Explore the vast range of titles available.

Background Autism spectrum disorders (ASD) imply a spectrum of symptoms rather than a single phenotype. ASD could affect brain connectivity at different degree based on the severity of the symptom. Given their excellent learning capability, graph neural networks (GNN) methods have recently been used to uncover functional connectivity patterns and biological mechanisms in neuropsychiatric disorders, such as ASD. However, there remain challenges to develop an accurate GNN learning model and understand how specific decisions of these graph models are made in brain network analysis. Results In this paper, we propose a graph attention network based learning and interpreting method, namely GAT-LI, which learns to classify functional brain networks of ASD individuals versus healthy controls (HC), and interprets the learned graph model with feature importance. Specifically, GAT-LI includes a graph learning stage and an interpreting stage. First, in the graph learning stage, a new graph attention network model, namely GAT2, uses graph attention layers to learn the node representation, and a novel attention pooling layer to obtain the graph representation for functional brain network classification. We experimentally compared GAT2 model’s performance on the ABIDE I database from 1035 subjects against the classification performances of other well-known models, and the results showed that the GAT2 model achieved the best classification performance. We experimentally compared the influence of different construction methods of brain networks in GAT2 model. We also used a larger synthetic graph dataset with 4000 samples to validate the utility and power of GAT2 model. Second, in the interpreting stage, we used GNNExplainer to interpret learned GAT2 model with feature importance. We experimentally compared GNNExplainer with two well-known interpretation methods including Saliency Map and DeepLIFT to interpret the learned model, and the results showed GNNExplainer achieved the best interpretation performance. We further used the interpretation method to identify the features that contributed most in classifying ASD versus HC. Conclusion We propose a two-stage learning and interpreting method GAT-LI to classify functional brain networks and interpret the feature importance in the graph model. The method should also be useful in the classification and interpretation tasks for graph data from other biomedical scenarios.

Heavy plate steels with bainitic microstructures are widely used in industry due to their good combination of strength and toughness. However, obtaining optimal mechanical properties is often challenging due to the complex bainitic microstructures and multiple phase constitutions caused by different cooling rates through the plate thickness. Here, both conventional and advanced microstructural characterization techniques which bridge the meso- and atomic-scales were applied to investigate how microstructure/mechanical property-relationships of a low-carbon low-alloyed steel are affected by phase transformations during continuous cooling. Mechanical tests show that the yield strength increases monotonically when cooling rates increase up to 90 K/s. The present study shows that this is associated with a decrease in the volume fraction of polygonal ferrite (PF) and a refinement of the substructure of degenerated upper bainite (DUB). The fine DUB substructures feature C-rich retained austenite/martensite-austenite (RA/M-A) constitutes which decorate the elongated micrograin boundaries in ferrite. A further increase in strength is observed when needle-shaped cementite precipitates form during water quenching within elongated micrograins. Pure martensite islands on the elongated micrograin boundaries lead to a decreased ductility. The implications for thick section plate processing are discussed based on the findings of the present work.

ObjectiveAdjuvant treatment remains a controversial issue for intermediate-risk cervical cancer. The aim of this study was to compare the prognosis of patients who underwent no adjuvant treatment, pelvic radiotherapy alone, or concurrent chemoradiotherapy after radical hysterectomy for intermediate-risk, early-stage cervical cancer.MethodsPatients with stage IB1–IIA2 (FIGO 2009) cervical squamous cell carcinoma treated with radical hysterectomy and pelvic lymph node dissection, with negative lymph nodes, surgical margins, or parametria, who had combined intermediate risk factors as defined in the Gynecologic Oncology Group trial (GOG-92; Sedlis criteria) were included in the study. Recurrence-free survival and disease-specific survival were compared.ResultsOf 861 patients included in the analysis, 85 patients received no adjuvant treatment, 283 patients were treated with radiotherapy, and 493 patients with concurrent chemoradiotherapy. After a median follow-up of 63 months (IQR 45 to 84), adjuvant radiotherapy or concurrent chemoradiotherapy was not associated with a survival benefit compared with no adjuvant treatment. The 5-year recurrence-free survival and corresponding disease-specific survival were 87.1%, 84.2%, 89.6% (p=0.27) and 92.3%, 87.7%, 91.4% (p=0.20) in the no adjuvant treatment, radiotherapy alone, and concurrent chemoradiotherapy groups, respectively. Lymphovascular space invasion was the only independent prognostic factor for both recurrence-free survival and disease-specific survival. Additionally, significant heterogeneity exists in Sedlis criteria: higher risk of relapse (HR=1.88; 95% CI 1.19 to 2.97; p=0.007) and death (HR=2.36; 95% CI 1.41 to 3.95; p=0.001) occurred in patients with lymphovascular space invasion and deep 1/3 stromal invasion compared with no lymphovascular space invasion, middle or deep 1/3 stromal invasion, and tumor diameter ≥4 cm.ConclusionsRadical hysterectomy alone without adjuvant treatment may achieve a favorable survival for patients with intermediate-risk cervical cancer as defined by Sedlis criteria. Criteria for adjuvant treatment in patients without high risk factors need to be further evaluated.

