Convolutional neural networks for accurate real-time diagnosis of oral epithelial dysplasia and oral squamous cell carcinoma using high-resolution in vivo confocal microscopy.

Oral cancer detection is based on biopsy histopathology, however with digital microscopy imaging technology there is real potential for rapid multi-site imaging and simultaneous diagnostic analysis. Fifty-nine patients with oral mucosal abnormalities were imaged in vivo with a confocal laser endomicroscope using the contrast agents acriflavine and fluorescein for the detection of oral epithelial dysplasia and oral cancer. To analyse the 9168 images frames obtained, three tandem applied pre-trained Inception-V3 convolutional neural network (CNN) models were developed using transfer learning in the PyTorch framework.

AXIN2 is a non-redundant regulator of AXIN1 stability and β-catenin in colorectal cancer cells.

AXIN proteins are major components of the β-catenin destruction complex or degradasome, which limits β-catenin nuclear translocation and Wnt signalling activation at steady state. Schmidt et al. performed quantitative analysis of cellular AXIN protein levels in human colorectal cancer cells and revealed that AXIN2 plays a non-redundant role in regulating the total AXIN pool and Wnt/β-catenin signalling activity.

Complex IIa formation and ABC transporters determine sensitivity of OSCC to Smac mimetics.

Small molecule inhibitors of apoptosis proteins (IAPs) antagonists, known as Smac mimetics (SMs), activate non-canonical NF-κB and sensitize cancer cells to TNF-induced cell death. SMs are currently in phase III clinical trials for head and neck squamous cell carcinoma (HNSCC) after promising phase II trials. To explore the utility of SMs in oral squamous cell carcinoma (OSCC), we tested nine human OSCC cell lines and correlated SM sensitivity with both IAP mutation and expression levels.