Search Results (353)

Background/Objectives: Dental metallic implants cause severe streaking artifacts in kilovoltage CT (kVCT), compromising dose calculation in radiotherapy (RT) treatment planning. The purpose of this study is to assess the dosimetric agreement of synthetic MVCT (sMVCT) images generated from artifact-affected kVCT using a deep learning network with respect to true MVCT (tMVCT) acquired at the treatment machine. Methods: Nineteen head and neck cancer patients with dental metallic implants treated with RT were included. Planning kVCT images were converted to sMVCT using Metal Artifact Reduction through Domain Transformation Network (MAR-DTN), a UNet-inspired deep learning network. The sMVCT images were rigidly registered to true MVCT (tMVCT) acquired on the Hi-Art II Tomotherapy system. Mean Hounsfield Unit (HU) values were compared across seven structures (thyroid, bilateral parotids, brainstem, spinal cord, GTV, PTV70) using pairwise Wilcoxon tests and Two One-Sided Tests (TOST) for statistical equivalence within a pre-specified margin of ±20 HU (corresponding to a 2% deviation in physical density). Dose distributions were recalculated on sMVCT using the AAA algorithm and compared to reference tMVCT-based plans via dose–volume histogram (DVH) metrics, evaluated for equivalence by TOST within a margin of ±2% of the prescribed dose (±142 cGy of 70.95 Gy), and via 3D gamma index, evaluated by one-sided non-inferiority test against the clinically accepted thresholds of 90% (2 mm/2%) and 95% (3 mm/3%). A pre-specified sensitivity analysis was performed by repeating all comparisons on the strictly independent sub-cohort (n = 16) excluding three patients drawn from the MAR-DTN training set. Results: All seven anatomical structures showed statistical equivalence between sMVCT and tMVCT under the ±20 HU margin (TOST p < 0.05; mean HU differences in the range −1.1 to +8.4 HU; all Wilcoxon p > 0.05). All nine DVH metrics achieved formal dosimetric equivalence within ±2% of the prescribed dose (TOST p < 0.05). Mean 3D gamma pass rates were 94.3% (95% CI: 89.3–97.1) for the 2 mm/2% criterion and 97.6% (95% CI: 94.8–99.0) for the 3 mm/3% criterion, both formally non-inferior to the respective clinical thresholds (p < 0.0001). Residual gamma failures were concentrated at the patient surface, consistent with inter-session repositioning uncertainty rather than errors in synthetic image generation. Sensitivity analysis on the n = 16 sub-cohort confirmed all conclusions, with mean HU and DVH differences smaller than in the full cohort for the structures showing the largest mean differences, and comparable for the remaining structures, with all TOST equivalence and gamma non-inferiority tests confirmed in both cohorts. Conclusions: sMVCT images generated via MAR-DTN show dosimetric agreement with physically acquired tMVCT in head and neck patients with dental implants, formally demonstrated by TOST equivalence within ±2% of prescribed dose for all DVH metrics. The combined HU and gamma index framework presented here represents a promising quality assurance approach for AI-based synthetic imaging tools in radiotherapy, pending validation in larger prospective multicentre cohorts. Full article

Forest fires cause severe ecological and economic losses, so timely and accurate detection becomes crucial for effective prevention and control. Edge devices with intelligent algorithms can detect forest fires in real time. Current deep learning algorithms can achieve high accuracy, but they are not suitable for edge devices because they require substantial computing resources. To address this issue, this study proposes a real-time lightweight forest fire detection network (RLFNet) improved from YOLOv11n, with three key enhancements to the backbone, neck, and head. (1) A Parallel Multi-Scale Extraction Block (PMEB) improves C3k2 with a dual-branch parallel strategy to enhance multi-scale feature extraction efficiency; (2) a Bidirectional Cross Fusion Module (BCFM) replaces simple Concat with a context-aware cross-gating mechanism to suppress background noise and reduce false alarms; and (3) a Faster Inference Detection Head (FIDH) leverages structural re-parameterization and group normalization to boost inference efficiency while reducing parameters. In addition, a Layer-Adaptive Magnitude-based Pruning (LAMP) strategy is applied to further improve model’s computational efficiency. Experimental results on the self-constructed Diverse Fire Scenario (DFS) dataset demonstrate that RLFNet reduces parameters and GFLOPs by 25.2% and 20.6%, boosts mAP50 by 5.3%, and achieves an inference speed of 225 FPS, attaining the best accuracy and speed among the compared models. Validation on a public remote sensing dataset further confirms its strong generalization. These results indicate that RLFNet provides a high efficiency and lightweight solution for edge devices to real-time detect forest fires. Full article

