Showing papers by "Jie Yuan published in 2021"
19 citations
TL;DR: Li et al. as mentioned in this paper proposed a global disassortative rewiring strategy to enhance the robustness of scale-free networks against LA without changing the degree distribution, which can be proved effective in enhancing network robustness against LA.
Abstract: The robustness of complex networks against attack has been an important issue for decades. Most of the previous studies focused on targeted attack (TA) and random attack (RA), while recently localized attack (LA) has drawn the attention of researchers. However, the existing studies related to LA mainly aim to reveal the properties on various network topologies so that the strategy to enhance network robustness against LA is still not well studied. In this paper, we propose a global disassortative rewiring strategy to enhance the robustness of scale-free networks against LA without changing the degree distribution. The validations are conducted on simulated scale-free networks and two real-life networks. As global disassortative rewiring strategy outperforms the other strategies, it can be proved effective in enhancing network robustness against LA and may contribute to future network risk reduction. In addition, by avoiding calculating and comparing the localized-robustness measurement within each rewire operation, our strategy offers a significant advantage in computational efficiency.
4 citations
TL;DR: A faster and more accurate thyroid nodule detection method based on the Faster R-CNN framework by adding three strategies: feature pyramid, spatial remapping and anchor-box redesign to meet the requirements of clinical application.
Abstract: Thyroid carcinoma is one of the most common endocrine diseases globally, and the incidence has been on the rise in recent years. Ultrasound imaging is the primary clinical method for early thyroid nodule diagnosis. Regions of interest (ROIs) of nodules in ultrasound images are difficult to detect because of their irregular shape nand vague margins. Accurate real-time thyroid nodule detection can provide ROIs for subsequent nodule diagnosis automatically, avoid variabilities between the subjective interpretations and inter-observer effectively and alleviate the workloads of medical practitioners. The aim of this study was to present a reliable, real-time detection method based on the Faster R-CNN (region-based convolutional network) framework for accurate and fast detection of thyroid nodules in ultrasound images. Our study proposed a faster and more accurate thyroid nodule detection method based on the Faster R-CNN framework by adding three strategies: feature pyramid, spatial remapping and anchor-box redesign. Specifically, the network takes raw ultrasound images as inputs and generates boxes with positions and the possibilities that these boxes contain thyroid nodules. The proposed method could locate and detect target nodules accurately with a mean average precision of 92.79% with more than 9000 patient images. In addition, the detection rate has accelerated to >16 frames per second, four times faster than that of the initial network. Therefore, it can meet the requirements of clinical application. The performance of the fivefold cross-validation was also accurate and robust. The proposed automatic thyroid nodule detection method yields better performance in accuracy and detection speed, which indicates the potential value of our method in assisting clinical ultrasound image interpretation.
1 citations
TL;DR: Wang et al. as mentioned in this paper proposed three methods based on photoacoustic and ultrasound signals to enhance the imaging quality using a 256-element full-ring array for biomedical imaging.
Abstract: Objective: With the growth of interest in different medical study on biological function, non-invasive photoacoustic imaging of biological tissue attracts the interests for researchers To eliminate the limited angle effect of photoacoustic imaging based on ultrasound linear array, spatially distributed ultrasound sensor array is applied The accurate sensor array position determines the quality of the imaging results In this study, we proposed three methods based on photoacoustic and ultrasound signals to enhance the imaging quality using a 256-element full-ring array Methods: Groups of photoacoustic and ultrasound signals are used to regress the position of each element sensor Result: In phantom study and mouse brain study, photoacoustic imaging results can both yield details clearly with average error rate of less than 1% (50 $\mu \text{m}$ ) Conclusion: The performance of our three methods have proved that they can be potentially applied to other ultrasound-based medical imaging studies with unknown distributed positions of sensor array to enhance the imaging quality Significance: The proposed methods can contribute to precise biomedical imaging with unknown distributed positions of sensor array in different application scenarios