reddish and yellowish red (p = 0.002) significantly correlated with SOH distinguishing early and advanced OSMF. CONCLUSION: Picrosirius red and PAS stains are reliable indicators of SOH and recurrence potential in SGT. Alcian blue, safranin O, and picrosirius red polarizing colors enable detection of SOH and accurately distinguish early from advanced OSMF. CLINICAL SIGNIFICANCE: SOH can be considered as a histological predictor of aggressive biologic behavior in OHEOL. These findings will result in appropriate management protocols.

A Histopathology-based Assessment of Biological Behavior in Oral Hyalinizing Odontogenic Tumors and Bone Lesions by Differential Stains.

AIM: Odontogenic tumors (OTs) and bone lesions of the oral cavity present diverse histological features and varying clinical behavior that makes predicting their biologic behavior difficult. The research undertaken in the current study aims to predict the biological behavior of oral hyalinizing odontogenic and bone lesions (OHO-BL) for the first time by employing four differential stains with clinicopathologic correlation. MATERIALS AND METHODS: The study was performed on retrospectively diagnosed formalin-fixed paraffin-embedded cases of OTs (n = 53) and bone lesions (n = 10). The severity of hyalinization (SOH) was assessed from stained tissue sections. Polarizing microscopy was used to analyze hyalinization in tissues stained with differential special stains, namely periodic acid-Schiff (PAS), Safranin-O, Alcian Blue, and Picrosirius red. SOH was also analyzed for possible correlation with recurrence and clinicopathologic correlation in OHO-BL. RESULTS: Intense staining was observed with PAS, Alcian Blue, and Safranin-O in OTs with increased SOH with a statistical significance. Polarizing greenish yellow color correlated significantly with the recurrence potential of the OT group. Recurrence in individual lesions of the OT group showed a statistically significant association with SOH. Such individual correlation was not observed in bone diseases. CONCLUSION: PAS, Alcian Blue, Safranin-O, and Picrosirius red are reliable stains to assess hyalinization in OHO-BL. Picrosirius red-polarizing microscopy is a dependable tool for identifying recurrent odontogenic lesions. CLINICAL SIGNIFICANCE: SOH can be considered a histological predictor of aggressive biologic behavior in oral hyalinizing odontogenic lesions that can enable the surgeon to arrive at an appropriate management protocol.

Sub-epithelial hyalinization, incomplete cystic lining, and corrugated surface could be a predictor of recurrence in Odontogenic Keratocysts.

BACKGROUND: Odontogenic Keratocysts (OKCs) are known for their rapid growth and tendency to invade the adjacent tissues. Its high recurrence rate (2.5%-62%) has attracted many kinds of research to identify new parameters to predict recurrence that would enable better treatment outcomes for such patients. The present study aims to correlate Sub-Epithelial Hyalinization (SEH) that has not been explored in an Asian population to date and other histopathologic features of OKC to its recurrence propensity. MATERIALS & METHODS: A total of 60 OKCs were analyzed for histopathologic correlation of thickness of lining, complete/incomplete lining, corrugated surface, ortho/para keratinization, intercellular edema, reversed polarity, basilar hyperplasia, the palisading arrangement of basal cells, presence/absence of rete pegs, folding of the epithelium, epithelial/connective tissue separation, SEH, basal offshoots, daughter cysts and inflammation with recurrence to arrive at the most significant histologic feature predicting recurrence. RESULTS: The most significant histologic parameter differentiating recurrent and non-recurrent OKCs was the presence of SEH (p = 0.004), incomplete lining epithelium (p â€‹= â€‹0.023), and a corrugated surface (p â€‹= â€‹0.049). Several other histologic parameters evaluated did not statistically correlate with recurrence, this can be attributed to the smaller sample size considered in the present study. CONCLUSION: SEH is a reliable histologic parameter to predict recurrence in OKCs. The presence of SEH is indicative of a higher recurrence potential in OKCs. Evaluation of histological parameters and their correlation with recurrence in OKCs on a larger sample size could validate the results of the current study undertaken and potentially unravel more insights on predicting recurrence. KEY MESSAGES: Sub-epithelial hyalinization is a significant feature for predicting recurrence in OKC.

Procedures and pitfalls in incisional biopsies of oral squamous cell carcinoma with respect to histopathological diagnosis.

This review has addressed the issues faced by a diagnostic pathologist during routine assessment of haematoxylin and eosin stained incisional biopsies from oral squamous cell carcinoma patients. Herein, the pragmatic means undertaken, has highlighted routinely faced problems & encounters determined at various levels as clinical, laboratory and diagnostic pitfalls, when possible, tips offered towards procedures and guidance. Also, dealt with subtypes of oral squamous cell carcinoma, differential diagnosis, and relevant prognostic indicators that can navigate the surgeon to take quick decisions. It speaks of the journey of biopsied material from the clinician to the laboratory until the generation of the final report. Although histopathological evaluation is a confirmatory tool for any clinically suspected lesion it mandates the co-operation of faculty from varied disciplines. The onus lies on a pathologist to establish standard protocols to oversee, audit the laboratory operating procedures from time and again. Technical errors and faults at the office desk doesn't come under the purview of this review.

Molecular pathways of oral cancer that predict prognosis and survival: A systematic review.

Several genes and pathways associated with oral squamous cell carcinoma (OSCC) are significant in terms of early detection and prognosis. The objective of this literature review is to evaluate the current research on molecular pathways and genes involved in oral cancer. Articles on the genes involved in oral cancer pathways were evaluated to identify potential biomarkers that can predict survival. In total, 36 articles were retrieved from internet databases, including EBSCO Host, Google Scholar, PubMed, and Science Direct, using the keywords "biomarker of oral cancer," "pathways of oral cancer," "genes involved in oral cancer," and "oral cancer pathways." A total of 36 studies related to OSCC were chosen. Most of the studies used cell lines, while others used archival tissues, few studies followed up the cases. Three major interlinked pathways found were the nuclear factor kappa B (NF-kB), PI3K-AKT, and Wnt pathways. The commonly mutated genes were cyclin D1 (CCND1), Rb, p53, FLJ10540, and TC21. The NF-kB, PI3K-AKT, and Wnt pathways are most frequently involved in the molecular pathogenesis of oral cancer. However, the CCND1, Rb, p53, FLJ10540, and TC21 genes were found to be more accurate in determining patients' overall survival. Polymerase chain reaction, immunohistochemistry, and immunoblotting were the commonly used detection methods.