To address the dual challenges of discriminating weeds from rice seedlings for precision weed management operations, such as targeted spraying and robotic weeding, in complex paddy-field scenes and deploying high-precision models on resource-limited edge devices, we propose DGS-Net, a deformable attention, GSConv-based feature fusion, and SEAM-enhanced lightweight network based on YOLOv11n. The backbone incorporates a convolutional block with parallel split attention and deformable attention transformer (C2PSA_DAT) module to improve the extraction of irregular and fine-grained weed features, the neck integrates a VoV-GSCSP module to enable lightweight multi-scale feature fusion for small and densely distributed targets, and a separated and enhancement attention module (SEAM) is placed before the detection head to enhance robustness under leaf occlusion and complex paddy-field background interference. In comparative experiments conducted on the paddy-field dataset under unified training and evaluation settings, DGS-Net achieved 91.7% precision, 86.8% recall, and 92.4% mean average precision (mAP), with a model size of 5.8 MB and a computational cost of 6.2 giga floating-point operations (GFLOPs). Compared with representative lightweight baseline detectors, DGS-Net showed a more favorable balance between detection accuracy and deployment efficiency. In additional edge-device deployment tests using the test set, the model sustained real-time inference at 32.5 FPS and achieved mAP@0.5, precision, and recall of approximately 0.928, 0.919, and 0.867, respectively. Overall, DGS-Net improves irregular feature extraction, enables lightweight multi-scale feature fusion, and increases robustness to occlusion while retaining strong deployability. The method therefore provides practical visual-perception support for precise, real-time crop–weed discrimination and precision weed management in complex paddy-field environments. Full article

Background: The very-low-calorie ketogenic diet (VLCKD) is increasingly used before bariatric surgery (BS), but its effects on surgical and long-term outcomes remain unclear. Objective: The aim of this study was to compare the impact of a 4-week VLCKD with a 4-week low-calorie diet (LCD) on preoperative, perioperative and postoperative outcomes for up 12 months in patients undergoing BS. Methods: In this prospective study, 72 (n = 36: VLCKD; n = 36: LCD) patients (mean age 43.2 ± 10.6 years; BMI 45.6 ± 6.4 kg/m²; 87.5% female) submitted to sleeve gastrectomy were enrolled at a tertiary care center from 2022 to 2024. Results: No adverse events were detected with both diets. The VLCKD was associated with a greater preoperative median weight loss percentage (−5.5 vs. −2.6 kg, p < 0.001), BMI reduction (−2.6 vs. −1.2 kg/m², p < 0.001), shorter hospital stay (3.0 ± 0.2 vs. 3.4 ± 0.9 days, p = 0.017), higher day-1 postoperative hemoglobin (12.7 ± 1.3 vs. 12.0 ± 1.2 g/dL, p = 0.024), and lower day-1 postoperative median C-reactive protein levels (9.7 vs. 13.4 mg/L, p = 0.042). These associations were confirmed in a multiple regression model, after adjustments for BMI at enrolment, age and sex. After 6 months, the VLCKD was associated with greater reductions in mean weight loss percentage (−24.9 ± 7.8 vs. −19.6 ± 9.4 kg, p = 0.012), BMI reduction (−11.7 ± 4.4 vs. −8.7 ± 3.9 kg/m², p = 0.003), neck circumference (−4.9 vs. −3.6 cm, p = 0.027) and lower aminotransferase levels. At 12 months, VLCKD patients maintained significant advantages over the same variables, except for neck circumference. Conclusions: A short preoperative VLCKD was safe and was associated with greater short-term weight reduction compared with the LCD, with potential benefits extending to early postoperative recovery and 1-year outcomes. Full article

