Deep multiple instance learning versus conventional deep single instance learning for interpretable oral cancer detection.

The current medical standard for setting an oral cancer (OC) diagnosis is histological examination of a tissue sample taken from the oral cavity. This process is time-consuming and more invasive than an alternative approach of acquiring a brush sample followed by cytological analysis. Using a microscope, skilled cytotechnologists are able to detect changes due to malignancy; however, introducing this approach into clinical routine is associated with challenges such as a lack of resources and experts. To design a trustworthy OC detection system that can assist cytotechnologists, we are interested in deep learning based methods that can reliably detect cancer, given only per-patient labels (thereby minimizing annotation bias), and also provide information regarding which cells are most relevant for the diagnosis (thereby enabling supervision and understanding). In this study, we perform a comparison of two approaches suitable for OC detection and interpretation: (i) conventional single instance learning (SIL) approach and (ii) a modern multiple instance learning (MIL) method. To facilitate systematic evaluation of the considered approaches, we, in addition to a real OC dataset with patient-level ground truth annotations, also introduce a synthetic dataset-PAP-QMNIST. This dataset shares several properties of OC data, such as image size and large and varied number of instances per bag, and may therefore act as a proxy model of a real OC dataset, while, in contrast to OC data, it offers reliable per-instance ground truth, as defined by design. PAP-QMNIST has the additional advantage of being visually interpretable for non-experts, which simplifies analysis of the behavior of methods. For both OC and PAP-QMNIST data, we evaluate performance of the methods utilizing three different neural network architectures. Our study indicates, somewhat surprisingly, that on both synthetic and real data, the performance of the SIL approach is better or equal to the performance of the MIL approach. Visual examination by cytotechnologist indicates that the methods manage to identify cells which deviate from normality, including malignant cells as well as those suspicious for dysplasia. We share the code as open source.

Dental hygienists and dentists as providers of brush biopsies for oral mucosa screening.

BACKGROUND: Oral cancer is a severe and potentially fatal disease usually starting in the squamous epithelium lining the oral cavity. Together with oropharyngeal carcinoma, it is the fifth to sixth most common malignancy worldwide. To limit the increase in the global oral cancer incidence over the past two decades, the World Health Assembly adopted a resolution urging member states to integrate preventive measures such as engagement and training of dental personnel in screening, early diagnosis, and treatment into their national cancer control programs. AIM: The aim of this study was to investigate if dental hygienists (DHs) and dentists (Ds) in general dental practice care can be entrusted to perform brush sampling of oral potentially malignant disorders (OPMDs), and to evaluate their level of comfort in performing brush biopsies. METHODS: Participants were five DHs and five Ds who received one day of theoretical and clinical training in oral pathology to identify OPMDs (leukoplakia [LP], erythroplakia [EP], and oral lichen planus [OLP]), and perform brush sampling for PAP cytology and high-risk human papillomavirus (hrHPV) analysis. RESULTS: Out of 222 collected samples, 215 were adequate for morphological assessment and hrHPV analysis. All the participants agreed that sample collection can be incorporated in DHs and Ds routine clinical duties, and most of them reported that sample collection and processing was easy/quite easy. CONCLUSION: Dentists and DHs are capable of collecting satisfactory material for cytology and hrHPV analysis. All the participating DHs and Ds were of the opinion that brush sampling could be handled routinely by DHs and Ds in GDP.

Integrative meta-analysis of gene expression profiles identifies FEN1 and ENDOU as potential diagnostic biomarkers for cervical squamous cell carcinoma.

