Polyphonic sound event localization and detection based on Multiple Attention Fusion ResNet.

Sound event localization and detection have been applied in various fields. Due to the polyphony and noise interference, it becomes challenging to accurately predict the sound event and their occurrence locations. Aiming at this problem, we propose a Multiple Attention Fusion ResNet, which uses ResNet34 as the base network. Given the situation that the sound duration is not fixed, and there are multiple polyphonic and noise, we introduce the Gated Channel Transform to enhance the residual basic block. This enables the model to capture contextual information, evaluate channel weights, and reduce the interference caused by polyphony and noise. Furthermore, Split Attention is introduced to the model for capturing cross-channel information, which enhances the ability to distinguish the polyphony. Finally, Coordinate Attention is introduced to the model so that the model can focus on both the channel information and spatial location information of sound events. Experiments were conducted on two different datasets, TAU-NIGENS Spatial Sound Events 2020, and TAU-NIGENS Spatial Sound Events 2021. The results demonstrate that the proposed model significantly outperforms state-of-the-art methods under multiple polyphonic and noise-directional interference environments and it achieves competitive performance under a single polyphonic environment.

A comparative study on the features of breast sclerosing adenosis and invasive ductal carcinoma via ultrasound and establishment of a predictive nomogram.

Objective: To analyze the clinical and ultrasonic characteristics of breast sclerosing adenosis (SA) and invasive ductal carcinoma (IDC), and construct a predictive nomogram for SA. Materials and methods: A total of 865 patients were recruited at the Second Hospital of Shandong University from January 2016 to November 2022. All patients underwent routine breast ultrasound examinations before surgery, and the diagnosis was confirmed by histopathological examination following the operation. Ultrasonic features were recorded using the Breast Imaging Data and Reporting System (BI-RADS). Of the 865 patients, 203 (252 nodules) were diagnosed as SA and 662 (731 nodules) as IDC. They were randomly divided into a training set and a validation set at a ratio of 6:4. Lastly, the difference in clinical characteristics and ultrasonic features were comparatively analyzed. Result: There was a statistically significant difference in multiple clinical and ultrasonic features between SA and IDC (P<0.05). As age and lesion size increased, the probability of SA significantly decreased, with a cut-off value of 36 years old and 10 mm, respectively. In the logistic regression analysis of the training set, age, nodule size, menopausal status, clinical symptoms, palpability of lesions, margins, internal echo, color Doppler flow imaging (CDFI) grading, and resistance index (RI) were statistically significant (P<0.05). These indicators were included in the static and dynamic nomogram model, which showed high predictive performance, calibration and clinical value in both the training and validation sets. Conclusion: SA should be suspected in asymptomatic young women, especially those younger than 36 years of age, who present with small-size lesions (especially less than 10 mm) with distinct margins, homogeneous internal echo, and lack of blood supply. The nomogram model can provide a more convenient tool for clinicians.

Effects of inflammation on the accuracy of ultrasound diagnosis of epidermoid cysts.

AIMS: Ultrasound (US) findings of epidermoid cyst (EC) are complex and diverse. Cases of misdiagnoses are high when EC is accompanied by inflammation. The aim of this study was to analyze the features of US diagnosis of EC with inflammation and explore the characteristic images which can improve the accuracy of ultrasound diagnosis. MATERIAL AND METHODS: A total of 241 cases were included and retrospectively analyzed. Complete clinical data of all cases were available. Lesions were examined by US before operation and the diagnosis was confirmed by histopathological examination. Based on pathological results ECs with/without acute and chronic inflammation and/or granuloma, all cases were divided into two groups: inflammation and non-inflammation group. The difference of clinical data and US features between groups was analyzed by univariate and multivariate logistic regression. RESULTS: Analysis of skin color, length/thickness, shape, boundary, CDFI and US diagnosis accuracy showed statistical differences between the two groups (p<0.05). Multivariate logistic regression model showed that indistinct boundaries and color Doppler signal were more frequent than those in ECs without inflammation (OR=4.72, 5.89, p<0.05). CONCLUSION: Indistinct boundaries and color Doppler signal are important features for US diagnosis of EC with inflammation, which can help in improving the accuracy of diagnosis.

Knockdown of circHomer1 ameliorates METH-induced neuronal injury through inhibiting Bbc3 expression.

Current studies have illustrated that circular RNAs (circRNAs) are a vital part of non-coding RNA (ncRNAs) species and highly abundant and dynamically expressed in brain. However, the exact mechanisms by which circRNAs modulate methamphetamine (METH)-induced neuronal damage still remain largely unexplored. Consistent with our previous study, the expression of circHomer1 was significantly up-regulated after METH treatment in HT-22 cells. We confirmed its loop structure by detection of its back-splice junction with qRT-PCR product via sequence. Moreover, circHomer1 was resistant against RNase R digestion compared with its linear mRNA Homer1. Inhibition of circHomer1 expression indeed alleviated METH-induced neurotoxicity, with lower apoptosis rate via flow cytometry and cleaved Caspase3 protein level. Furthermore, we speculated that Bbc3 functioned as a target of circHomer1 based on computational algorithm, and knockdown of circHomer1 actually reduced Bbc3 expression at the mRNA and protein level. Besides, suppression of Bbc3 decreased the reactive oxygen species (ROS) level and radio of PI-positive cells. Furthermore, we analyzed the correlation in pairs among circHomer1, Bbc3 and behaviors in well-developed METH-addicted models using Pearson's correlation coefficient, which implied an important role of circHomer1 and Bbc3 in addictive behaviors. In all, we for the first time identified a novel circRNA, circHomer1 and our results suggested that circHomer1 regulated METH-induced lethal process by suppressing the Bbc3 expression.

Melatonin protects against Aß-induced neurotoxicity in primary neurons via miR-132/PTEN/AKT/FOXO3a pathway.

Alzheimer's disease (AD) is a kind of neurodegenerative disorder associated with age. Investigations suggest that amyliod-ß (Aß) is implicated in the pathogenesis of AD. The accumulation of Aß in the brain causes oxidative stress and synaptic toxicity, leads to synaptic dysfunction and neuronal death. Previous investigations suggest that melatonin an endogenous hormone can counteract Aß-induced neurotoxicity. However, the molecular mechanisms of Aß-induced toxicity and melatonin treatment remain elusive. Studies indicate that microRNA-132 is crucial for neuronal survival and plays a key role in the pathological process of AD. Moreover, PTEN and FOXO3a two key targets of miR-132 are upregulated in the AD brain. Here, we exposed the primary cultured cortical neurons with Aß25-35 and treated with melatonin. Our investigations demonstrated that Aß25-35 exposure significantly decreased the expression of miR-132 and elevated the expression of PTEN and FOXO3a. Whereas, melatonin treatment could rescue the expression of miR-132 and downregulate the level of PTEN and FOXO3a. Moreover, melatonin blocked the nuclear translocation of FOXO3a and thereby suppressed its pro-apoptotic pathways. In addition, our investigations suggested that the over-expression of miR-132 could block Aß-induced neurotoxicity. We also found that VO-OHpic (PTEN inhibitor) could counteract Aß-induced neuronal damage, and LY294002 (AKT inhibitor) suppressed the protective effect of melatonin. Together, these results indicate that melatonin exerts its neuroprotective effect in Aß-induced neurotoxicity via miR-132/PTEN/AKT/FOXO3a pathway. © 2018 BioFactors, 44(6):609-618, 2018.