According to the National Cancer Institute, approximately 3.9 billion people worldwide suffer from non-communicable oral diseases, with head and neck cancer patients experiencing exacerbated oral mucositis primarily from radiotherapy. This condition manifests as painful, debilitating mucosal lesions, necessitating effective antimicrobial interventions. This study developed and characterized stable mouthwash formulations containing green-synthesized silver nanoparticles (AgNPs) derived from Baccharis trimera (carqueja) extract for the management of oral mucositis, evaluating their physicochemical stability, antimicrobial efficacy, and biosafety. AgNPs formation was confirmed by color change to brown and a surface plasmon resonance band at 407 nm (UV-Vis), with dynamic light scattering revealing a monomodal hydrodynamic diameter of ~25 nm and stable dispersion; scanning electron microscopy showed spherical particles of 25–35 nm. Four formulations (22–85 ppm AgNPs) in a commercial vehicle exhibited excellent stability over 60 days at 5 °C and 25 °C, maintaining near-neutral pH (~7), low surface tension (<5 mN/m), and unchanged spectral profiles, with no phase separation under centrifugation or thermal stress (up to 70 °C). Antimicrobial assays via broth microdilution demonstrated broad-spectrum activity for the 85 ppm formulation: MICs of 125 µg/mL (S. epidermidis, E. faecalis), 62.5 µg/mL (E. coli, P. aeruginosa), and 250 µg/mL (S. aureus), with MBC of 125 µg/mL (bactericidal) against P. aeruginosa; no activity against C. albicans (MIC > 500 µg/mL). Against human oral microbiota (n = 4 volunteers), it reduced bacterial growth by 14–156% relative to controls (e.g., −5% to 156% inhibition). Cytogenotoxicity tests (A. cepa) confirmed non-toxicity (mitotic index 79–93% of control, low cellular alteration index). These findings establish the carqueja-mediated instant green AgNPs mouthwash as a stable, potent antimicrobial agent, poised to mitigate mucositis-related infections and enhance the quality of life of cancer patients. Full article

Background/objectives: This comprehensive study of infants with combinational deformational plagiocephaly with brachycephaly (cDPB) and combinational deformational brachycephaly with plagiocephaly (cDBP) examined the effectiveness of a custom, thermoplastic vacuum-formed cranial remolding orthosis and identified clinical predictive factors that affect treatment outcomes. In addition, a standardized classification scale for babies with combinational head shapes was developed for this study. Methods: This was a retrospective study of patients who were treated by Cranial Technologies between January 2014 and March 2025 and met the following inclusion criteria: (a) presented with a Cranial Vault Asymmetry Index (CVAI(S)) > 3.5 AND Cephalic Index (CI) > 90, (b) were compliant with the treatment protocol, (c) were nonsyndromic, and (d) did not have craniosynostosis. Infants with isolated plagiocephaly or isolated brachycephaly were excluded. Multiple linear regression (MLR) analyses and paired t-tests were used to model the effects of clinical predictive factors on CVAI(S) and CI outcomes and determine the change between pre- and post-treatment cranial anthropometric measurements, respectively. Results: N = 82,326 infants met the inclusion criteria for this study. The mean overall reduction in CVAI(S) was −3.64 (p < 0.001) and for specific age groups it was as follows: 3–4 months −5.274 (p < 0.001), 4–6 months −4.074 (p < 0.001), 6–8 months −3.262 (p < 0.001), 8–11 months −2.692 (p < 0.001), and >11 months −2.247 (p < 0.001). The mean overall reduction for CI was −3.84 (p < 0.001) and was not related to age. In terms of clinician-rated outcomes, 95–100% of babies who entered treatment at less than 6 months of age had a “good” or “great” outcome, while the “good” or “great” success rate dropped to less than 19% for babies who started treatment after 11 months of age. MLR (Adj. R²: 0.582) identified the following factors as significant predictors (p < 0.001) for change in CVAI(S): entry age (β = 0.008), left-sided plagiocephaly (β = −0.420), initial cephalic index (β = −0.056), initial CVAI(S) (β = −0.479), prematurity (β = −0.189), and the presence of torticollis or neck muscle involvement (β = 0.053). A second MLR for change in CI (Adj. R²: 0.217) observed significance (p < 0.001) for the following predictors: initial CI (β = −0.335), left-sided plagiocephaly (β = −0.332), multiple birth (β = −0.290), male sex (β = −0.158), initial CVAI(S) (β = −0.049), premature (β = −0.086), and neck muscle involvement (β = −0.106). Conclusions: CRO treatment for cDPB/cDBP resulted in highly significant improvement in both CVAI(S) and CI across all age groups with the youngest babies requiring the shortest treatment durations and demonstrating more favorable results, especially in correcting asymmetry. Overall, the mean reduction in CVAI(S) varied significantly between age groups, with younger babies experiencing greater change in CVAI(S) scores, whereas CI did not demonstrate the same relationship with entry age. This study proposed new terminology for infants who present with elements of both plagiocephaly and brachycephaly. The use of standardized terms such as cDPB/cDBP to describe a combinational head shape will enhance comparability across future studies, thus enabling better outcome reporting. Full article

