Advancing quinoa(Chenopodium quinoa Willd.) quality assessment using hyperspectral imaging.

The fault of the power grid transmission line itself or the foreign matter caught in it will pose a potential threat to the power system. Efficient anomaly detection is the key to maintain the stability of modern transmission systems. At present, the increasing demand for edge computing equipment makes it a trend to develop lightweight and efficient power grid anomaly detection methods. To deal with the practical demands of power grid anomaly detection, this paper brings the LPGANet, a lightweight model designed to achieve high accuracy while enhancing detection efficiency. The model is integrated with dynamic snake convolution (DSConv) and spatial-channel reconstruction convolution (SCConv) to increase multi-scale feature extraction and fusion and cut computational cost. In addition, An EMA method is adopted to enhance the concentration on foreground and reduce the impact of background. We release a new dataset containing 6,200 images of typical power grid anomalies such as broken strands, scattered strands, and other floating suspensions. The experimental results on the dataset demonstrate that LPGANet achieves the best accuracy, highest efficiency, and best comprehensive performance compared with other object detection methods. In addition, the effectiveness of the system under computational resource limitation is also verified in the deployment on Jetson AGX Orin edge devices.

Central lumbar spinal stenosis, a prevalent degenerative spinal disorder, severely impacts the quality of life for those affected. Axial and sagittal MRI images offer diverse information on tissue structure and lesions, which is crucial for accurate diagnosis. However, MRI-based diagnostic approaches still have poor lesion localization, insufficient cross-view alignment, underutilization of multi-view MRI information, and limited generalization across patient variability. To address these problems, we proposed an Encompassing Lumbar Central Spinal Stenosis Grading Model via Multi-view MRI Image Fusion called ELSG-MF. ELSG-MF consists of three stages: the first stage utilizes the extraction of robust pseudo-labels through a contrast-driven consistency reinforcement technique to guide Med-SAM in localizing and segmenting spinal tissue components. The Sagittal-Axial Pairing (SAP) Algorithm was developed by stage2 to integrate the spatial anatomical relationship between the vertebral body and the intervertebral disc, facilitating the correlation pairing between sagittal and axial images. Stage3 subsequently innovated the multi-view Adaptive Fusion (M²AF) module, which enables adaptive dynamic fusion of anatomical features across views. M²AF enhances the extraction of contextual complementary information, and significantly improves the model's capacity to detect subtle variations in the degree of narrowness. A series of studies show that our model achieves an overall accuracy of 0.8631, AUC of 0.96, and F1-score of 0.8614. These results indicate that our model substantially outperforms mainstream approaches, attaining superior segmentation and grading accuracy, exhibiting robust generalization and clinical application potential.

Ewing sarcoma (ES) is a rare aggressive neoplasm that is the second most common primary bone tumor of childhood and adolescence, with less frequent extraskeletal presentations. ES with EWSR1::FEV translocation is extremely rare and is characterized by extraskeletal location, varying morphology and immunophenotype, and an aggressive clinical course. We present a prostatic ES confirmed by EWSR1::FEV fusion, detailing its clinical presentation, histopathologic and immunophenotypic features, molecular profile, and management. A man in his mid-50s presented with urinary frequency and difficulty voiding. Imaging revealed a 4.4 cm prostatic mass with bladder invasion and right iliac lymphadenopathy. Serum PSA was within normal limits. Biopsy demonstrated a poorly differentiated epithelioid neoplasm with neuroendocrine features. Immunohistochemistry showed strong expression of keratins AE1/3 and CAM5.2, chromogranin, synaptophysin, NKX2.2, and CD99 (weak), while PSA was negative. NKX3.1 was focally positive in rare tumor cells and Ki67 was approximately 35%. Perineural invasion and intraductal spread were noted. The tumor was initially interpreted as poorly differentiated carcinoma with neuroendocrine features. The patient underwent radical prostatectomy, revealing a 5.5 cm tumor with perineural and lymphovascular invasion, and nodal metastasis. Next-generation sequencing confirmed an EWSR1::FEV fusion, establishing the diagnosis of ES. Immunostain for androgen receptor was strongly and diffusely positive in the primary tumor and in the nodal metastasis, which together with focal staining for NKX3.1 were suggestive of primary prostatic origin and invited consideration of androgen deprivation therapy. This report highlights a rare prostatic Ewing-family sarcoma harboring an EWSR1::FEV fusion and immunophenotypic features that mimic a neuroendocrine carcinoma.

Efficient and accurate image segmentation models play a vital role in medical image segmentation, however, high computational cost of traditional models limits clinical deployment. Based on pyramid visual transformers and convolutional neural networks, this paper proposes a lightweight Context Contrast Enhancement Network (CCE-Net) that ensures efficient inference and achieves accurate segmentation through the contextual feature synergy mechanism and feature contrast enhancement strategy. The Local Context Fusion Enhancement module is designed to obtain more specific local detail information through cross-layer context fusion and bridge the semantic gap between the encoder and decoder. The Deep Feature Multi-scale Extraction module is proposed to fully extract the comprehensive information about the deepest features in the bottleneck layer of the model and provide more accurate global contextual features for the decoder. The Detail Contrast Enhancement Decoder module is designed to effectively solve the inherent problems of missing image details and blurred edges through adaptive dual-branch feature fusion and frequency-domain contrast enhancement operations. Experiments show that CCE-Net only requires 5.40M parameters and 0.80G FLOPs, and the average Dice coefficients on the Synapse and ACDC datasets are 82.25% and 91.88%, respectively, which are 37%-62% less than the parameters of mainstream models, promoting the transformation of lightweight medical AI models from laboratory research to clinical practice.

