Search

Background: Early-stage diagnosis and treatment can improve survival rates of liver cancer patients. Dynamic contrast-enhanced MRI provides the most comprehensive information for differential diagnosis of liver tumors. However, MRI diagnosis is affected by subjective experience, so deep learning may supply a new diagnostic strategy. We used convolutional neural networks (CNNs) to develop a deep learning system (DLS) to classify liver tumors based on enhanced MR images, unenhanced MR images, and clinical data including text and laboratory test results.Methods: Using data from 1,210 patients with liver tumors (N = 31,608 images), we trained CNNs to get seven-way classifiers, binary classifiers, and three-way malignancy-classifiers (Model A-Model G). Models were validated in an external independent extended cohort of 201 patients (N = 6,816 images). The area under receiver operating characteristic (ROC) curve (AUC) were compared across different models. We also compared the sensitivity and specificity of models with the performance of three experienced radiologists.Results: Deep learning achieves a performance on par with three experienced radiologists on classifying liver tumors in seven categories. Using only unenhanced images, CNN performs well in distinguishing malignant from benign liver tumors (AUC, 0.946; 95% CI 0.914–0.979 vs. 0.951; 0.919–0.982, P = 0.664). New CNN combining unenhanced images with clinical data greatly improved the performance of classifying malignancies as hepatocellular carcinoma (AUC, 0.985; 95% CI 0.960–1.000), metastatic tumors (0.998; 0.989–1.000), and other primary malignancies (0.963; 0.896–1.000), and the agreement with pathology was 91.9%.These models mined diagnostic information in unenhanced images and clinical data by deep-neural-network, which were different to previous methods that utilized enhanced images. The sensitivity and specificity of almost every category in these models reached the same high level compared to three experienced radiologists.Conclusion: Trained with data in various acquisition conditions, DLS that integrated these models could be used as an accurate and time-saving assisted-diagnostic strategy for liver tumors in clinical settings, even in the absence of contrast agents. DLS therefore has the potential to avoid contrast-related side effects and reduce economic costs associated with current standard MRI inspection practices for liver tumor patients.

In order to satisfy the requirements of long-distance multi-node quantum networks，two multi-party controlledquantum communication protocols are put forward via maximally and partially entangled quantum channels.For the maximally entangled channels,projective measurements are used to realizemulti-party controlled joint remote preparation of an arbitrary four-qubitX-state.For the partially entangled channels,collective unitary operations and optimal positive operator-valued measures are used to realize multi-party controlled joint remote preparation of an arbitrary four-qubitX-state.The theoretical analysis shows that the efficiency of the first scheme can be up to 100% which is suprior to that of others.In addition,the efficiency of the second scheme is effectively improved and the way to be used to construct two kinds of measurement methods can be utilized in the similar protocols.

Multi-party concurrent signatures were first proposed by Tonien et al at ISC2006,but Xie and Tan pointed Tonien et al's scheme doesn't satisfy fairness and they reconstructed multi-party concurrent signature schemes respectively.Through analysis,the multi-party concurrent signature schemes proposed by Xie and Tan don't satisfy fairness either,so a formal security model of fair multi-party concurrent signatures was proposed and a multi-party concurrent signature scheme based on bilinear pairing and multi-party key agreement was also reconstructed.Analysis shows that the new scheme satisfies correctness,unforgeability,ambiguity,concurrency and fairness in the random oracle model assuming the CDH problem is intractable and highly efficient in signature size,computation cost and communication cost compared with other schemes of its kind.

Objective: To investigate the clinical characteristics and prognosis of single center adult chronic myeloid leukemia in chronic phase (CML-CP)., Methods: Clinical data of 41 adult CML-CP patients in Department of Hematology, Shanghai Fengxian District Central Hospital from January 2015 to May 2021 were retrospectively analyzed. The clinical characteristics and prognosis of patients between <60 years group and ≥60 years group were compared., Results: The 41 patients included 27 (65.9%) males and 14 (34.1%) females. The median age of the patients was 56(19-84) years, with 22 cases (53.7%) <60 years and 19 cases (46.3%) ≥60 years. Univariate analysis indicated that the proportions of patients with comorbidities, intermediate/high-risk Sokal score, myelofibrosis, and lactate dehydrogenase ≥1 000 U/L were significantly increased in ≥60 years group compared with <60 years group at initial diagnosis (all P <0.05). There were no statistical differences in the distribution of sex, ELST score, white blood cell count, platelet count, peripheral blood basophil percentage, peripheral blood eosinophil percentage and bone marrow primitive cell percentage between the two groups ( P >0.05). The proportion of patients taking reduced-dose imatinib in ≥60 years group significantly increased ( P <0.001). Patients <60 years had a higher proportion of molecular biological remission after treatment of tyrosine kinase inhibitors (TKIs) than patients ≥60 years ( P <0.001). The incidence of non-hematologic adverse reactions to TKI therapy significantly increased in patients ≥60 years ( P <0.001). Multivariate analysis showed that no adverse factors affecting the efficacy and prognosis of TKI., Conclusion: Compared with adult CML-CP patients <60 years, patients ≥60 years gain fewer benefits from TKI treatment and increased adverse reactions.