Real-time detection of apple leaf diseases in orchard environments faces ongoing challenges, particularly in preserving fine-grained disease features with limited computing resources. To address these issues, we propose a high-precision lightweight model based on YOLOv10n, called YOLO-ALD. First, we introduce Spatial and Channel Reconstruction Convolution into deeper backbone networks to replace standard downsampling layers and convolutions. This suppresses spatial and channel redundancy caused by environmental noise and optimizes feature representation. Second, we design a new C2f-Faster-SimAM module for the neck network. This module combines the inference efficiency of FasterNet with a parameter-free 3D attention mechanism to adaptively focus on early lesions, effectively distinguishing them from leaf veins without increasing model complexity. Third, in the detection head section, we use the Focaler-ShapeIoU loss function to optimize bounding box regression. It utilizes a dynamic focusing mechanism and geometric constraints to ensure the localization accuracy of irregular shapes and hard-to-detect samples. Experimental results on our self-built dataset covering four specific diseases and healthy leaves showed that, compared with YOLOv10n, the mAP@0.5 of YOLO-ALD reached 92.1%, achieving a 2.1% increase. In addition, the model has an inference speed of 105 FPS, with only 2.1 M parameters and 5.6 GFLOPs. Therefore, YOLO-ALD achieves a good balance between efficiency and robustness, showing strong theoretical potential for resource-constrained mobile agriculture diagnosis. Full article

Background/Objectives: The role of muscle trigger points (TrPs) in neuropathic pain (NP) components in whiplash-associated disorders (WAD) has not been investigated. Our aim was to systematically investigate if referred pain elicited by trigger points (TrPs) in neck musculature reproduces neuropathic pain (NP) characteristics in chronic whiplash-associated disorders (WAD) and to determine the association of TrPs with pain intensity, mechanosensitivity, and disability. Methods: An exploratory cross-sectional study was conducted (n = 64; chronic WAD: n = 32; age- and sex-matched healthy controls: n = 32). TrPs in upper trapezius, suboccipital, splenius capitis, levator scapulae, scalene, and sternocleidomastoid muscles were evaluated. Pain intensity, NP components, pain catastrophizing, and disability were assessed with an 11-point numerical pain rating scale (0–10), NP questionnaires (Douleur Neuropathique 4 [DN4], self-administered Leeds Assessment of Neuropathic Symptoms and Signs [S-LANSS], and Neuropathic Pain Symptom Inventory [NSPI]), the Pain Catastrophizing Scale, and the Neck Disability Index, respectively. Mechanosensitivity (pressure pain thresholds) was assessed bilaterally over C2–C3 and C5–6 zygapophyseal joints, second metacarpal, and tibialis anterior muscle. The Mann–Whitney U test and advanced chi-square (χ²) test, including rank-based ANCOVA adjusted for age and sex, were used for comparisons between groups. Additionally, multivariate analyses were also performed (rank-based MANCOVA adjusted for age, sex, and pain intensity). Spearman’s rho (r_s) and LOESS regression analysis, corroborated with linear regression and/or polynomial regression coefficient analysis, were used to explore associations between clinical variables in WAD. Results: Significant differences in distribution of TrPs, with a significant effect of sex, were found between groups (p < 0.05). In WAD, a greater number of active TrPs, mostly prevalent in levator scapulae and suboccipital muscles, was associated with higher pain intensity, number and intensity of NP components, and disability (0.372 < r_s < 0.570, p < 0.05), or local mechanical hyperalgesia (r_s = −0.362, p < 0.05). Conclusions: Referred pain elicited by active TrPs in the neck muscles reproduced NP symptoms in chronic WAD. This study contributes to a new understanding of pain mechanisms in WAD, highlighting the role of active TrPs in generating or maintaining NP symptoms and sensitization processes. Full article

