No abstract

BackgroundToll-like receptors (TLRs) play an important role in innate immunity by sensing a variety of pathogens and inducing acquired immunity. To test our hypothesis that dysregulation of innate immune responses acts to trigger carcinogenesis, we studied the expression of TLR2 and 4 in sporadic human colorectal cancer tissue.MethodsIn specimens of cancerous and noncancerous colorectal tissue obtained at surgery, mRNA expression levels of TLR2 and 4 were quantified by TaqMan real-time polymerase chain reaction and compared between the two types of tissue. To confirm TLR2 and TLR4 protein expression levels, immunohistochemical analysis was performed using the same samples.ResultsTLR2 mRNA expression was significantly higher in cancerous tissue than in noncancerous tissue, while TLR4 mRNA expression did not differ significantly. Immunohistochemical analysis revealed stronger staining for TLR2 in cancerous mucosal epithelial cells than in noncancerous tissue. Staining for TLR4 in the lamina propria of the mucosa was equally weakly positive in noncancerous tissue and cancerous tissue. This TLR-specific difference in expression suggested that such expression does not only reflect a local inflammatory response to cancer infiltration, i.e., if this was the case, both TLR2 and 4 expression would probably be up-regulated. Our results suggest that TLR2 expression might be involved in sporadic colorectal carcinogenesis, whereas TLR4 is not.

Deep learning using convolutional neural networks (CNNs) is a distinguished tool for many image classification tasks. Due to its outstanding robustness and generalization, it is also expected to play a key role to facilitate advanced computer-aided diagnosis (CAD) for pathology images. However, the shortage of well-annotated pathology image data for training deep neural networks has become a major issue at present because of the high-cost annotation upon pathologist's professional observation. Faced with this problem, transfer learning techniques are generally used to reinforcing the capacity of deep neural networks. In order to further boost the performance of the state-of-the-art deep neural networks and alleviate insufficiency of well-annotated data, this paper presents a novel stepwise fine-tuning-based deep learning scheme for gastric pathology image classification and establishes a new type of target-correlative intermediate datasets. Our proposed scheme is deemed capable of making the deep neural network imitating the pathologist's perception manner and of acquiring pathology-related knowledge in advance, but with very limited extra cost in data annotation. The experiments are conducted with both well-annotated gastric pathology data and the proposed target-correlative intermediate data on several state-of-the-art deep neural networks. The results congruously demonstrate the feasibility and superiority of our proposed scheme for boosting the classification performance.

No abstract

No abstract