Search

To explore the clinical application value of optical coherence microscopy (OCM) in Hirschsprung's disease. 109 HSCR patients were recuited in a Chinese hospital from January 2018 to July 2021. All the recruited patients underwent barium enema angiography preoperatively and the resected diseased intestinal tubes were evaluated intraoperatively. The OCM and the histopathological examination were performed successively on the surgical specimens, and the OCM images were compared with the relevant tissue sections to characterize different lesions. 10 non-HSCR fetal colorectal tissues at the same period were retained for OCM, the characteristics of which with and without HSCR under OCM imaging were analyzed. In the OCM images of in vitro tissue, it can be clearly observed that the scattering degree of HSCR narrow segment mucosal is high, glands and crypt structures are reduced or even atrophy, and the scattering degree of submucosal and intermuscular is low; In the dilated segment, the low scattering and high scattering are complex, and the muscle layer is obviously hypertrophy and structural disorder. Compared with the pathological findings, the OCM sensitivity, Kappa value, and AUC area reached 92.66%, 0.63, and 0.91, respectively. OCM can quickly and clearly display the structure of all layers of colorectal tissue, which is highly consistent with the corresponding histopathological examination results and has high sensitivity. which will provide a more reliable basis for OCM diagnosis of early HSCR, targeted biopsy and location of operative treatment, and has a certain potential for clinical application. [ABSTRACT FROM AUTHOR]

Cache-enabled UAVs are widely used as edge servers to provide on-demand content services for ground users. Most of prior works deploy UAVs based on user locations and explore the benefits of UAV caching under static content library. Motivated by this observation, we further consider heterogeneous user activity level and dynamic content library. We formulate a joint optimization problem of UAV deployment and content placement to minimize the average request delay, which is proved to be NP-hard. To tackle this problem efficiently, we decompose this optimization problem into two sub-problems, UAV deployment problem and content placement problem. Specifically, we first jointly consider user activity level and user locations for UAV deployment using weighted K-means method. After the UAV deployment, we propose a Q-learning algorithm to learn the content placement directly, rather than estimating the content popularity first, which is not effective when content library is dynamically changing. The simulation results show that the proposed algorithm outperforms the benchmark algorithms when dynamic content library and heterogeneous user activity level are considered. [ABSTRACT FROM AUTHOR]

Class incremental learning (CIL) has been proposed to solve the problem of learning to classify new classes while maintaining the performance on old classes. A typical strategy is to update the old classification model with entire new class data and a few old exemplars, which face serious performance degradation on old classes. The main reasons come down to class imbalance between old and new classes along with catastrophic forgetting towards old classes. Most existing CIL methods have proposed solving the above two issues in classification space, ignoring their adverse effects of overlapping between old and new classes and confusion among old classes in feature space. In this paper, we propose a rebalancing network with knowledge stability (RNKS), aiming to adequately retain the model performance on old classes in CIL by solving class imbalance and catastrophic forgetting in feature and classification space simultaneously. In detail, the proposed RNKS mainly consists of multi-proxies rebalancing (MPR) and hybrid knowledge distillation (HKD). MPR, focusing on class imbalance, employs multi-proxies metric learning to decrease the feature overlapping between old and new classes, together with balanced data sampling to correct the skewed decision boundary. HKD, coping with catastrophic forgetting, encourages the updated model to reproduce identical feature topologies and predictions of old classes as the old model via feature relation-based and response-based distillations. Experiments on CIFAR-100 and ILSVRC datasets demonstrate the effectiveness of this work against the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

What are the different features of the vaginal microbiome (VMB) between patients with polycystic ovary syndrome (PCOS) and healthy women? A cross-sectional study was conducted at a single academic university-affiliated centre. A total of 1446 participants were recruited (PCOS group, n =713, control group, n = 733). Vaginal swabs were analysed using 16S rRNA gene sequencing. The diversity and composition of the microbiome were compared between the PCOS group and the control group. Microbial interaction networks and functional prediction were investigated. The PCOS group had a higher alpha diversity than the control group (Shannon P = 0.03, Simpson P = 0.02), and higher intra-group variability was observed in PCOS group (P < 2.2E-16). At the genus level, the proportion of Lactobacillus decreased (85.1% versus 89.3%, false discovery rate [FDR] = 0.02), whereas the proportion of Gardnerella vaginalis and Ureaplasma increased in the PCOS group (5.1% versus 3.3%, FDR = 0.006; 1.2% versus 0.6%, FDR = 0.002, respectively). Lactobacillus acidophilus, Prevotella buccalis and G. vaginalis were identified as the main differential species. L. acidophilus was positively correlated with serum levels of anti-Müllerian hormone (AMH), and triglyceride (P = 2.01E-05, P = 0.004, respectively). P. buccalis was negatively correlated with serum levels of AMH and testosterone (P = 0.002, P = 0.003, respectively). G. vaginalis was positively correlated with serum levels of AMH, oestradiol and progesterone (P = 0.004, P = 0.005, P = 0.03, respectively). The VMB interaction network indicated that Lactobacillus crispus, Prevotella timonensis, and P. buccalis could be key drivers in the PCOS group. Overall, 55 predicted genes were found to be differentially abundant between PCOS and the control (FDRs < 0.25). The PCOS group had a higher diversity of vaginal microbiome and showed an enhanced level of heterogeneity. The proportion of Lactobacillus in the PCOS group decreased, whereas the proportions of Gardnerella and Ureaplasma increased. These results warrant further research that can validate the correlation between PCOS and VMB. [ABSTRACT FROM AUTHOR]