Cardiovascular disease has seriously affected the lives of modern people. One of the most commonly used imaging methods for diagnosing cardiovascular disease is computed tomography angiography (CTA). To generate a diagnosis report for doctors, every coronary artery needs to be identified and segmented, including the right coronary artery (RCA), the posterior descending artery (PDA), the posterior lateral branch (PLB), the left circumflex (LCx), the left anterior descending branch (LAD), the ramus intermedius (RI), the obtuse marginal branches (OM1, OM2), and the diagonal branches (D1, D2). In this paper, we proposed a coronary artery automatic identification algorithm, which performs better in terms of accuracy than other similar algorithms and works efficiently. Normally, each Coronary Computed Tomographic Angiography (CCTA) dataset can be completed within seconds. This algorithm fully complies with the coronary label standard established by the Society of Cardiovascular Computed Tomography (SCCT). This algorithm has been put into operation in more than 100 hospitals for over one year. According to all previous tests, the labels obtained from the algorithm were compared with results manually corrected by several experts. Among 892 CCTA datasets, 95.96% of the labels obtained from the algorithms were correct. INDEX TERMS Automatic identification, computed tomography angiography, coronary artery.

No abstract

The higher-order structure of networks is a hot research topic in complex networks. It has received much attention because it is closely related to the functionality of networks, such as network transportation and propagation. For instance, recent studies have revealed that studying higher-order networks can explore hub structures in transportation networks and information dissemination units in neuronal networks. Therefore, the destruction of the connectivity of higher-order networks will cause significant damage to network functionalities. Meanwhile, previous works pointed out that the function of a complex network depends on the giant component of the original(low-order) network. Therefore, the network functionality will be influenced by both the low-order and its corresponding higher-order network. To study this issue, we build a network model of the interdependence of low-order and higher-order networks (we call it ILH). When some low-order network nodes fail, the low-order network’s giant component shrinks, leading to changes in the structure of the higher-order network, which further affects the low-order network. This process occurs iteratively; the propagation of the failure can lead to an eventual network crash. We conducted experiments on different networks based on the percolation theory, and our network percolation results demonstrated a first-order phase transition feature. In particular, we found that an ILH is more fragile than the low-order network alone, and an ILH is more likely to be corrupted in the event of a random node failure.

Link prediction is a hot issue in information filtering. Link prediction algorithms, based on local similarity indices, are widely used in many fields due to their high efficiency and high prediction accuracy. However, most existing link prediction algorithms are available for unweighted networks, and there are relatively few studies for weighted networks. In the previous studies on weighted networks, some scholars pointed out that links with small weights play a more important role in link prediction and emphasized that weak-ties theory has a significant impact on prediction accuracy. On this basis, we studied the edges with different weights, and we discovered that, for edges with large weights, this weak-ties theory actually does not work; Instead, the weak-ties theory works in the prediction of edges with small weights. Our discovery has instructive implications for link predictions in weighted networks.