Search

In the field of nanotechnology, rotary jet spinning technology has garnered attention due to its unique advantages in fabricating composite nanofibers. The composite nanofibers prepared using this technology exhibit exceptional purity, uniformity, and consistency, thereby enhancing reliability and controllability in practical applications. During the process of rotary jet spinning, the spinning solution flows into the nozzle and converges at a micro-triangle under the combined influence of centrifugal force, viscous force, surface tension, and gravity. Stepped jet refers to the flow phenomenon occurring within a channel with a gradually decreasing cross-sectional area. In this process, an increase in the flow velocity of the composite spinning solution aids in stabilizing stretching at the micro-triangle which is crucial for forming continuous jets. This article analyzes cone formation mechanisms for composite spinning solutions and stepped jet principles while establishing corresponding models that reflect relationships between solution velocity magnitude and parameters such as rotational speed, concentration, and nozzle diameter. Finally, polyethylene oxide (PEO)/polyvinylpyrrolidone (PVP) composite nanofibers were prepared using a rotary jet spinning device where experimental investigation focused on examining how parameters such as rotational speed, solution concentration, and nozzle diameter impact motion of spinning solution within micro-triangle. Highlights * Preparation of PEO/PVP composite nanofibers by rotary jet spinning. * Presentation of cone formation mechanisms for composite solutions. * The stepped injection principle was proposed. * Modeling of composite solution motion. * Rotational speed, solution concentration, and nozzle diameter impact motion. KEYWORDS composite nanofiber, micro-triangle, rotating jet spinning, stepped jet, 1 | INTRODUCTION Nanofibers, as a type of nanomaterial, exhibit immense potential for diverse applications and have garnered extensive attention owing to their distinctive structure and exceptional performance. (1) Nanofibers [...]

Abstract Background The COVID-19 pandemic has significantly impacted the psychological well-being of undergraduate nursing students in China. It is vital to have an understanding of their COVID-19 phobia and its predictors, especially during transitions in public health policy. Objective This study aims to evaluate the situation and factors contributing to COVID-19 phobia among nursing students in Southwestern China. Methods A cross-sectional study was conducted in December 2022 among nursing undergraduates in southwestern China. A convenience sample of 317 undergraduate nursing students from all grades at a medical university in Chengdu was assessed using the COVID-19 Phobia Scale (C19P). Results The mean COVID-19 Phobia Scale (C19P-SC) score was 52.92 (± 13.02), indicating moderate levels of phobia, with gender, chronic disease, and perceived susceptibility being significant predictors. 11.67% of the students reported an infection history, while 81.39% knew an infected individual. Notably, fourth-year students showed significantly higher phobia level than first-year. Gender, chronic disease, perceived susceptibility, and risk significantly predicted COVID-19 phobia, explaining 16.4% of the variance Results of the thematic analysis revealed four main themes related to COVID-19 phobia and career choice among nursing undergraduates: concerns of infection risk, professional commitment, compromise and acceptance, and confronting phobia. Conclusions This study discovered a significant level of COVID-19 phobia among undergraduate nursing students and identified several risk factors, including being female, having chronic diseases, perceiving a high susceptibility to the virus, and perceiving a high level of harm after infection. These findings highlight the importance of educators focusing on the mental well-being of nursing students, particularly seniors, to reduce the impact of phobia on their social interactions and career aspirations. This will help ensure that they are well-prepared for their future roles in healthcare.

Rhodiola, belonging to the Crassulaceae family, is a perennial herbaceous plant genus. There are about 90 Rhodiola species worldwide, some of which have been reported to have medicinal properties. Rhodiola sachalinensis is a perennial medicinal herb within this genus and, in the present study, its chloroplast genome was sequenced, assembled, annotated and compared with 24 other Rhodiola species. The results obtained show that the chloroplast genome of R. sachalinensis is 151 595 bp long and has a CG content of 37.7%. The inverted repeats (IR) region of the Rhodiola chloroplast genome is the most conserved region, with the main differences being observed in the ycf1 and ndhF genes at the IRb‐small single copy boundary, and rps19 and trnH genes at the IRa‐large single copy boundary. Phylogenetic analysis showed that Rhodiola species form two major clades, and species with recorded medicinal properties, clustered together in one branch except for R. dumulosa. Within the genus, R. sachalinensis is most closely related to Rhodiola rosea, although comparative analyses showed that only R. sachalinensis and Rhodiola subopposita contained the psbZ gene, which encodes a highly conserved protein subunit of the Photosystem II core complex. Overall, the present study contributes to the understanding of the chloroplast genome of Rhodiola species, and provides a theoretical basis for the study of their genetic diversity and possible use as medicinal plants.