Bronchitis obliterans is a major complication of Mycoplasma pneumoniae pneumonia (MPP) with bronchial casts. This retrospective study aimed to identify predictors of pediatric bronchitis obliterans (PBO) in patients with mycoplasma pneumoniae pneumonia (MPP) complicated by bronchial casts. We screened 236 hospitalized children with MPP and bronchial casts on bronchoscopy between June 2018 and June 2023, of whom 197 were included in the analysis, including 49 with PBO and 148 without PBO. The clinical features, laboratory data, radiological findings, and bronchoscopic features of the children in the PBO and non-PBO groups were compared. Children in the PBO group had a significantly higher incidence of pleural effusion, more severe radiological abnormalities, and higher C-reactive protein level, white blood cell count, erythrocyte sedimentation rate (ESR), and immunoglobulin M level than those in non-PBO group. Additionally, children in the PBO group were more likely to have delayed bronchoscopy (> 13.5 days). Multivariable logistic regression analysis revealed that ESR > 57.5 mm/h (OR: 3.833, P  = 0.001), pulmonary consolidation > 2/3 of a lobe (OR: 2.453, P  = 0.036) and delayed bronchoscopy (OR 5.827, P  < 0.001) were significant predictors of PBO in patients with MPP complicated by bronchial casts.These three indicators combined had a sensitivity of 0.571, specificity of 0.885, and area under the curve of 0.766 for predicting PBO.

Deep learning models have been successfully applied to the analysis of various functional MRI data. Convolutional neural networks (CNN), a class of deep neural networks, have been found to excel at extracting local meaningful features based on their shared-weights architecture and space invariance characteristics. In this study, we propose M2D CNN, a novel multichannel 2D CNN model, to classify 3D fMRI data. The model uses sliced 2D fMRI data as input and integrates multichannel information learned from 2D CNN networks. We experimentally compared the proposed M2D CNN against several widely used models including SVM, 1D CNN, 2D CNN, 3D CNN, and 3D separable CNN with respect to their performance in classifying task-based fMRI data. We tested M2D CNN against six models as benchmarks to classify a large number of time-series whole-brain imaging data based on a motor task in the Human Connectome Project (HCP). The results of our experiments demonstrate the following: (i) convolution operations in the CNN models are advantageous for high-dimensional whole-brain imaging data classification, as all CNN models outperform SVM; (ii) 3D CNN models achieve higher accuracy than 2D CNN and 1D CNN model, but 3D CNN models are computationally costly as any extra dimension is added in the input; (iii) the M2D CNN model proposed in this study achieves the highest accuracy and alleviates data overfitting given its smaller number of parameters as compared with 3D CNN.

In aquaculture, underwater instance segmentation methods offer precise individual identification and counting capabilities. However, due to the inherent unique optical characteristics and high noise in underwater imagery, existing underwater instance segmentation models struggle to accurately capture the global and local feature information of objects, leading to generally lower detection accuracy in underwater instance segmentation models. To address this issue, this study proposes a novel Channel Space Coordinates Attention (CSCA) attention module and a Channel A Prior Attention Fusion (CAPAF) feature fusion module, aiming to improve the accuracy of underwater instance segmentation. The CSCA module effectively captures local and global information by combining channel and spatial attention weight, while the CAPAF module optimizes feature fusion by removing redundant information through learnable parameters. Experimental results demonstrate significant improvements when these two modules are applied to the YOLOv8 model, with the mAP@0.5 metric increasing by 3.2% and 2% on the UIIS underwater instance segmentation dataset. Furthermore, the instance segmentation accuracy is significantly improved on the UIIS and USIS10K datasets after these two modules are applied to other networks.

