Search Results (560)

Background/Objectives: The ¹⁰³Pd/^103mRh in vivo generator represents a promising Auger electron-emitting system, in which both parent and daughter radionuclides emit predominantly Auger electrons with minimal accompanying radiation. This study investigates the release dynamics of daughter radionuclides from the ¹⁰³Pd/^103mRh in vivo generator and evaluates the underlying mechanisms governing bond rupture and daughter retention. Methods: Cyclotron irradiation of rhodium foils was performed in two separate batches, followed by radionuclide separation using conventional wet chemistry and a novel dry distillation technique. The purified ¹⁰³Pd radionuclide was used to radiolabel DOTA-TATE, phthalocyanine-TATE, and DOTA-TOC chelators. The resulting complexes were immobilized on Strata-X and Strata-C18 solid-phase extraction columns. Scheduled elution experiments were conducted to quantify the release of the ^103mRh daughter radionuclide. Results: The measured ^103mRh release rates were 9.8 ± 3.0% and 9.6 ± 2.7% from Strata-X columns with DOTA-TATE and phthalocyanine-TATE, respectively, and 10.5 ± 2.7% and 12.0 ± 0.5% from Strata-X and Strata-C18 columns, respectively, with DOTA-TOC. These values are significantly lower than the ~100% release predicted based on the reported Auger electron yield of 186%. One explanation for this difference could be potential inconsistencies in decay data that may require correction; this needs further investigation. The results further demonstrated that delocalized π-electrons, introduced via phthalocyanine-based chelation, did not mitigate daughter release. Conclusions: The low observed daughter nuclide release represents a favorable characteristic for the future clinical translation of the ¹⁰³Pd/^103mRh Auger emitter pair. The findings support the conclusion that Auger electron cascades, rather than nuclear recoil energy, dominate bond rupture processes. Full article

Identifying minute targets within UAV-acquired imagery continues to pose substantial technical hurdles, primarily due to blurred boundaries, scarce textural details, and drastic scale variations amidst complex backgrounds. In response to these limitations, this paper proposes BFRI-YOLO, an enhanced architecture based on the YOLOv11n baseline. The framework is built upon four synergistic components designed to achieve high-precision localization and robust feature representation. First, we construct a Balanced Adaptive Feature Pyramid Network (BAFPN) that utilizes a resolution-aware attention mechanism to promote bidirectional interaction between deep and shallow features. This is complemented by incorporating the Receptive Field Convolutional Block Attention Module (RFCBAM) to refine the backbone network. By constructing the C3K2_RFCBAM block, we effectively enhance the feature representation of small objects across diverse receptive fields. To further refine the prediction phase, we develop a Four-Shared Detail Enhancement Detection Head (FSDED) to improve both efficiency and stability. Finally, regarding the loss function, we formulate the Inner-WIoU strategy by integrating auxiliary bounding boxes with dynamic focusing mechanisms to ensure precise target localization. The experimental results on the VisDrone2019 benchmark demonstrate that our method secures mAP@0.5 and mAP@0.5:0.95 scores of 42.1% and 25.6%, respectively, outperforming the baseline by 8.8% and 6.2%. Extensive tests on the TinyPerson and DOTA1.0 datasets further validate the robust generalization capability of our model, confirming that BFRI-Yolo strikes a superior balance between detection accuracy and computational overhead in aerial scenes. Full article

To address the problems of missed and false detections caused by insufficient feature quality in small object detection from UAV perspectives, this paper proposes a UAV small object detection algorithm based on YOLOv8 feature optimization. A spatial cosine convolution module is introduced into the backbone network to optimize spatial features, thereby alleviating the problem of small object feature loss and improving the detection accuracy and speed of the model. An improved C2f_SCConv feature fusion module is employed for feature integration, which effectively reduces feature redundancy in spatial and channel dimensions, thereby lowering model complexity and computational cost. Meanwhile, the WIoU loss function is used to replace the original CIoU loss function, reducing the interference of geometric factors in anchor box regression, enabling the model to focus more on low-quality anchor boxes, and enhancing its small object detection capability. Ablation and comparative experiments on the VisDrone dataset validate the effectiveness of the proposed algorithm for small object detection from UAV perspectives, while generalization experiments on the DOTA and SSDD datasets demonstrate that the algorithm possesses strong generalization performance. Full article