In intensive farming, contactless individual pig identification is crucial for precision feeding and health monitoring. However, real-world barn conditions—such as fluctuating illumination, severe occlusions, non-rigid poses, and high inter-individual similarity—pose significant challenges. Existing models struggle to balance high accuracy with lightweight deployment. To address this, we propose YOLO-ESO, an optimized detection framework based on YOLOv10n. YOLO-ESO introduces three core innovations: (1) integrating the C2f_ODConv module into the backbone to strengthen feature learning under complex poses via dynamic convolution; (2) redesigning the neck with a Semantics and Detail Infusion (SDI) module to improve multi-scale fusion while suppressing background noise; and (3) embedding an Efficient Multi-Scale Attention (EMA) mechanism before the detection head to capture fine-grained identity cues like texture and contours. Evaluated on a real-world pig dataset, YOLO-ESO achieves an mAP@0.5 of 96.6%, an mAP@0.5:0.95 of 71.1%, and an F1 of 92.0%. YOLO-ESO surpasses state-of-the-art detectors including YOLOv8, YOLOv11, and RT-DETR, while introducing only 8.7 GFLOPs and 3.48 million parameters. Overall, the proposed YOLO-ESO provides an accurate and lightweight solution for robust individual pig identification in complex farming environments, showing strong potential for practical deployment in precision livestock farming. Full article

A high-precision and efficient surface defect detection for printed circuit board (PCB) is critical to ensuring the reliability of electronic systems. However, the presence of complex circuit backgrounds and the small scale of defects often limit the precision and effectiveness of conventional inspection approaches. To address these challenges, this paper proposes FMW-YOLO, a lightweight and accurate detection framework based on YOLO11n. Specifically, a Frequency-Enhanced Channel-Transposed and Local Feature backbone network is developed to improve feature extraction. By designing a Dual-Frequency and Channel Attention Aggregation module and a Lightweight Edge-Gaussian Block, the original C3k2 structure is refined to suppress noise interference while preserving high-frequency details, thereby enhancing feature representation. Furthermore, a neck network incorporating a Multi-Scale Context-Aware Enhancement mechanism is constructed, in which an Attention-Integrated Feature Pyramid is employed to facilitate more effective cross-scale feature interaction. In addition, a Dilated Reparam Residual Module is embedded into the C3k2 structure to expand the receptive field without significantly increasing computational burden. Finally, Wise-IoU is adopted to optimize bounding box regression by assigning greater importance to anchors of moderate quality. Extensive experiments conducted on the HRIPCB and DeepPCB datasets demonstrate that FMW-YOLO improves mAP50 by 2.1% and 0.3%, respectively, while reducing the number of parameters by 23%. These results indicate that the proposed method achieves improved detection accuracy and demonstrates strong potential for practical industrial applications. Full article

