Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study

Background: Ex vivo fluorescent confocal microscopy (FCM) is a novel and effective method for a fast-automatized histological tissue examination. In contrast, conventional diagnostic methods are primarily based on the skills of the histopathologist. In this study, we investigated the potential of convolutional neural networks (CNNs) for automatized classification of oral squamous cell carcinoma via ex vivo FCM imaging for the first time. Material and Methods: Tissue samples from 20 patients were collected, scanned with an ex vivo confocal microscope immediately after resection, and investigated histopathologically. A CNN architecture (MobileNet) was trained and tested for accuracy. Results: The model achieved a sensitivity of 0.47 and specificity of 0.96 in the automated classification of cancerous tissue in our study. Conclusion: In this preliminary work, we trained a CNN model on a limited number of ex vivo FCM images and obtained promising results in the automated classification of cancerous tissue. Further studies using large sample sizes are warranted to introduce this technology into clinics.

miRNA-3651: a Diagnostic Marker in Oral Squamous Cell Carcinoma?

Background and aim: microRNAs are a group of small non-coding single-stranded RNAs that control post-transcriptional gene expression. They can act as oncogenes or tumor suppressors by amplifying or preventing the expression of certain genes. present study was conducted to assess the expression of miRNA-3651 in paraffin blocks of oral squamous cell carcinoma (OSCC) cells using qRT-PCR method in Islamic Azad university, dental branch of Tehran in 1399.Material and methods: This case-control study was conducted on 20 paraffin blocks of irritation fibroma (IF) as control group and 20 paraffin blocks of patients with oral squamous cell carcinoma as case group. After RNA extraction, qRT-PCR was performed. all experiments were repeated 3 times for each sample. Eventually the data were analyzed by SPSS 24 statistics software. Differences in miRNA expression levels between the two groups were compared using the independent samples t-test. In order to evaluate the correlation between mean levels of miRNA-3651 marker and different variables (grade, age and sex of patients), Kruskal-Wallis test, Pearson's correlation coefficient test and independent samples t-test were used, respectively.Results: The results showed that the mean expression of this biomarker method was 10.15± 5.44 rpm in normal tissue and 8.11± 1.57 rpm in cancerous tissue. Despite the lower expression of miRNA-3651 in cancerous tissue samples than normal samples, this decrease was not statistically significant (P> 0.05). There was no significant difference between the mean level of miRNA-3651 marker and different grades, age and sex of patients (p> 0.05).Conclusion: In the end, it seems that the evaluation of changes in the expression of miRNAs such as miRNA-3651, can be a minimally invasive method, in early detection and screening of patients with OSCC. Decreased expression of miRNA-3651 marker in cancerous tissue compared to normal tissue indicates the importance of these biomarkers, including miRNA-3651 in the diagnosis of oral cancer, and the researchers of this project suggest further and broader investigations on the mechanism of action and signaling cascades associated with this marker in oral cancer.

DNA Methylation Status of RETN and ADIPOQ Genes in Sporadic Colon Cancer

Background: Colon cancer develops through a complex process that involves epigenetic alterations. Compelling evidence has been achieved that adipocytokines link obesity with colon cancer progression Therefore, understanding the epigenetic modifications in adipokine genes might help in clarifying their role in colon cancer pathogenesis. The aim of the present project was to study the DNA methylation status of RETN and ADIPOQ genes in sporadic colon cancer patients. Methods: 70 cancerous colon tissue and adjacent paired non-cancerous tissue was used to determine the DNA methylation status using methylation-specific polymerase chain reaction (MS-PCR) assay. Quantitative real-time PCR (qRT-PCR) was used to determine the expression level of RETN and ADIPOQ genes. Results: In colon cancer tissues, the CpG sites in the three selected promoter regions of ADIPOQ and RETN were hypermethylated in all samples. DNA methylation level at the CpG sites in exon one of the RETN gene exhibited a lower level in the non-cancerous tissue compared to the cancerous tissue and paired blood samples. The RETN mRNA was upregulated. Conclusion: We postulate that DNA methylation status at the CpG sites in exon one of the RETN gene might help uncover cancer signatures in sporadic colon cancer and may be used as a biomarker. The upregulation of the RETN mRNA level might play a role in sporadic colon cancer tumorigenesis.

Characteristic and Interplay of Esophageal Microbiota in Esophageal Squamous Cell Carcinoma

Background: Esophageal squamous cell carcinoma(ESCC) is severe cancer in the world. The role of esophageal microbiota for ESCC is still uncertain. In the current study, 120 paired tissues from ESCC patients were collected, and 16s rRNA sequencing was performed to explore the esophageal microbiota. Results: The present investigation shows that the diversity and composition of the microbiota in ESCC cancerous tissues and para-cancerous tissues is significantly different, this variation between subjects beta diversity mainly explained by regions and sampling seasons. Species R.Mucilaginosa, P.Endodontalis, unclassified species in genus Leptotrichia, genus Phyllobacterium, and genus Sphingomonas were enriched in cancerous tissue. On the other hand, class Bacilli, N.Subflava, H.Pylori, A.Parahaemolyticus, A.Rhizosphaerae, unclassified species in genus Campylobacter and genus Haemophilus were increased in para-cancerous tissue. Compared with the co-occurrence network in cancerous tissue, a denser and more complex association network was formed in para-cancerous tissue. Moreover, the above differential taxa also participated in both co-occurrence network but played quite different roles. Finally, the functional association analyses revealed the altered signaling pathways in ESCCs were correlated to esophageal microbiota. Conclusion: Compared with para-cancerous tissues, microbiota in cancerous tissues showed significant differences in diversity and composition. The alterations in microbial co-occurrence network and functional pathways in ESCC tissues may be involved in carcinogenesis and the maintenance of local microenvironment for ESCC. These discoveries of the esophageal microbiota for ESCC patients may contribute to the etiology for ESCC prevention, diagnosis, early intervention, and treatment.