Search

Presepsin is a diagnostic and prognostic biomarker of sepsis; however, elevated presepsin levels have also been documented without sepsis. This study aims to retrospectively analyze the laboratory parameters and Sequential Organ Failure Assessment (SOFA) score affecting presepsin levels in 567 patients. Some patients with elevated presepsin levels exhibited renal dysfunction or elevation of biliary enzymes despite a low SOFA score. The univariate regression analysis revealed a close correlation between presepsin levels and SOFA score, serum creatinine (CRE), blood urea nitrogen, and biliary enzymes. In addition, a multivariate regression analysis revealed that SOFA score, alkaline phosphatase (ALP), and CRE independently affected presepsin levels significantly. The analysis of covariance (ANCOVA) revealed that presepsin levels were significantly higher in patients with hepatobiliary disease. Besides, we found that patients who presented with the dilatation of intra- or extrahepatic bile ducts and the elevation of ALP or total bilirubin exhibited remarkable high presepsin levels in the bile. Furthermore, the presepsin production in the liver’s Kupffer cells was established by immunostaining in patients who received surgical liver resection. Overall, this study elucidates that biliary enzymes’ elevation affects presepsin levels, presepsin exists in high concentrations in the bile, and is positive in Kupffer cells.

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.