IntroductionSynaptic failure, a hallmark of Alzheimer's disease (AD), is correlated with reduced levels of synaptic proteins. Though people with Down syndrome (DS) are at markedly increased risk for AD (AD-DS), few studies have addressed synapse dysfunction.MethodsSynaptic proteins were measured in the frontal cortex of DS, AD-DS, sporadic AD cases, and controls. The same proteins were examined in the Dp16 model of DS.ResultsA common subset of synaptic proteins were reduced in AD and AD-DS, but not in DS or a case of partial trisomy 21 lacking triplication of APP gene. Pointing to compromised synaptic function, the reductions in AD and AD-DS were correlated with reduced SNARE complexes. In Dp16 mice reductions in syntaxin 1A, SNAP25 and the SNARE complex recapitulated findings in AD-DS; reductions were impacted by both age and increased App gene dose.DiscussionSynaptic phenotypes shared between AD-DS and AD point to shared pathogenetic mechanisms.

Abstract Background The association between exposure to PM2.5 chemical constituents and obesity remains to be elucidated, as most studies have used a single measure of obesity. This study aimed to investigate the associations of exposure to PM2.5 chemical constituents with general, abdominal, and visceral obesity, and the mediation effect of physical activity (PA) in the associations. Methods Based on a total of 49,819 adults from the baseline of the Yunnan Behavior and Disease Surveillance cohort (YBDS) in southern China in 2021, we used multiple linear regression, weighted quantile sum regression, and quantile regression to estimate independent and joint effects of PM2.5 chemical constituents on elevated BMI, waist circumference (WC) and visceral adiposity index (VAI) and whether these effects changed in quantiles. Mediation analysis was used to examine whether physical activity acts as a mediator in these pathways. Results Per IQR μg/m3 increase in all PM2.5 chemical constituents was significantly associated with the elevated BMI (β [95% CI]: 0.170 [0.127, 0.214]), WC (0.316 [0.217, 0.415]) and VAI (0.102 [0.075, 0.129]), with the largest weights from OM (53.89, 81.67, and 89.82%, respectively). The effects of PM2.5 chemical constituents on obesity showed an overall upward trend from quantiles 1–4 of BMI, WC, and VAI, especially with a rapid upward trend from the sixth decile of VAI. Reduced PA mediated 3.16, 7.08, and 3.78% of the associations between PM2.5 chemical constituents and elevated BMI, WC, and VAI, respectively. Conclusions Exposure to PM2.5 chemical constituents, especially OM, was significantly associated with increased risks for obesity in adults. The effects of associations increased with obesity severity, with PA playing a mediation role.

Abstract To compare and analyze the diagnostic value of different enhancement stages in distinguishing low and high nuclear grade clear cell renal cell carcinoma (ccRCC) based on enhanced computed tomography (CT) images by building machine learning classifiers. A total of 51 patients (Dateset1, including 41 low-grade and 10 high-grade) and 27 patients (Independent Dateset2, including 16 low-grade and 11 high-grade) with pathologically proven ccRCC were enrolled in this retrospective study. Radiomic features were extracted from the corticomedullary phase (CMP), nephrographic phase (NP), and excretory phase (EP) CT images, and selected using the recursive feature elimination cross-validation (RFECV) algorithm, the group differences were assessed using T-test and Mann–Whitney U test for continuous variables. The support vector machine (SVM), random forest (RF), XGBoost (XGB), VGG11, ResNet18, and GoogLeNet classifiers are established to distinguish low-grade and high-grade ccRCC. The classifiers based on CT images of NP (Dateset1, RF: AUC = 0.82 ± 0.05, ResNet18: AUC = 0.81 ± 0.02; Dateset2, XGB: AUC = 0.95 ± 0.02, ResNet18: AUC = 0.87 ± 0.07) obtained the best performance and robustness in distinguishing low-grade and high-grade ccRCC, while the EP-based classifier performance in poorer results. The CT images of enhanced phase NP had the best performance in diagnosing low and high nuclear grade ccRCC. Firstorder_Kurtosis and firstorder_90Percentile feature play a vital role in the classification task.

