A novel medical image segmentation approach by using multi-branch segmentation network based on local and global information synchronous learning.

In recent years, there have been several solutions to medical image segmentation, such as U-shaped structure, transformer-based network, and multi-scale feature learning method. However, their network parameters and real-time performance are often neglected and cannot segment boundary regions well. The main reason is that such networks have deep encoders, a large number of channels, and excessive attention to local information rather than global information, which is crucial to the accuracy of image segmentation. Therefore, we propose a novel multi-branch medical image segmentation network MBSNet. We first design two branches using a parallel residual mixer (PRM) module and dilate convolution block to capture the local and global information of the image. At the same time, a SE-Block and a new spatial attention module enhance the output features. Considering the different output features of the two branches, we adopt a cross-fusion method to effectively combine and complement the features between different layers. MBSNet was tested on five datasets ISIC2018, Kvasir, BUSI, COVID-19, and LGG. The combined results show that MBSNet is lighter, faster, and more accurate. Specifically, for a [Formula: see text] input, MBSNet's FLOPs is 10.68G, with an F1-Score of [Formula: see text] on the Kvasir test dataset, well above [Formula: see text] for UNet++ with FLOPs of 216.55G. We also use the multi-criteria decision making method TOPSIS based on F1-Score, IOU and Geometric-Mean (G-mean) for overall analysis. The proposed MBSNet model performs better than other competitive methods. Code is available at https://github.com/YuLionel/MBSNet .

Medication Non-adherence and Condomless Anal Intercourse Increased Substantially During the COVID-19 Pandemic Among MSM PrEP Users: A Retrospective Cohort Study in Four Chinese Metropolises.

Background: The coronavirus disease (COVID-19) pandemic has impacted HIV prevention strategies globally. However, changes in pre-exposure prophylaxis (PrEP) adherence and HIV-related behaviors, and their associations with medication adherence among men who have sex with men (MSM) PrEP users remain unclear since the onset of the COVID-19 pandemic. Methods: A Retrospective Cohort Study of HIV-negative MSM PrEP users was conducted in four Chinese metropolises from December 2018 to March 2020, assessing the changes in PrEP adherence and HIV-related behaviors before and during the COVID-19. The primary outcome was poor PrEP adherence determined from self-reported missing at least one PrEP dose in the previous month. We used multivariable logistic regression to determine factors correlated with poor adherence during COVID-19. Results: We enrolled 791 eligible participants (418 [52.8%] in daily PrEP and 373 [47.2%] in event-driven PrEP). Compared with the data conducted before the COVID-19, the proportion of PrEP users decreased from 97.9 to 64.3%, and the proportion of poor PrEP adherence increased from 23.6 to 50.1% during the COVID-19 [odds ratio (OR) 3.24, 95% confidence interval (CI) 2.62-4.02]. While the percentage of condomless anal intercourse (CAI) with regular partners (11.8 vs. 25.7%) and with casual partners (4.4 vs. 9.0%) both significantly increased. The proportion of those who were tested for HIV decreased from 50.1 to 25.9%. Factors correlated with poor PrEP adherence during the COVID-19 included not being tested for HIV (adjusted odds ratio [aOR] = 1.38 [95% CI: 1.00, 1.91]), using condoms consistently with regular partners (vs. never, aOR = 2.19 [95% CI: 1.16, 4.13]), and being married or cohabitating with a woman (vs. not married, aOR = 3.08 [95% CI: 1.60, 5.95]). Conclusions: Increased poor PrEP adherence and CAI along with the decrease in HIV testing can lead to an increase in HIV acquisition and drug resistance to PrEP. Targeted interventions are needed to improve PrEP adherence and HIV prevention strategies.