Accurate identification of plant numbers is crucial for evaluating the effectiveness of mechanical rice seedling transplanting, which directly affects yield estimation and replanting decisions in precision agriculture. Conventional manual counting methods are time-consuming and labor-intensive, which hinders their application in modern agriculture, where efficiency and precision are paramount. Therefore, this study constructed a dataset based on images collected by consumer-grade Unmanned Aerial Vehicles (UAVs) and proposed an improved lightweight detection model named CLR-YOLO (Complex-scene Lightweight Rice-detection YOLO) based on the YOLOv11n. The model replaces the original C3k2 module with C3k2-PConv to improve computational efficiency while maintaining feature extraction capability. Additionally, it reconstructs the neck network using the Heterogeneous Selective Feature Pyramid Network (HSFPN) to optimize the handling of features from both large and small targets. Finally, the PConvHead detection head is designed to enhance feature utilization efficiency and reduce both false positives and missed detections in dense rice seedling scenarios. Experimental results demonstrated that CLR-YOLO achieved an average precision (AP@0.5) of 93.9%. While maintaining comparable accuracy, the model reduced parameters to 1.4 M, computational cost to 3.7 GFLOPs, and model size to 2.9 MB—reductions of 46.2%, 41.3%, and 44.2%, respectively, compared to the baseline model. This model provides significant support for rice seedling detection and offers valuable insights to assist agricultural producers in making subsequent decisions. Full article

Background: Extracranial metastasis (EM) from glioblastoma (GB), IDH-wildtype (WHO CNS 2021 grade 4) is rare and often under-recognized, yet it has immediate implications for staging and management. We report a case series integrating advanced neuroimaging, whole-body imaging, and pathology/biomarkers to characterize imaging–pathology correlates of EM and highlight practical clinical triggers that should prompt systemic evaluation. Case presentation: We report three patients with adult-type, IDH-wildtype GB who developed EM confirmed by cytology/histology and/or concordant multimodality imaging. Brain MRI (1.5T/3T) demonstrated aggressive primary tumors with qualitative elevation of DSC-perfusion and frequent tumor–surface contact (dural, ependymal/leptomeningeal contact). Intratumoral susceptibility signal reached grade 3 where assessed. All patients underwent surgical resection followed by temozolomide-based chemoradiation; two received fotemustine and bevacizumab, and one underwent re-irradiation. EM presented with clinical triggers including severe axial/back pain, palpable cervical masses, and/or cytopenias. Initial EM sites were bone marrow/vertebrae (n = 1) and cervical lymph nodes (n = 2); staging revealed additional osseous disease in both nodal cases and a small pulmonary nodule in one. Nodal and osseous lesions were FDG-avid on 18F-FDG PET/CT. OLIG2-positive cytology confirmed cervical nodal metastases, and bone marrow aspiration with GFAP/OLIG2 positivity confirmed medullary infiltration. All tumors shared a molecular profile of TERT-promoter mutation, ATRX wild-type, TP53 mutation, and MGMT-promoter methylation. Despite attempts at second- and third-line therapies, disease progression was rapid, and all patients succumbed within 8–16 months of diagnosis. Discussion: This series underscores that EM can occur despite MGMT-promoter methylation and supports the concept of heterogeneous metastatic phenotypes in GB. Our cases reinforce that new axial/back pain or hematologic abnormalities may signal osseous or marrow involvement, and necrotic cervical lymphadenopathy in GB patients warrants dedicated imaging and tissue confirmation with glial markers. Integrating brain MRI features (high perfusion, surface contact, susceptibility burden) with FDG-PET/CT and targeted cytology/pathology can expedite diagnosis and inform multidisciplinary care. Conclusions: EM can arise despite MGMT-promoter methylation in IDH-wildtype GBM. Imaging red flags (high perfusion, surface contact, necrotic/FDG-avid cervical nodes) and clinical cues (axial pain, cytopenias, neck masses) should prompt early systemic staging (CT/PET-CT) and targeted tissue confirmation to advance management. Full article