The current advanced neural network models are expanding in size and complexity to achieve improved detection accuracy. This study designs a lightweight fabric defect detection algorithm based on YOLOv7-tiny, called YOLOv7-tiny-MGCK. Its objectives are to improve the performance of fabric defect detection against complex backgrounds and to find a balance between the algorithm’s lightweight nature and its accuracy. The algorithm utilizes the Mish activation function, known for its superior nonlinear performance capability and smoother curve, enabling the neural network to manage more complex challenges. The Ghost convolution module is also incorporated to reduce computation and model parameters. The lightweight upsampling technique CARAFE facilitates the flexible extraction of deep features, coupled with their integration with shallow features. In addition, an improved K-Means clustering algorithm, KMMP, is employed to select appropriate anchor box for fabric defects. The experimental results show: a reduction in the number of parameters by 45.5% and computational volume by 41.0%, along with increases in precision by 3.9%, recall by 7.0%, and mAP by 3.0%. These results indicated that the improved algorithm achieves a more effective balance between detection performance and the requirement for a lightweight solution.

Abstract Background Healthy lifestyles are crucial for preventing chronic diseases. Nonetheless, approximately 90% of Chinese community residents regularly engage in at least one unhealthy lifestyle. Mobile smart devices-based health interventions (mHealth) that incorporate theoretical frameworks regarding behavioral change in interaction with the environment may provide an appealing and cost-effective approach for promoting sustainable adaptations of healthier lifestyles. We designed a randomized controlled trial (RCT) to evaluate the effectiveness of a socioecological model-guided, smart device-based, and self-management-oriented lifestyles (3SLIFE) intervention, to promote healthy lifestyles among Chinese community residents. Methods This two-arm, parallel, cluster-RCT with a 6-month intervention and 6-month follow-up period foresees to randomize a total of 20 communities/villages from 4 townships in a 1:1 ratio to either intervention or control. Within these communities, a total of at least 256 community residents will be enrolled. The experimental group will receive a multi-level intervention based on the socioecological model supplemented with a multi-dimensional empowerment approach. The control group will receive information only. The primary outcome is the reduction of modifiable unhealthy lifestyles at six months, including smoking, excess alcohol consumption, physical inactivity, unbalanced diet, and overweight/obesity. A reduction by one unhealthy behavior measured with the Healthy Lifestyle Index Score (HLIS) will be considered favorable. Secondary outcomes include reduction of specific unhealthy lifestyles at 3 months, 9 months, and 12 months, and mental health outcomes such as depression measured with PHQ-9, social outcomes such as social support measured with the modified Multidimensional Scale of Perceived Social Support, clinical outcomes such as obesity, and biomedical outcomes such as the development of gut microbiota. Data will be analyzed with mixed effects generalized linear models with family and link function determined by outcome distribution and accounting for clustering of participants in communities. Discussion This study will provide evidence concerning the effect of a mHealth intervention that incorporates a behavioral change theoretical framework on cultivating and maintaining healthy lifestyles in community residents. The study will provide insights into research on and application of similar mHealth intervention strategies to promote healthy lifestyles in community populations and settings. Trial registration number ChiCTR2300070575. Date of registration: April 17, 2023. https://www.chictr.org.cn/index.aspx .