Yunnan Jiama (paper horse prints), a representative form of intangible cultural heritage in southwest China, is characterized by subtle inter-class differences, complex woodblock textures, and heterogeneous preservation conditions, which collectively pose significant challenges for digital preservation and automatic image classification. To address these challenges and improve the computational analysis of Jiama images, this study proposes an enhanced object detection framework based on YOLOv8 integrated with a Global Attention Mechanism (GAM), referred to as YOLOv8-GAM. In the proposed framework, the GAM module is embedded into the high-level semantic feature extraction and multi-scale feature fusion stages of YOLOv8, thereby strengthening global channel–spatial interactions and improving the representation of discriminative cultural visual features. In addition, image augmentation strategies, including brightness adjustment, salt-and-pepper noise, and Gaussian noise, are employed to simulate real-world image acquisition and degradation conditions, which enhances the robustness of the model. Experiments conducted on a manually annotated Yunnan Jiama image dataset demonstrate that the proposed model achieves a mean average precision (mAP) of 96.5% at an IoU threshold of 0.5 and 82.13% under the mAP@0.5:0.95 metric, with an F1-score of 94.0%, outperforming the baseline YOLOv8 model. These results indicate that incorporating global attention mechanisms into object detection networks can effectively enhance fine-grained classification performance for traditional folk print images, thereby providing a practical and scalable technical solution for the digital preservation and computational analysis of intangible cultural heritage.

Nocturnal non-speech sounds encapsulate critical physiological and behavioral information, making them a valuable modality for non-invasive assessment of sleep quality. Despite this potential, existing approaches predominantly rely on single-view spectral features or shallow learning architectures, limiting their ability to generalize across diverse acoustic patterns. To overcome these limitations, this study proposes a hybrid deep learning architecture tailored for the classification of seven distinct nocturnal sound categories. The system employs a tri-branch design that independently processes Mel-frequency cepstral coefficients (MFCC), Mel-spectrogram, and constant-Q transform (CQT)-spectrogram representations. Each branch passes through a dedicated pipeline comprising convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM) layers, and attention-equipped vision transformers (ViT). This configuration facilitates hierarchical learning of local, temporal, and global contextual features. The softmax outputs of each branch are fused using a stacking ensemble strategy, with an XGBoost-based meta-classifier performing the final decision integration. A complementary weighted ensemble is also implemented for comparative evaluation. Experimental results on a publicly available seven-class non-speech sound dataset demonstrate the proposed model’s outstanding performance, achieving 99.71% accuracy under 10-fold cross-validation, along with consistently high precision, recall, and F1-scores across all classes. Comparative benchmarks show substantial improvements over existing state-of-the-art models, including CNNs, long short-term memory (LSTM) variants, classical machine learning approaches, and metaheuristic-based ensembles. Supporting analyses such as confidence score distributions and dimensionality reduction visualizations (principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE)) further validate the model’s robustness and discriminative power. These findings highlight the effectiveness of integrating multi-spectral representations, deep hierarchical modeling, and ensemble strategies for high-fidelity nocturnal non-speech sound classification.

ABSTRACT Shallow marine environments are critical transition zones between land and sea and exhibit dynamic, spatially heterogeneous seafloor sediments. Conventional single-source acoustic mapping using multibeam echosounder (MBES) or side-scan sonar (SSS) often fails to fully capture this complexity because of survey-orientation effects and instrument-related limitations. To address these challenges, this study proposes a multisource acoustic seafloor mapping framework that integrates MBES bathymetry and SSS intensity data for improved sediment classification in shallow reef environments. A spatial coregistration approach is applied to align MBES and SSS datasets by extracting common feature points and using a high-precision transformation model. A multiscale–multidirectional (MS–MD) feature extraction strategy is then developed by combining bathymetric and acoustic texture features. The Relief-F algorithm is employed to optimize feature selection and reduce redundancy. Five supervised classifiers—Random Forest (RF), K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Random Under-Sampling Boosting (RUS Boost), and Broad Learning System (BLS)—are evaluated. Results show that under the MS–MD feature strategy, the RF model achieves an overall accuracy of 98.26% using fused multisource data, outperforming the MBES-only RF baseline (96.96%). Other classifiers show consistent improvements under the same strategy. In addition to accuracy gains, multisource fusion produces sediment maps with improved spatial coherence and clearer transitional boundaries. Overall, the proposed framework demonstrates the potential of multisource acoustic integration and machine-learning-based classification for high-resolution benthic habitat mapping in complex shallow-water environments.

MediFlora-Net: Quantum-enhanced deep learning for precision medicinal plant identification.

Recommending Move Method Refactoring Opportunities Based on Feature Fusion and Deep Learning

YMAD: An efficient poultry gender classification method based on feature fusion and YOLO model

DeepCut++: Graph-based unsupervised segmentation with feature fusion and diffusion learning

XP-GCN: Extreme learning machines and parallel graph convolutional networks for high-throughput prediction of blood-brain barrier penetration based on feature fusion.

GAN-based novel feature selection approach with hybrid deep learning for heartbeat classification from ECG signal.

A data-driven digital twin model for bridge health monitoring using feature fusion and unsupervised deep learning

GL-mamba-net: A magnetic resonance imaging restoration network with global-local mamba.

Fusion of deep feature and apparent feature for flotation grade prediction based on apparent information guidance encoder–decoder network

Manual acupuncture manipulation recognition model with a multimodal fusion of tactile and visual features

Multimodal fusion of CT features and density for rapid prediction of raw-coal ash

Deep feature representations and fusion strategies for speech emotion recognition from acoustic and linguistic modalities: A systematic review