Liver cancer is one of the world's largest causes of death to humans. It is a difficult task and time consuming to identify the cancer tissue manually in the present scenario. The segmentation of liver lesions in CT images can be used to assess the tumor load, plan treatments predict, and monitor the clinical response. In this paper, the Hybridized Fully Convolutional Neural Network (HFCNN) has been proposed for liver tumor segmentation, which has been modeled mathematically to resolve the current issue of liver cancer. For semantic segmentation, HFCNN has been used as a powerful tool for liver cancer analysis. Whereas the CT-based lesion-type definition defines the diagnosis and therapeutic strategy, the distinction between cancer and non-cancer lesions is crucial. It demands highly qualified experience, expertise, and resources. However, a deep end-to-end learning approach to help discrimination in abdominal CT images of the liver between liver metastases of colorectal cancer and benign cysts has been analyzed. Our method includes the successful extraction of features from Inception combined with residual and pre-trained weights. Feature maps have been consistent with the original image voxel features, and The importance of features seemed to represent the most relevant imaging criteria for every class. This deep learning system shows the concept of illumination portions of the decision-making process of a pre-trained deep neural network, through an analysis of inner layers and the description of features that lead to predictions.

Cancer cells can escape antitumor immune responses by exploiting inhibitory immune checkpoints. Immune checkpoint therapy, mainly including anti-CTLA-4 therapy and anti-PD-1/PD-L1 therapy, can enhance antitumor immune responses by blocking the inhibitory signals of the immune system. This therapy has produced clinical advances in a fraction of patients. Deeper insight into the tumor microenvironment and immune checkpoint inhibitors will improve this therapy. Here, we review immune checkpoint inhibitors that prevent tumor immune escape and recent clinical studies of immune checkpoint therapy. We also compare the efficacy of different combination immunotherapies, describe how the relationship between the gut microbiome and immune system can determine the therapeutic outcomes for immune checkpoint inhibitors and introduce several novel immune checkpoints that are potential targets for antitumor immunotherapy in the future.

Kidney-type glutaminase (GLS1) plays a significant role in tumor metabolism. Our recent studies demonstrated that GLS1 was aberrantly expressed in hepatocellular carcinoma (HCC) and facilitated tumor progression. However, the roles of GLS1 in intrahepatic cholangiocarcinoma (ICC) remain largely unknown. Thus, the aim of this study was to evaluate the expression and clinical significance of GLS1 in ICC. For this purpose, combined data from the Oncomine database with those of immunohistochemistry were used to determine the expression levels of GLS1 in cancerous and non-cancerous tissues. Second, a wound-healing assay and Transwell assay were used to observe the effects of the knockdown and overexpression of GLS1 on the invasion and migration of ICC cells. We examined the associations between the expression of GLS1 and epithelial-mesenchymal transition (EMT)-related markers by western blot analysis. Finally, we examined the associations between GLS1 levels and clinicopathological factors or patient prognosis. The results revealed that GLS1 was overexpressed in different digestive system tumors, including ICC, and that GLS1 expression in ICC tissue was higher than that in peritumoral tissue. The overexpression of GLS1 in RBE cells induced metastasis and invasion. Moreover, the EMT-related markers, E-cadherin and Vimentin, were regulated by GLS1 in ICC cells. By contrast, the knockdown of GLS1 expression in QBC939 cells yielded opposite results. Clinically, a high expression of GLS1 in ICC samples negatively correlated with E-cadherin expression and positively correlated with Vimentin expression. GLS1 protein expression was associated with tumor differentiation (P=0.001) and lymphatic metastasis (P=0.029). Importantly, patients with a high GLS1 expression had a poorer overall survival (OS) and a shorter time to recurrence than patients with a low GLS1 expression. Multivariate analysis indicated that GLS1 expression was an independent prognostic indicator. On the whole, the findings of this study demonstrated that GLS1 is an independent prognostic biomarker of ICC. GLS1 facilitates ICC progression and may thus prove to be a therapeutic target in ICC.

Background Surgical resection is the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC) and the survival of patients after radical resection is closely related to relapse. We aimed to develop models to predict the risk of relapse using machine learning methods based on multiple clinical parameters. Methods Data were collected and analysed of 262 PDAC patients who underwent radical resection at 3 institutions between 2013 and 2017, with 183 from one institution as a training set, 79 from the other 2 institution as a validation set. We developed and compared several predictive models to predict 1- and 2-year relapse risk using machine learning approaches. Results Machine learning techniques were superior to conventional regression-based analyses in predicting risk of relapse of PDAC after radical resection. Among them, the random forest (RF) outperformed other methods in the training set. The highest accuracy and area under the receiver operating characteristic curve (AUROC) for predicting 1-year relapse risk with RF were 78.4% and 0.834, respectively, and for 2-year relapse risk were 95.1% and 0.998. However, the support vector machine (SVM) model showed better performance than the others for predicting 1-year relapse risk in the validation set. And the k neighbor algorithm (KNN) model achieved the highest accuracy and AUROC for predicting 2-year relapse risk. Conclusions By machine learning, this study has developed and validated comprehensive models integrating clinicopathological characteristics to predict the relapse risk of PDAC after radical resection which will guide the development of personalized surveillance programs after surgery.

Background: Pancreatic cancer (PC) was regarded as the 4th principal cause of cancerrelated fatalities in the United States and patients usually suffered from severe nutrition deficiency, muscle wasting, as well as bone loss. In our previous research, we have found that PC-derived exosomes potentially initiate insulin resistance in skeletal muscle cells. However, the role of exosomes in the PC-related bone loss remains unknown. Methods: The effect of PC-derived exosomes on the osteoclast differentiation and femoral bone structure in the orthotopic xenograft mouse model were investigated. MiRNA expression profiles were detected and a dual luciferase experiment was conducted to identify the direct target of miRNA. Results: Our data showed that PC-derived exosomes significantly induced osteoclast differentiation and increased expression of NFAT2, TRAP, CTSK and MMP-9. The bone volume fraction and trabecular thickness of femur significantly reduced in osteoporotic model. Microarray analyses and luciferase reporter assay showed that the process was, at least partially, mediated by the miR-125a-5p/TNFRSF1B signaling pathways. Conclusion:According to the results, novel insights have been claimed the effect of exosomes derived from PC on bone deterioration and explained correlation between PC and cancer-related bone loss.