Oriented object detection in remote sensing images remains a challenging task due to arbitrary target rotations, extreme scale variations, and complex backgrounds. However, current rotated detectors still face several limitations: insufficient orientation-sensitive feature representation, feature misalignment for rotated proposals, and unstable optimization of rotation parameters. To address these issues, this paper proposes an enhanced Rotation-Sensitive Feature Pyramid Network (RSFPN) framework. Building upon the effective Oriented R-CNN paradigm, we introduce three novel core components: (1) a Dynamic Adaptive Feature Pyramid Network (DAFPN) that enables bidirectional multi-scale feature fusion through semantic-guided upsampling and structure-enhanced downsampling paths; (2) an Angle-Aware Collaborative Attention (AACA) module that incorporates orientation priors to guide feature refinement; (3) a Geometrically Consistent Multi-Task Loss (GC-MTL) that unifies the regression of rotation parameters with periodic smoothing and adaptive weight mechanisms. Comprehensive experiments on the DOTA-v1.0 and HRSC2016 benchmarks show that our RSFPN achieves superior performance. It attains a state-of-the-art mAP of 77.42% on DOTA-v1.0 and 91.85% on HRSC2016, while maintaining efficient inference at 14.5 FPS, demonstrating a favorable accuracy-efficiency trade-off. Visual analysis confirms that our method produces concentrated, rotation-aware feature responses and effectively suppresses background interference. The proposed approach provides a robust solution for detecting multi-oriented objects in high-resolution remote sensing imagery, with significant practical value for urban planning, environmental monitoring, and security applications. Full article

Oriented object detection in remote sensing images rapidly evolves as a pivotal technique, driving transformative advancements across geospatial analytics, intelligent transportation systems, and urban infrastructure planning. However, the inherent characteristics of remote sensing objects, including complex background interference, multi-scale variations, and high-density distribution, pose critical challenges to balance detection accuracy and computational efficiency. This paper presents an anchor-free framework that eliminates the intrinsic constraints of anchor-based detectors, specifically the positive–negative sample imbalance and the computationally expensive non-maximum suppression (NMS) process. By effectively integrating adaptive kernel module with boundary refinement network, we achieved lightweight and efficient detection. Our method adaptively generates convolutional kernels tailored for multi-scale objects to extract discriminative features, while utilizing a boundary refinement network to precisely capture oriented bounding boxes. Experiments were carried out on the widely recognized HRSC2016 and DOTA datasets for the oriented bounding box (OBB) task. The proposed approach achieves 90.13% mAP (VOC07 metric) on HRSC2016 with 61.60 M parameters and 158.84 GFLOPS. For the DOTA benchmark, we attain 75.84% mAP with 45.96 M parameters and 131.39 GFLOPs. Our work highlights a lightweight yet powerful architecture that effectively balances accuracy and efficiency, making it particularly suitable for resource-constrained edge platforms. Full article

Rotated Bounding Boxes (RBBs) for oriented object detection are labor-intensive and time-consuming to annotate. Single-point supervision offers a cost-effective alternative but suffers from insufficient size and orientation information, leading existing methods to rely heavily on complex priors and fixed refinement stages. In this paper, we propose DP2PNet (Diffusion-Point-to-Polygon Network), the first diffusion model-based framework for single-point supervised oriented object detection. DP2PNet features three key innovations: (1) A multi-scale consistent noise generator that replaces manual or external model priors with Gaussian noise, reducing dependency on domain-specific information; (2) A Noise Cross-Constraint module based on multi-instance learning, which selects optimal noise point bags by fusing receptive field matching and object coverage; (3) A Semantic Key Point Aggregator that aggregates noise points via graph convolution to form semantic key points, from which pseudo-RBBs are generated using convex hulls. DP2PNet supports dynamic adjustment of refinement stages without retraining, enabling flexible accuracy optimization. Extensive experiments on DOTA-v1.0 and DIOR-R datasets demonstrate that DP2PNet achieves 53.82% and 53.61% mAP50, respectively, comparable to methods relying on complex priors. It also exhibits strong noise robustness and cross-dataset generalization. Full article