Reliable real-time detection and counting of tuna during distant-water deck operations is critical for automated catch monitoring but remains challenging due to strong illumination variation, background clutter, and frequent occlusion. This study proposes YOLOv10n-EMCNet, an improved lightweight detector based on YOLOv10n, integrating an ESC-based C2f enhancement in the backbone, a Multi-Branch and Scale Modulation-Fusion Feature Pyramid Network (SMFPN) in the neck, and a Convolutional Attention Fusion Module (CAFM) in the head for fine-grained representation and multi-scale feature fusion. An end-to-end detection–tracking–counting pipeline is further constructed by combining the detector with DeepSORT and an ROI-based de-duplication strategy. On the tuna dataset, YOLOv10n-EMCNet achieved 94.84% mAP@0.5, 65.29% mAP@0.5:0.95, and 91.77% recall with 6.5 GFLOPs. In addition, a controlled comparison among DeepSORT, ByteTrack, and OC-SORT on challenging videos showed that DeepSORT provided the best overall balance between counting accuracy, identity stability, and runtime efficiency. In shipboard video validation on four representative videos covering daytime high glare, nighttime low light, dense occlusion, and dense multi-target, the proposed pipeline achieved an average counting accuracy of 91.4%, with an average relative error of 8.62% and an average absolute error of 1.25 fish per video, while operating at approximately 30 FPS on an RTX 4090D platform. These results provide encouraging preliminary evidence that the proposed method can support automated tuna monitoring under representative shipboard conditions. Full article

Under maize–soybean rotation systems, weeds and crops at the seedling stage in dryland fields exhibit high similarity in morphological structure, scale distribution, and spatial arrangement. In addition, complex illumination conditions, occlusion, and background interference further complicate accurate weed discrimination. To address these challenges, this study proposes an improved YOLOv11n-based weed detection method for seedling-stage crops under dryland rotation conditions, aiming to enhance detection accuracy and robustness in UAV-acquired field images. Three key improvements were introduced to enhance model performance: (1) the incorporation of Dynamic Convolution (DynamicConv) to adaptively strengthen feature representation for weeds with varying morphologies and scales in low-altitude remote sensing imagery; (2) the design of a SlimNeck lightweight feature fusion architecture to improve multi-scale feature propagation efficiency while reducing computational cost; (3) the cascaded group attention mechanism (CGA) is integrated into the C2PSA module, thereby improving discrimination capability under complex background conditions. These results represent consistent improvements over baseline models, including YOLOv5, YOLOv6, YOLOv8, YOLOv11, and YOLOv12. Specifically, detection performance for broadleaf weeds and Poaceae weeds reached mAP@0.5 values of 87.2% and 73.9%, respectively. Overall, the proposed method demonstrates superior detection accuracy and stability for seedling-stage weed identification under rotation conditions, providing reliable technical support for variable-rate herbicide application and precision field management. Full article

To address the challenges of rapid and accurate grape variety identification in natural orchard environments, along with the demand for efficient deployment on mobile devices, we propose in this paper YOLOv11n-GrapeLite, a lightweight model built upon an enhanced YOLOv11n architecture. First, an Efficient Channel Attention (ECA) mechanism is incorporated into the Neck layer. This mechanism adaptively recalibrates feature channel weights to emphasize those relevant to grape variety recognition, suppress background interference, and enhance target feature perception in complex scenes. Second, an adaptive downsampling (ADown) strategy is employed to replace the traditional convolutional downsampling module, reducing computational complexity while preserving critical features. Finally, the original C3k2 module is redesigned as a multi-scale convolution block (MSCB). This block integrates depthwise separable convolutions with multi-scale convolutions, which achieves significant parameter compression and enhances multi-scale feature extraction. Experimental results demonstrate that the proposed model achieves a mean average precision (mAP) of 91.5%, representing a 0.2% improvement over the original YOLOv11n, along with a 0.6% increase in recall. These results indicate outstanding robustness in complex field scenarios. The model’s parameter count was reduced to 1.87 million, computational complexity to 5.0 GFLOPS, and model size to 4.1 MB. These figures represent reductions of 27.8%, 23.1%, and 25.5%, respectively, compared to the original YOLOv11n, demonstrating significant lightweight optimization. Compared to mainstream models such as YOLOv6, YOLOv8n, YOLOv9s, YOLOV12, YOLOv13 and YOLOv26, the proposed model achieves superior performance in parameter count, computational load, and model size, while maintaining competitive detection accuracy. The YOLOv11n-GrapeLite model efficiently adapts to mobile terminal deployment, providing a feasible and efficient technical solution for real-time, precise identification of grape varieties in complex field scenarios. Full article