Cervical carcinoma is a global public health burden. Given that it is usually asymptomatic at potentially curative stages, the development of clinically accurate tests is critical for early detection and individual risk stratification. The present study performed an integrative meta-analysis of the transcriptomes from 10 cervical carcinoma cohorts, with the aim of identifying biomarkers that are associated with malignant transformation of cervical epithelium, and establish their clinical applicability. From among the top ranked differentially expressed genes, flap structure-specific endonuclease 1 (FEN1) and poly (U)-specific endoribonuclease (ENDOU) were selected for further validation, and their clinical applicability was assessed using immunohistochemically stained microarrays comprising 110 tissue cores, using p16 and Ki67 staining as the comparator tests. The results demonstrated that FEN1 expression was significantly upregulated in 65% of tumor specimens (P=0.0001), with no detectable expression in the non-tumor tissues. Furthermore, its expression was significantly associated with Ki67 staining in tumor samples (P<0.0001), but no association was observed with p16 expression or the presence of human papilloma virus types 16/18, patient age, tumor grade or stage. FEN1 staining demonstrated lower sensitivity than p16 (69.3 vs. 96.8%) and Ki67 (69.3 vs. 76.3%); however, the specificity was identical to p16 and higher than that of Ki67 (100 vs. 71.4%).ENDOU staining was consistent with the microarray results, demonstrating 1% positivity in tumors and 40% positivity in non-tumor tissues. Gene set enrichment analysis of cervical tumors overexpressing FEN1 revealed its association with enhanced growth factor signaling, immune response inhibition and extracellular matrix remodeling, whereas tumors with low ENDOU expression exhibited inhibition of epithelial development and differentiation processes. Taken together, the results of the present study demonstrate the feasibility of the integrative meta-analysis approach to identify relevant biomarkers associated with cervical carcinogenesis. Thus, FEN1 and ENDOU may be useful diagnostic biomarkers for squamous cervical carcinoma. However, further studies are required to determine their diagnostic performance in larger patient cohorts and validate the results presented here.

Loss of Serglycin Promotes Primary Tumor Growth and Vessel Functionality in the RIP1-Tag2 Mouse Model for Spontaneous Insulinoma Formation.

The serglycin proteoglycan is mainly expressed by hematopoietic cells where the major function is to retain the content of storage granules and vesicles. In recent years, expression of serglycin has also been found in different forms of human malignancies and a high serglycin expression level has been correlated with a more migratory and invasive phenotype in the case of breast cancer and nasopharyngeal carcinoma. Serglycin has also been implicated in the development of the tumor vasculature in multiple myeloma and hepatocellular carcinoma where reduced expression of serglycin was correlated with a less extensive vasculature. To further investigate the contribution of serglycin to tumor development, we have used the immunocompetent RIP1-Tag2 mouse model of spontaneous insulinoma formation crossed into serglycin deficient mice. For the first time we show that serglycin-deficiency affects orthotopic primary tumor growth and tumor vascular functionality of late stage carcinomas. RIP1-Tag2 mice that lack serglycin develop larger tumors with a higher proliferative activity but unaltered apoptosis compared to normal RIP1-Tag2 mice. The absence of serglycin also enhances the tumor vessel functionality, which is better perfused than in tumors from serglycin wild type mice. The presence of the pro-angiogenic modulators vascular endothelial growth factor and hepatocyte growth factor were decreased in the serglycin deficient mice which suggests a less pro-angiogenic environment in the tumors of these animals. Taken together, we conclude that serglycin affects multiple aspects of spontaneous tumor formation, which strengthens the theory that serglycin acts as an important mediator in the formation and progression of tumors.

TNF stimulation induces VHL overexpression and impairs angiogenic potential in skeletal muscle myocytes.

Decreased skeletal muscle capillarization is considered to significantly contribute to the development of pulmonary cachexia syndrome (PCS) and progressive muscle wasting in several chronic inflammatory diseases, including chronic obstructive pulmonary disease (COPD). It is unclear to which extent the concurrent presence of systemic inflammation contributes to decreased skeletal muscle capillarization under these conditions. The present study was designed to examine in vitro the effects of the pro-inflammatory cytokine, tumor necrosis factor (TNF), on the regulation of hypoxia-angiogenesis signal transduction and capillarization in skeletal muscles. For this purpose, fully differentiated C2C12 skeletal muscle myocytes were stimulated with TNF and maintained under normoxic or hypoxic conditions. The expression levels of the putative elements of the hypoxia-angiogenesis signaling cascade were examined using qPCR, western blot analysis and immunofluorescence. Under normoxic conditinos, TNF stimulation increased the protein expression of anti-angiogenic von-Hippel Lindau (VHL), prolyl hydroxylase (PHD)2 and ubiquitin conjugating enzyme 2D1 (Ube2D1), as well as the total ubiquitin content in the skeletal muscle myocytes. By contrast, the expression levels of hypoxia-inducible factor 1­α (HIF1-α) and those of its transcriptional targets, vascular endothelial growth factor (VEGF)A and glucose transporter 1 (Glut1), were markedly reduced. In addition, hypoxia increased the expression of the VHL transcript and further elevated the VHL protein expression levels in C2C12 myocytes following TNF stimulation. Consequently, an impaired angiogenic potential was observed in the TNF-stimulated myocytes during hypoxia. In conclusion, TNF increases VHL expression and disturbs hypoxia-angiogenesis signal transduction in skeletal muscle myocytes. The current findings provide a mechanism linking systemic inflammation and impaired angiogenesis in skeletal muscle. This is particularly relevant to further understanding the mechanisms mediating muscle wasting and cachexia in patients with chronic inflammatory diseases, such as COPD.