Small target detection in remote sensing images faces challenges due to complex backgrounds, weak features, and large scale differences. This paper proposes an improved YOLOv5-based network, termed ClearSight-RS, with the full name “Clear and Accurate Small-target Insight for Remote Sensing”. As the name implies, the network is dedicated to achieving clear feature perception and accurate target localization for small targets in remote sensing images. The improvements focus on three aspects: integrating an improved Dynamic Snake Convolution (DSConv) module into the backbone network to strengthen the extraction of small target boundaries and geometric features, as well as the expression of weak textures; embedding a Bi-Level Routing Attention (BRA) module in the Neck part to enhance target focusing and suppress background interference; and optimizing the detection head by retaining only shallow high-resolution feature layers for prediction, reducing feature loss and redundant computations. Experimental results show that, based on the VEDAI dataset, ClearSight-RS achieves the highest mAP for all 8 vehicle categories; based on the NWPU VHR-10 dataset, its overall mAP reaches 93.8%, significantly outperforming algorithms such as Faster RCNN and YOLOv5l; based on the DOTA dataset, the capability of the proposed BRA module in suppressing background interference and capturing small target features is demonstrated. The network balances accuracy and efficiency, performing prominently in detecting vehicles and multi-category small targets in complex backgrounds, verifying its effectiveness. Full article

Background/Objectives: The imo Vifa^® is reportedly useful for diagnosing functional visual field loss; however, its potential for detecting malingering is unclear. Here, we intentionally simulated monocular visual field defects under bilateral randomized visual field testing conditions using the imo Vifa^® in healthy participants and compared their resulting defect phenotypes. Methods: Twenty participants (mean age, 37.3 ± 12.4 years; 12 orthoptists, 1 physician, and 7 administrative staff members) without ocular disease were enrolled. Four types of monocular visual field defects were simulated: right eye nasal hemianopia, left eye temporal hemianopia, right eye centripetal visual field constriction, and left eye central scotoma. Bilateral randomized visual field testing was performed using the AIZE-rapid mode with the 24-2 and 24plus(1) programs. Results: Accurate simulation of the intended defects was challenging. Orthoptists produced left homonymous hemianopia for right nasal hemianopia and left temporal hemianopia. Regarding right nasal hemianopia, many office workers generated patterns resembling right homonymous hemianopia-like, whereas for left temporal hemianopia, noncertified orthoptists produced patterns similar to those of left homonymous hemianopia-like. Considering the right centripetal constriction, all orthoptists produced the intended centripetal constriction, whereas non-orthoptists generated right homonymous hemianopia-like or patchy patterns. Orthoptists produced central scotomas or patchy patterns for the left central scotoma, whereas non-orthoptists generated left homonymous hemianopia-like patterns. Conclusions: Creating targeted monocular abnormalities during bilateral randomized visual field testing was challenging. Differences in the participants’ understanding of visual field testing influenced the resulting patterns. In future research, having participants create monocular visual field defects under occlusion conditions would be necessary. Full article

In recent years, deep learning-based remote sensing object detection has achieved remarkable progress, yet the detection of tiny objects remains a significant challenge. Tiny objects in remote sensing images typically occupy only a few pixels, resulting in low contrast, poor resolution, and high sensitivity to localization errors. Their diverse scales and appearances, combined with complex backgrounds and severe class imbalance, further complicate the detection tasks. Conventional spatial feature extraction methods often struggle to capture the discriminative characteristics of tiny objects, especially in the presence of noise and occlusion. To address these challenges, we propose a frequency-aware attention-based tiny-object detection network with two plug-and-play modules that leverage frequency-domain information to enhance the targets. Specifically, we introduce a Multi-Scale Frequency Feature Enhancement Module (MSFFEM) to adaptively highlight the contour and texture details of tiny objects while suppressing background noise. Additionally, a Channel Attention-based RoI Enhancement Module (CAREM) is proposed to selectively emphasize high-frequency responses within RoI features, further improving object localization and classification. Furthermore, to mitigate sample imbalance, we employ multi-directional flip sample augmentation and redundancy filtering strategies, which significantly boost detection performance for few-shot categories. Extensive experiments on public object detection datasets, i.e., AI-TOD, VisDrone2019, and DOTA-v1.5, demonstrate that the proposed FANet consistently improves detection performance for tiny objects, outperforming existing methods and providing new insights into the integration of frequency-domain analysis and attention mechanisms for robust tiny-object detection in remote sensing applications. Full article

