Search

Vessel segmentation is a fundamental, yet not well-solved problem in medical image analysis, due to the complicated geometrical and topological structures of human vessels. Unlike existing rule- and conventional learning-based techniques, which hardly capture the location of tiny vessel structures and perceive their global spatial structures, we propose Simultaneous Self- and Channel-attention Neural Network (termed SSCA-Net) to solve the multiscale structure-preserving vessel segmentation (MSVS) problem. SSCA-Net differs from the conventional neural networks in modeling image global contexts, showing more power to understand the global semantic information by both self- and channel-attention (SCA) mechanism and offering high performance on segmenting vessels with multiscale structures (e.g., DSC: 96.21% and MIoU: 92.70% on the intracranial vessel dataset). Specifically, the SCA module is designed and embedded in the feature decoding stage to learn SCA features at different layers, in which the self-attention is used to obtain the position information of the feature itself, and the channel attention is designed to guide the shallow features to obtain global feature information. To evaluate the effectiveness of our SSCA-Net, we compare it with several state-of-the-art methods on three well-known vessel segmentation benchmark datasets. Qualitative and quantitative results demonstrate clear improvements of our method over the state-of-the-art in terms of preserving vessel details and global spatial structures. [ABSTRACT FROM AUTHOR]

To determine if the effect of manipulative acupuncture monitored by laser speckle contrast imaging (LSCI) can improve facial blood perfusion in patients with severe Bell's palsy. This randomized, single-blind, controlled trial included 120 newly diagnosed patients (within 14 days) with severe Bell's palsy (House–Brackmann grading system (HBGS) ≥ grade IV). The patients were randomized (1 : 1) to receive either acupoints acupuncture combined with manipulations of twirling, lifting, and thrusting treatments (manipulative acupuncture) or acupoints acupuncture therapy alone (simple acupuncture). These treatments consisted of a total of 24 sessions, three times per week, and each treatment lasted for 30 min. Following 8 weeks of treatment and 6 months after the initial onset of facial palsy, facial nerve functioning was scored (HBGS) and clinical efficacy was measured. The patients' facial blood perfusion significantly improved following manipulative acupuncture assisted by LSCI compared with that at baseline (P < 0.01). At the conclusion of the 8-week treatment, both groups showed improvement; however, the recovery rate was significantly different (manipulative acupuncture 53.3% vs. simple acupuncture 33.9%, P < 0.05). Follow-up analysis at 6 months after the onset of facial palsy revealed a significantly higher recovery rate (91.7% vs. 78.0%; P < 0.05). In addition, the number of treatments in the observation group was less than that in the simple acupuncture therapy group (P < 0.05). Compared with simple acupuncture therapy, manipulative acupuncture therapy led to a more significant recovery rate in the treatment of severe Bell's palsy and required a shorter course of treatment. This trial was registered with ChiCTR1800019463. [ABSTRACT FROM AUTHOR]