Search

Radiologists often inspect hundreds of two-dimensional computed-tomography (CT) images to accurately locate lesions and make diagnoses, by classifying and labeling the ribs. However, this task is repetitive and time consuming. To effectively address this problem, we propose a multi-axial rib segmentation and sequential labeling (MARSS) method. First, we slice the CT volume into sagittal, frontal, and transverse planes for segmentation. The segmentation masks generated for each plane are then reconstructed into a single 3D segmentation mask using binarization techniques. After separating the left and right rib volumes from the entire CT volume, we cluster the connected components identified as bones and sequentially assign labels to each rib. The segmentation and sequential labeling performance of this method outperformed existing methods by up to 4.2%. The proposed automatic rib sequential labeling method enhances the efficiency of radiologists. In addition, this method provides an extended opportunity for advancements not only in rib segmentation but also in bone-fracture detection and lesion-diagnosis research. [ABSTRACT FROM AUTHOR]

Emerging applications require processing a huge amount of environmental data from wireless sensor networks, and then triggering appropriate actions in response to the detected events. To this end, it is desirable to minimize the time needed for data aggregation. This paper investigates the minimum-latency aggregation scheduling problem in wireless sensor networks. We propose an aggregation tree construction algorithm called Break-and-Join which adjusts any aggregation tree toward a smaller delay one. In order to perform tree adjustments, the algorithm iteratively changes parent of some nodes in the tree, using a novel numerical metric as a tree quality guideline. Each node determines if it can adopt an additional child in the neighborhood in order to relax the aggregation load at some bottleneck node in the network, thereby improving the overall aggregation tree quality. We performed the algorithm on several state-of-the-art aggregation schemes, and the results shows that final aggregation delay is quite indifferent to choice of initial tree and the tree quality can be significantly improved (e.g. 7 times for shortest path tree). Scheduling on the obtained trees also outperforms the best known scheme up to 13% in terms of delay. [ABSTRACT FROM AUTHOR]