Background/Objectives: Overactivation of the HGF/c-MET pathway is implicated in various cancers, making its inhibition a promising therapeutic strategy. While several MET-targeting agents are currently approved or in advanced clinical development, patient selection often relies on invasive tissue-based assays. The development of a specific c-MET radioligand for PET imaging and radioligand therapy represents a non-invasive alternative, enabling real-time monitoring of target expression and offering a pathway to personalized treatment. Methods: Radiosynthesis of [⁶⁸Ga]Ga-DOTA-EMP100 was performed using a GMP-certified ⁶⁸Ge/⁶⁸Ga generator connected to an automated synthesis module. The radiopharmaceutical production was optimized by scaling down the amount of DOTA-EMP-100 from 50 to 20 μg. Synthesis efficiency and release criteria were assessed according to Ph. Eur. for all the final products by evaluating radiochemical yield (RY%), radiochemical purity, presence of free gallium (by Radio-UV-HPLC) and gallium colloids (by Radio-TLC), molar activity (Am), chemical purity, pH, and LAL test results. Results: An optimized formulation of [⁶⁸Ga]Ga-DOTA-EMP-100, using 40 μg of precursor, provided the best outcome in terms of radiochemical performance. Process validation across three independent productions confirmed a consistent radiochemical yield of 64.5% ± 0.5, high radiochemical purity (>99.99%), and a molar activity of 53.41 GBq/µmol ± 0.8. Conclusions: [⁶⁸Ga]Ga-DOTA-EMP-100 was successfully synthesized with high purity and reproducibility, supporting its potential for multi-dose application in clinical PET imaging and targeted radioligand therapy. Full article

Expanding the receptive field while maintaining efficiency is a key challenge in lightweight remote sensing super-resolution. Existing methods often suffer from parameter redundancy or insufficient channel utilization. To address these issues, we propose the Receptive Field Aggregation Network (RFANSR). First, we design a Progressive Receptive Field Aggregator (PRFA). It expands the receptive field by cascading medium-sized kernels, avoiding the heavy overhead of extremely large kernels. Second, we introduce a Statistical Guidance Module (SGM). This module replaces inefficient identity mappings with statistical channel recalibration to maximize feature utility. Additionally, we propose a Spatial-Gated Feed-Forward Network (SGFN) to reduce information loss via spatial attention. Extensive experiments demonstrate that RFANSR outperforms state-of-the-art lightweight models. Notably, RFANSR achieves PSNR improvements of 0.06 dB on RSCNN7 and 0.14 dB on DOTA datasets. Remarkably, it requires only 383 K parameters, representing a 45.4% reduction compared to DLKN. Full article

Background: Inflammatory bowel diseases (IBD) rely on invasive methods for detecting intestinal inflammation, with the needs for non-invasive molecular imaging tools being unmet. Integrin α4β7 is a key target in IBD pathogenesis due to its role in the recruitment of T cells. This study aimed to develop a novel ⁶⁸Ga-labeled integrin α4β7-targeted radiopharmaceutical (⁶⁸Ga-A2) and evaluate its feasibility for non-invasive PET/CT imaging of IBD inflammation in a dextran sulfate sodium (DSS)-induced murine colitis model. Methods: ⁶⁸Ga-A2 was synthesized via radiolabeling DOTA-A2 with ⁶⁸Ga. In vitro properties (radiochemical purity, stability, binding specificity, and affinity) of ⁶⁸Ga-A2 were validated. The DSS-induced colitis model was established and confirmed in C57BL/6J mice, followed by in vivo PET/CT imaging, ex vivo biodistribution studies, and histological (HE and IHC) analyses to evaluate the targeting efficacy of ⁶⁸Ga-A2. Results: ⁶⁸Ga-A2 was prepared efficiently (20 min) with a radiochemical purity of >95% and demonstrated good in vitro stability. It exhibited specific binding to integrin α4β7 with a Kd of 68.48 ± 6.55 nM. While whole-body PET/CT showed no visible inflammatory focus uptake, ex vivo imaging and biodistribution of colon tissue revealed significantly higher uptake in DSS-treated mice compared to that in healthy/blocking groups, which was consistent with histological evidence of inflammation. Conclusions: ⁶⁸Ga-A2 demonstrated specific targeting of IBD inflammatory foci in vitro and ex vivo. Despite whole-body imaging limitations, further optimization of its structure may enable it to become a promising non-invasive PET agent for IBD. These findings support future clinical investigations to validate its utility in IBD diagnosis and monitoring. Full article

