In this paper, we propose a bottom-up saliency model based on absorbing Markov chain (AMC). First, a sparsely connected graph is constructed to capture the local context information of each node. All image boundary nodes and other nodes are, respectively, treated as the absorbing nodes and transient nodes in the absorbing Markov chain. Then, the expected number of times from each transient node to all other transient nodes can be used to represent the saliency value of this node. The absorbed time depends on the weights on the path and their spatial coordinates, which are completely encoded in the transition probability matrix. Considering the importance of this matrix, we adopt different hierarchies of deep features extracted from fully convolutional networks and learn a transition probability matrix, which is called learnt transition probability matrix. Although the performance is significantly promoted, salient objects are not uniformly highlighted very well. To solve this problem, an angular embedding technique is investigated to refine the saliency results. Based on pairwise local orderings, which are produced by the saliency maps of AMC and boundary maps, we rearrange the global orderings (saliency value) of all nodes. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art methods on six publicly available benchmark data sets.

No abstract

Considering an ad hoc cognitive radio network, this paper presents channel assignment methods that can be used by a cognitive radio node to select a channel for communication. The proposed channel assignment methods aim to maximize spectral efficiency, minimize transmit power, or maximize data rate. When a number of available channels are detected, based on the proposed methods, a cognitive radio node can decide a suitable channel to use. These methods are executed distributively in cognitive radio nodes without using central controllers. This reduces the complexity of spectrum sharing in cognitive radio networks.

Value of computed tomography (CT) and magnetic resonance imaging (MRI) in the diagnosis of small hepatocellular carcinoma (HCC), and in analysis of the prognostic factors of primary hepatocellular carcinoma (PHC) were compared. A total of 300 patients with PHC were selected from January 2013 to January 2016. Among them, 170 patients were diagnosed with small HCC. Patients were diagnosed by MRI and CT scans, respectively, and diagnostic efficacy of the methods was compared. A single factor and multivariate analysis of prognostic factors were performed on 300 patients. The sensitivity of MRI screening was 78.82%, specificity was 78.46%, accuracy was 78.67%, positive predictive value was 82.72%, and negative predictive value was 73.91%. CT screening showed a sensitivity of 62.35%, a specificity of 73.85%, an accuracy of 67.33%, a positive predictive value of 75.71%, and a negative predictive value of 60.00%. Differences in sensitivity, accuracy, and negative predictive value between MRI and CT screening were statistically significant (P<0.05). There was no statistically significant difference between two groups in specificity and positive predictive value (P>0.05). Diagnostic efficiency of MRI is better than that of CT diagnosis. Univariate analysis showed that age, hepatitis B cirrhosis background, tumor stage, and portal vein embolization were prognostic factors for PHC. Cox multivariate regression analysis showed that the background of liver cirrhosis, tumor stage, and portal thrombosis were independent risk factors for poor prognosis for PHC patient and the differences were statistically significant (P<0.05). MRI is superior to CT in the sensitivity, specificity and accuracy of the diagnosis of small HCC. Individualized comprehensive treatment plans based on the patient's condition may be effective in prolonging the patient's survival time. Imaging diagnosis can provide survival basis for patients, improve diagnostic accuracy, and help to improve the survival rate.

No abstract

No abstract

No abstract

No abstract