Abstract In recent years, with the increasing incidence of endometrial carcinoma in women of child-bearing age, to decision of whether to preserve patients’ fertility during treatment has become increasingly complex, presenting a formidable challenge for both physicians and patients. Non-fertility-sparing treatment can remove lesions more thoroughly than fertility-sparing treatment. However, patients will permanently lose their fertility. In contrast, fertility-sparing treatment can treat tumors without impairing fertility, but the risk of disease progression is high as compared with non-fertility-sparing treatment. Therefore, it is extremely important to accurately identify patients who are suitable for fertility-sparing treatments. The evaluation of prognostic factors, including myometrial invasion, the presence of lymph node metastases, and histopathological type, is vital for determining whether a patient can receive fertility-sparing treatment. As a non-invasive and quantitative approach, radiomics has the potential to assist radiologists and other clinicians in determining more precise judgments with regard to the above factors by extracting imaging features and establishing predictive models. In this review, we summarized currently available fertility-sparing strategies and reviewed the performance of radiomics in predicting risk factors associated with fertility-sparing treatment. This review aims to assist clinicians in identifying patients suitable for fertility-sparing treatment more accurately and comprehensively and informs more appropriate and rigorous treatment decisions for endometrial cancer patients of child-bearing age. Critical relevance statement: Radiomics is a promising tool that may assist clinicians identify risk factors about fertility-sparing more accurately and comprehensively. Graphical abstract

BackgroundImpaired axonal transport may contribute to the pathogenesis of neurodegenerative diseases, including Alzheimer's disease (AD) and Down syndrome (DS). Axonal transport is a complex process in which specific motor proteins move cargoes to and from neuronal cell bodies and their processes. Inconsistent reports point to the changes in AD in the levels of the classical anterograde motor protein kinesin family member 5 (KIF5) and the primary neuronal KIF regulator kinesin light chain 1 (KLC1), raising the possibility that anterograde transport is compromised in AD.Methods and materialsTo address inconsistencies and determine if the shared pathologies in AD and elderly DS subjects with dementia (AD in DS; AD-DS) extend to the changes in KIF5 and KLC1, we measured the levels of all the three KIF5 family members and KLC1 in the AD and AD-DS frontal cortex and AD temporal cortex and cerebellum in samples taken with a short postmortem interval. To support future studies to explore the cell biological basis for any changes detected, we also examined the levels of these proteins in the brains of young and aged adult mice in the Dp (16)1Yey/+ (Dp16) mouse model of DS and J20 mouse model of AD.ResultsThere were no changes in comparison with controls in KIF5 family members in either the AD or AD-DS samples when normalized to either β-actin or glyceraldehyde-3-phosphate dehydrogenase (GAPDH). Interestingly, however, samples from control brains as well as from AD and AD-DS demonstrated strong positive correlations between the levels of KIF5 family members, suggesting positive co-regulated expression. Importantly, while earlier reports pointed to a negative correlation between the levels of the amyloid precursor protein (APP) and KIF5A levels, we found the opposite to be true in AD-DS; this was especially striking given triplication of the APP gene, with increased APP protein levels. AD and control samples showed positive correlations between fl-hAPP and KIF5 members, but they were less consistent. In contrast to the findings for KIF5, the levels of KLC1 were downregulated in the frontal cortex of both AD and AD-DS brains; interestingly, this change was not seen in the AD temporal cortex or cerebellum. As postmortem interval has a negative effect on the levels of KLC1, but not KIF5 members, we analyzed a subset of samples with a very short postmortem interval (PMI) (≤ 6 h), a PMI that was not significantly correlated with the levels of KLC1 in either AD or AD-DS samples; we confirmed the presence of a statistically significant reduction of KLC1 in AD and AD-DS brains as compared with control brains. Studies comparing Dp16 to its euploid control recapitulated human studies in demonstrating no change in KIF5 levels and a positive correlation between the levels of KIF5 family members. J20 mice also showed normal KIF5 levels. However, unlike the AD and AD-DS frontal cortex, KLC1 levels were not reduced in the brains of Dp16 or J20 mice.ConclusionThese data point to significant reductions in KLC1 in AD and AD-DS. In so doing, they raise the possibility of compromised KLC1-mediated axonal transport in these conditions, a posit that can now be pursued in model systems in which KLC1 expression is reduced.

