BACKGROUND Efforts should be made to develop a deep-learning diagnosis system to distinguish pancreatic cancer from benign tissue due to the high morbidity of pancreatic cancer. AIM To identify pancreatic cancer in computed tomography (CT) images automatically by constructing a convolutional neural network (CNN) classifier. METHODS A CNN model was constructed using a dataset of 3494 CT images obtained from 222 patients with pathologically confirmed pancreatic cancer and 3751 CT images from 190 patients with normal pancreas from June 2017 to June 2018. We established three datasets from these images according to the image phases, evaluated the approach in terms of binary classification ( i.e ., cancer or not) and ternary classification ( i.e ., no cancer, cancer at tail/body, cancer at head/neck of the pancreas) using 10-fold cross validation, and measured the effectiveness of the model with regard to the accuracy, sensitivity, and specificity. RESULTS The overall diagnostic accuracy of the trained binary classifier was 95.47%, 95.76%, 95.15% on the plain scan, arterial phase, and venous phase, respectively. The sensitivity was 91.58%, 94.08%, 92.28% on three phases, with no significant differences ( χ 2 = 0.914, P = 0.633). Considering that the plain phase had same sensitivity, easier access, and lower radiation compared with arterial phase and venous phase , it is more sufficient for the binary classifier. Its accuracy on plain scans was 95.47%, sensitivity was 91.58%, and specificity was 98.27%. The CNN and board-certified gastroenterologists achieved higher accuracies than trainees on plain scan diagnosis ( χ 2 = 21.534, P < 0.001; χ 2 = 9.524, P < 0.05; respectively). However, the difference between CNN and gastroenterologists was not significant ( χ 2 = 0.759, P = 0.384). In the trained ternary classifier, the overall diagnostic accuracy of the ternary classifier CNN was 82.06%, 79.06%, and 78.80% on plain phase, arterial phase, and venous phase, respectively. The sensitivity scores for detecting cancers in the tail were 52.51%, 41.10% and, 36.03%, while sensitivity for cancers in the head was 46.21%, 85.24% and 72.87% on three phases, respectively. Difference in sensitivity for cancers in the head among the three phases was significant ( χ 2 = 16.651, P < 0.001), with arterial phase having the highest sensitivity. CONCLUSION We proposed a deep learning-based pancreatic cancer classifier trained on medium-sized datasets of CT images. It was suitable for screening purposes in pancreatic ...
Background and aimsProstaglandin E receptor 2 (EP2) is an immune modulatory molecule that regulates the balance of immunity. Here we investigated the role of EP2 in immune dysregulation in patients with acute-on-chronic liver failure (ACLF).MethodsPlasma Progstaglandin E2 (PGE2) levels and EP2 expression on immune cells were determined in blood samples collected from patients with chronic hepatitis B related ACLF(HB-ACLF), patients with chronic hepatitis B (CHB), acute decompensated cirrhosis without ACLF (AD) and healthy controls (HC). Cytokine production, bacterial phagocytosis and reactive oxygen species (ROS) production were detected to explore the role of EP2 in regulating immune cell functions.ResultsThe plasma PGE2 levels were increased and EP2 expression on CD8+ T cells was decreased in HB-ACLF compared with those in controls. The levels of PGE2 and EP2 were associated with systemic inflammation and disease severity. Small molecular chemicals against EP2 increased both cytokine secretion in PBMCs and ROS production in neutrophils and monocytes, but decreased monocytic phagocytosis. By contrast, an EP2-selective agonist reduced the production of a series of cytokines in PBMCs, but increased G-CSF.ConclusionAltered PGE2-EP2 augmented the excessive inflammation of innate and adaptive immune cells in response to LPS or E. coli in HB-ACLF. EP2 might be a new potential target for HB-ACLF treatment.Electronic supplementary materialThe online version of this article (10.1186/s12967-019-1844-0) contains supplementary material, which is available to authorized users.
Background: The proportion of recurrences after discharge among patients with coronavirus disease 2019 (COVID-19) was reported to be between 9.1% and 31.0%. Little is known about this issue, however, so we performed a meta-analysis to summarize the demographical, clinical, and laboratorial characteristics of non-recurrence and recurrence groups. Methods: Comprehensive searches were conducted using eight electronic databases. Data regarding the demographic, clinical, and laboratorial characteristics of both recurrence and non-recurrence groups were extracted, and quantitative and qualitative analyses were conducted. Results: Ten studies involving 2071 COVID-19 cases were included in this analysis. The proportion of recurrence cases involving patients with COVID-19 was 17.65% (between 12.38% and 25.16%) while older patients were more likely to experience recurrence (weighted mean difference (WMD)=1.67, range between 0.08 and 3.26). The time from discharge to recurrence was 13.38 d (between 12.08 and 14.69 d). Patients were categorized as having moderate severity (odds ratio (OR)=2.69, range between 1.30 and 5.58), while those with clinical symptoms including cough (OR=5.52, range between 3.18 and 9.60), sputum production (OR=5.10, range between 2.60 and 9.97), headache (OR=3.57, range between 1.36 and 9.35), and dizziness (OR=3.17, range between 1.12 and 8.96) were more likely to be associated with recurrence. Patients presenting with bilateral pulmonary infiltration and decreased leucocyte, platelet, and CD4 + T counts were at risk of
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.