Semiconductor lasers operating at the 730 nm peak wavelength have diverse applications, including biomedical diagnostics, agricultural lighting, and high-precision sensing. However, quantum well (QW) materials, commonly employed at this wavelength, often fail to simultaneously meet the dual requirements of lattice matching and bandgap alignment. In this study, GaAsP/AlGaInP large strain compensation QW with lattice mismatches of −7.533‰ and 1.112‰ was developed. Strain compensation was utilized to address the lattice mismatch while ensuring lasing action at 730 nm. Based on this, the impact of waveguide design, particularly graded and asymmetric waveguides, on the power output was explored. Additionally, the relationship between the doping profile of the device and lasing efficiency was investigated. The completed 100 μm wide semiconductor edge-emitting laser (EEL) achieved 730 nm continuous wave laser with 1 W output power at 2 A current. This study proposes an approach to enhance the lasing power and optoelectronic conversion efficiency of lasers and provide valuable solutions for their practical applications.

Objective This study was performed to analyze 22 cases of Mycoplasma pneumoniae pneumonia (MPP) associated with bronchial casts (BCs) in children. Methods We retrospectively reviewed all cases of MPP in children treated at our institution from November 2015 to December 2016. Demographic information, laboratory parameters, radiologic and fiberoptic bronchoscopy findings, treatment outcomes, and follow-up results were analyzed. Results Among 161 patients with MPP, 22 had BCs and 139 had no BCs. All BCs occurred in a segmental or subsegmental bronchus and were removed by fiberoptic bronchoscopy. Patients with BCs had a longer duration of fever after admission and higher incidence of refractory MPP. Substantially more children with than without BCs had a high M. pneumoniae load in the bronchoalveolar lavage fluid. All patients with BCs but only 55.4% without BCs were given methylprednisolone in addition to the standard antibiotic treatment. A significantly higher proportion of children with than without BCs received oxygen therapy. After discharge, complete radiological resolution took significantly longer in children with than without BCs. Conclusions In children with MPP, prompt removal of BCs may be necessary to prevent BC propagation. MPP with BCs is more severe than that without BCs, and treatment and recovery are more difficult.

Titanium dioxide (TiO2) is of great interest as anode material for lithium-ion batteries (LIBs) because of its safety, structure stability, and low cost. However, the limitations of low conductivity and small theoretical capacity prevent its further applications. Herein, TiO2 nanospheres with a hollow structure (H-TiO2) were successfully synthesized via a hard-template method. The resultant material used as LIBs anode with superior lithium storage properties in terms of high initial capacity (∼289 mA h g−1 at 0.1 A g−1), good rate capability (∼101 mA h g−1 at 2 A g−1), and excellent cycling stability (∼196 mA h g−1 was retained over 300 cycles at 0.1 A g−1). The improved performances are attributed to the large specific area (~225 m2 g−1) and abundant mesoporous of the hollow structure, which can not only promote the diffusion of Li+ and e− but also achieve an increase in the contact area between electrodes and electrolyte.

In intertidal mudflat culture (IMC), the fishing efficiency and the degree of damage to nature have always been a pair of irreconcilable contradictions. To improve the efficiency of razor clam fishing and at the same time reduce the damage to the natural environment, in this study, a razor clam burrows dataset is established, and an intelligent razor clam fishing method is proposed, which realizes the accurate identification and counting of razor clam burrows by introducing the object detection technology into the razor clam fishing activity. A detection model called intertidal mudflat culture-You Only Look Once (IMC-YOLO) is proposed in this study by making improvements upon You Only Look Once version 8 (YOLOv8). In this study, firstly, at the end of the backbone network, the Iterative Attention-based Intrascale Feature Interaction (IAIFI) module module was designed and adopted to improve the model’s focus on advanced features. Subsequently, to improve the model’s effectiveness in detecting difficult targets such as razor clam burrows with small sizes, the head network was refactored. Then, FasterNet Block is used to replace the Bottleneck, which achieves more effective feature extraction while balancing detection accuracy and model size. Finally, the Three Branch Convolution Attention Mechanism (TBCAM) is proposed, which enables the model to focus on the specific region of interest more accurately. After testing, IMC-YOLO achieved mAP50, mAP50:95, and F1best of 0.963, 0.636, and 0.918, respectively, representing improvements of 2.2%, 3.5%, and 2.4% over the baseline model. Comparison with other mainstream object detection models confirmed that IMC-YOLO strikes a good balance between accuracy and numbers of parameters.