ObjectiveRecent clinical trials targeting amyloid beta (Aβ) and tau in Alzheimer's disease (AD) have yet to demonstrate efficacy. Reviewing the hypotheses for AD pathogenesis and defining possible links between them may enhance insights into both upstream initiating events and downstream mechanisms, thereby promoting discovery of novel treatments. Evidence that in Down syndrome (DS), a population markedly predisposed to develop early onset AD, increased APP gene dose is necessary for both AD neuropathology and dementia points to normalization of the levels of the amyloid precursor protein (APP) and its products as a route to further define AD pathogenesis and discovering novel treatments.BackgroundAD and DS share several characteristic manifestations. DS is caused by trisomy of whole or part of chromosome 21; this chromosome contains about 233 protein-coding genes, including APP. Recent evidence points to a defining role for increased expression of the gene for APP and for its 99 amino acid C-terminal fragment (C99, also known as β-CTF) in dysregulating the endosomal/lysosomal system. The latter is critical for normal cellular function and in neurons for transmitting neurotrophic signals.New/updated hypothesisWe hypothesize that the increase in APP gene dose in DS initiates a process in which increased levels of full-length APP (fl-APP) and its products, including β-CTF and possibly Aβ peptides (Aβ42 and Aβ40), drive AD pathogenesis through an endosome-dependent mechanism(s), which compromises transport of neurotrophic signals. To test this hypothesis, we carried out studies in the Ts65Dn mouse model of DS and examined the effects of Posiphen, an orally available small molecule shown in prior studies to reduce fl-APP. In vitro, Posiphen lowered fl-APP and its C-terminal fragments, reversed Rab5 hyperactivation and early endosome enlargement, and restored retrograde transport of neurotrophin signaling. In vivo, Posiphen treatment (50 mg/kg/d, 26 days, intraperitoneal [i.p.]) of Ts65Dn mice was well tolerated and demonstrated no adverse effects in behavior. Treatment resulted in normalization of the levels of fl-APP, C-terminal fragments and small reductions in Aβ species, restoration to normal levels of Rab5 activity, reduced phosphorylated tau (p-tau), and reversed deficits in TrkB (tropomyosin receptor kinase B) activation and in the Akt (protein kinase B [PKB]), ERK (extracellular signal-regulated kinase), and CREB (cAMP response element-binding protein) signaling pathways. Remarkably, Posiphen treatment also restored the level of choline acetyltransferase protein to 2N levels. These findings support the APP gene dose hypothesis, point to the need for additional studies to explore the mechanisms by which increased APP gene expression acts to increase the risk for AD in DS, and to possible utility of treatments to normalize the levels of APP and its products for preventing AD in those with DS.Major challenges for the hypothesisImportant unanswered questions are: (1) When should one intervene in those with DS; (2) would an APP-based strategy have untoward consequences on possible adaptive changes induced by chronically increased APP gene dose; (3) do other genes present on chromosome 21, or on other chromosomes whose expression is dysregulated in DS, contribute to AD pathogenesis; and (4) can one model strategies that combine the use of an APP-based treatment with those directed at other AD phenotypes including p-tau and inflammation.Linkage to other major theoriesThe APP gene dose hypothesis interfaces with the amyloid cascade hypothesis of AD as well as with the genetic and cell biological observations that support it. Moreover, upregulation of fl-APP protein and products may drive downstream events that dysregulate tau homeostasis and inflammatory responses that contribute to propagation of AD pathogenesis.