The periodontal pathogen Porphyromonas gingivalis changes the gene expression in vascular smooth muscle cells involving the TGFbeta/Notch signalling pathway and increased cell proliferation.

BACKGROUND: Porphyromonas gingivalis is a gram-negative bacterium that causes destructive chronic periodontitis. In addition, this bacterium is also involved in the development of cardiovascular disease. The aim of this study was to investigate the effects of P. gingivalis infection on gene and protein expression in human aortic smooth muscle cells (AoSMCs) and its relation to cellular function. RESULTS: AoSMCs were exposed to viable P. gingivalis for 24 h, whereafter confocal fluorescence microscopy was used to study P. gingivalis invasion of AoSMCs. AoSMCs proliferation was evaluated by neutral red assay. Human genome microarray, western blot and ELISA were used to investigate how P. gingivalis changes the gene and protein expression of AoSMCs. We found that viable P. gingivalis invades AoSMCs, disrupts stress fiber structures and significantly increases cell proliferation. Microarray results showed that, a total of 982 genes were identified as differentially expressed with the threshold log2 fold change > |1| (adjust p-value <0.05). Using bioinformatic data mining, we demonstrated that up-regulated genes are enriched in gene ontology function of positive control of cell proliferation and down-regulated genes are enriched in the function of negative control of cell proliferation. The results from pathway analysis revealed that all the genes belonging to these two categories induced by P. gingivalis were enriched in 25 pathways, including genes of Notch and TGF-beta pathways. CONCLUSIONS: This study demonstrates that P. gingivalis is able to invade AoSMCs and stimulate their proliferation. The activation of TGF-beta and Notch signaling pathways may be involved in the bacteria-mediated proliferation of AoSMCs. These findings further support the association between periodontitis and cardiovascular diseases.

Exposure to cigarette smoke induces overexpression of von Hippel-Lindau tumor suppressor in mouse skeletal muscle.

Cigarette smoke (CS) is a well-established risk factor in the development of chronic obstructive pulmonary disease (COPD). In contrast, the extent to which CS exposure contributes to the development of the systemic manifestations of COPD, such as skeletal muscle dysfunction and wasting, remains largely unknown. Decreased skeletal muscle capillarization has been previously reported in early stages of COPD and might play an important role in the development of COPD-associated skeletal muscle abnormalities. To investigate the effects of chronic CS exposure on skeletal muscle capillarization and exercise tolerance, a mouse model of CS exposure was used. The 129/SvJ mice were exposed to CS for 6 mo, and the expression of putative elements of the hypoxia-angiogenic signaling cascade as well as muscle capillarization were studied. Additionally, functional tests assessing exercise tolerance/endurance were performed in mice. Compared with controls, skeletal muscles from CS-exposed mice exhibited significantly enhanced expression of von Hippel-Lindau tumor suppressor (VHL), ubiquitin-conjugating enzyme E2D1 (UBE2D1), and prolyl hydroxylase-2 (PHD2). In contrast, hypoxia-inducible factor-1α (HIF-1α) and vascular endothelial growth factor (VEGF) expression was reduced. Furthermore, reduced muscle fiber cross-sectional area, decreased skeletal muscle capillarization, and reduced exercise tolerance were also observed in CS-exposed animals. Taken together, the current results provide evidence linking chronic CS exposure and induction of VHL expression in skeletal muscles leading toward impaired hypoxia-angiogenesis signal transduction, reduced muscle fiber cross-sectional area, and decreased exercise tolerance.