Posiphen tartrate (Posiphen) is an orally available small molecule that targets a conserved regulatory element in the mRNAs of amyloid precursor protein (APP) and α-synuclein (αSYN) and inhibits their translation. APP and αSYN can cause neurodegeneration when their aggregates induce neurotoxicity. Therefore, Posiphen is a promising drug candidate for neurodegenerative diseases, including Alzheimer's disease and Parkinson's disease. Posiphen's safety has been demonstrated in three independent phase I clinical trials. Moreover, in a proof of concept study, Posiphen lowered neurotoxic proteins and inflammatory markers in cerebrospinal fluid of mild cognitive impaired patients. Herein we investigated whether Posiphen reduced the expression of other proteins, as assessed by stable isotope labeling with amino acids in cell culture (SILAC) followed by mass spectrometry (MS)-based proteomics. Neuroblastoma SH-SY5Y cells, an in vitro model of neuronal function, were used for the SILAC protein profiling response. Proteins whose expression was altered by Posiphen treatment were characterized for biological functions, pathways and networks analysis. The most significantly affected pathway was the Huntington's disease signaling pathway, which, along with huntingtin (HTT) protein, was down-regulated by Posiphen in the SH-SY5Y cells. The downregulation of HTT protein by Posiphen was confirmed by quantitative Western blotting and immunofluorescence. Unchanged mRNA levels of HTT and a comparable decay rate of HTT proteins after Posiphen treatment supported the coclusion that Posiphen reduced HTT via downregulation of the translation of HTT mRNA. Meanwhile, the downregulation of APP and αSYN proteins by Posiphen was also confirmed. The mRNAs encoding HTT, APP and αSYN contain an atypical iron response element (IRE) in their 5'-untranslated regions (5'-UTRs) that bind iron regulatory protein 1 (IRP1), and Posiphen specifically bound this complex. Conversely, Posiphen did not bind the IRP1/IRE complex of mRNAs with canonical IREs, and the translation of these mRNAs was not affected by Posiphen. Taken together, Posiphen shows high affinity binding to the IRE/IRP1 complex of mRNAs with an atypical IRE stem loop, inducing their translation suppression, including the mRNAs of neurotoxic proteins APP, αSYN and HTT.

Down syndrome (DS) is the most common genetic cause of Alzheimer's disease (AD) due to trisomy for all or part of human chromosome 21 (Hsa21). It is also associated with other phenotypes including distinctive facial features, cardiac defects, growth delay, intellectual disability, immune system abnormalities, and hearing loss. All adults with DS demonstrate AD-like brain pathology, including amyloid plaques and neurofibrillary tangles, by age 40 and dementia typically by age 60. There is compelling evidence that increased APP gene dose is necessary for AD in DS, and the mechanism for this effect has begun to emerge, implicating the C-terminal APP fragment of 99 amino acid (β-CTF). The products of other triplicated genes on Hsa21 might act to modify the impact of APP triplication by altering the overall rate of biological aging. Another important age-related DS phenotype is hearing loss, and while its mechanism is unknown, we describe its characteristics here. Moreover, immune system abnormalities in DS, involving interferon pathway genes and aging, predispose to diverse infections and might modify the severity of COVID-19. All these considerations suggest human trisomy 21 impacts several diseases in an age-dependent manner. Thus, understanding the possible aging-related mechanisms associated with these clinical manifestations of DS will facilitate therapeutic interventions in mid-to-late adulthood, while at the same time shedding light on basic mechanisms of aging.

Pelvic landmark detection is a significant pre-task to measure the clinical measurement in pelvic abnormality analysis. Accurate pelvic landmark detection could provide reliable clinical parameter measurement results, which are helpful for doctors to diagnose and treat pelvic diseases. However, the multi-scale characteristics, temporal diversity, and pathological abnormalities of different pelvic X-rays bring enormous challenges to the landmark detection task. In order to retain strong robustness in irregular pelvic X-rays, we propose a novel, flexible two-stage framework. In the initial stage, a single neural network is employed to estimate the locations of every landmark simultaneously, enabling the identification of potential landmark regions. Then, the receptive field of candidate region proposals is expanded by 4 times through the receptive field amplification module. In the second stage, the landmark detection module fuses semantically rich features at different scales through a multi-scale semantic fusion module. So that the framework can fully learn the strongly relevant semantic information around the landmark at high resolution. We collected a data set of 430 pelvic X-rays, including a large number of irregular pelvic X-rays, to evaluate our framework. The experimental results demonstrate that our framework achieves a state-of-the-art detection mean radial error of 3.724 ± 4.247-mm. The experimental results show that the proposed method can help doctors quickly and accurately find the characteristic points of the pelvis and could be applied to clinical diagnosis.

Abstract Here, we investigate the precoding schemes for the downlink data transmission of a time‐division duplex cell‐free massive multiple‐input multiple‐output (MIMO) system with channel aging, which arises from the user mobility. Closed‐form spectral efficiency (SE) expressions of the downlink with the normalized conjugate beamforming (NCB), and the full‐pilot zero‐forcing (FZF), are derived, which are used for the analytical system performance evaluation. Then, a novel combinatorial precoding scheme with enhanced system SE performance, which adopts either NCB or FZF according to each user channel aging condition, is proposed. Moreover, a pilot allocation strategy is proposed to alleviate the extra interference brought by the combinatorial precoding scheme. Also, a statistical channel cooperative power control is employed to further improve the performance for all the above precoding schemes. Numerical results show that the proposed precoding scheme can substantially improve the average downlink SE.

Ultrasound (US) is widely used in the clinical diagnosis and treatment of musculoskeletal diseases. However, the low efficiency and non-uniformity of artificial recognition hinder the application and popularization of US for this purpose. Herein, we developed an automatic muscle boundary segmentation tool for US image recognition and tested its accuracy and clinical applicability. Our dataset was constructed from a total of 465 US images of the flexor digitorum superficialis (FDS) from 19 participants (10 men and 9 women, age 27.4 ± 6.3 years). We used the U-net model for US image segmentation. The U-net output often includes several disconnected regions. Anatomically, the target muscle usually only has one connected region. Based on this principle, we designed an algorithm written in C++ to eliminate redundantly connected regions of outputs. The muscle boundary images generated by the tool were compared with those obtained by professionals and junior physicians to analyze their accuracy and clinical applicability. The dataset was divided into five groups for experimentation, and the average Dice coefficient, recall, and accuracy, as well as the intersection over union (IoU) of the prediction set in each group were all about 90%. Furthermore, we propose a new standard to judge the segmentation results. Under this standard, 99% of the total 150 predicted images by U-net are excellent, which is very close to the segmentation result obtained by professional doctors. In this study, we developed an automatic muscle segmentation tool for US-guided muscle injections. The accuracy of the recognition of the muscle boundary was similar to that of manual labeling by a specialist sonographer, providing a reliable auxiliary tool for clinicians to shorten the US learning cycle, reduce the clinical workload, and improve injection safety.

IntroductionStroke-associated pneumonia (SAP) is a common complication of stroke that can increase the mortality rate of patients and the burden on their families. In contrast to prior clinical scoring models that rely on baseline data, we propose constructing models based on brain CT scans due to their accessibility and clinical universality.MethodsOur study aims to explore the mechanism behind the distribution and lesion areas of intracerebral hemorrhage (ICH) in relation to pneumonia, we utilized an MRI atlas that could present brain structures and a registration method in our program to extract features that may represent this relationship. We developed three machine learning models to predict the occurrence of SAP using these features. Ten-fold cross-validation was applied to evaluate the performance of models. Additionally, we constructed a probability map through statistical analysis that could display which brain regions are more frequently impacted by hematoma in patients with SAP based on four types of pneumonia.ResultsOur study included a cohort of 244 patients, and we extracted 35 features that captured the invasion of ICH to different brain regions for model development. We evaluated the performance of three machine learning models, namely, logistic regression, support vector machine, and random forest, in predicting SAP, and the AUCs for these models ranged from 0.77 to 0.82. The probability map revealed that the distribution of ICH varied between the left and right brain hemispheres in patients with moderate and severe SAP, and we identified several brain structures, including the left-choroid-plexus, right-choroid-plexus, right-hippocampus, and left-hippocampus, that were more closely related to SAP based on feature selection. Additionally, we observed that some statistical indicators of ICH volume, such as mean and maximum values, were proportional to the severity of SAP.DiscussionOur findings suggest that our method is effective in classifying the development of pneumonia based on brain CT scans. Furthermore, we identified distinct characteristics, such as volume and distribution, of ICH in four different types of SAP.