Objectives: Pretargeting strategies enhance the specificity and safety of radiopharmaceuticals by separating tumor targeting from radionuclide delivery. To address the rapid clearance and systemic exposure of directly labeled small-molecule agents, a DZ-1–based pretargeting system was developed, utilizing its broad-spectrum tumor-targeting characteristics. Methods: Three DZ-TCO precursors (DZ-1-TCO, DZ-Lys-TCO, and DZ-Lys-PEG₄-TCO) were synthesized and evaluated by near-infrared fluorescence imaging in HeLa and U87MG tumor-bearing mice. Two tetrazine probes (methyl-tetrazine and mono-substituted tetrazine) were labeled with ⁶⁸Ga to yield ⁶⁸Ga-DOTA-Me-Tz and ⁶⁸Ga-DOTA-H-Tz, whose stability was assessed in PBS and serum. Pretargeted PET imaging was performed using different precursor/probe combinations and pretargeting intervals (24, 48, and 72 h). Results: All precursors exhibited tumor accumulation peaking at 24 h and signal retention up to 96 h. Both ⁶⁸Ga-DOTA-Me-Tz and ⁶⁸Ga-DOTA-H-Tz maintained >85% radiochemical stability after 4 h. PET imaging identified DZ-Lys-TCO as the most effective precursor (1.98 ± 0.72 %ID/g, T/M 3.86 ± 0.91). Using ⁶⁸Ga-DOTA-H-Tz, the 48 h interval achieved optimal uptake (3.24 ± 0.95 %ID/g) with the highest tumor-to-muscle ratio (8.30 ± 3.39). Biodistribution confirmed rapid renal clearance, low off-target accumulation, and peak tumor uptake of 3.53 ± 1.76 %ID/g (T/M 10.9 ± 0.3 at 30 min). Conclusions: The DZ-TCO/⁶⁸Ga-DOTA-Tz pretargeting system enables high-contrast tumor imaging with low background. The combination of DZ-Lys-TCO and ⁶⁸Ga-DOTA-H-Tz at a 48 h interval provides optimal performance, representing a promising platform for precise and safe radiopharmaceutical imaging. Full article

Introduction: Peptide Receptor Radionuclide Therapy (PRRT) with [¹⁷⁷Lu]Lu-DOTA-TATE is effective in treating advanced Neuroendocrine Tumors (NETs), yet predicting individual response in this treatment remains a challenge due to inter-lesion heterogeneity. There is a lack of standardized, effective methods for using multi-lesion radiomics to predict progression and Time to Progression (TTP) in PRRT-treated patients. This study evaluated how aggregating radiomic features from multiple PET-identified lesions can be used to predict disease progression (event [progression and death] vs. event-free) and TTP. Methods: Eighty-one NETs patients with multiple lesions underwent pre-treatment PET/CT imaging. Lesions were segmented and ranked by minimum Standard Uptake Value (SUV_min) (both descending and ascending), SUV_mean, SUV_max, and volume (descending). From each sorting, the top one, three, and five lesions were selected. For the selected lesions, radiomic features were extracted (using the Pyradiomics library) and lesion aggregation was performed using stacked vs. statistical methods. Eight classification models along with three feature selection methods were used to predict progression, and five survival models and three feature selection methods were used to predict TTP under a nested cross-validation framework. Results: The overall appraisal showed that sorting lesions based on SUV_min (descending) yields better classification performance in progression prediction. This is in addition to the fact that aggregating features extracted from all the lesions, as well as the top five lesions sorted by SUV_mean, lead to the highest overall performance in TTP prediction. The individual appraisal in progression prediction models trained on the single top lesion sorted by SUV_min (descending) showed the highest recall and specificity despite data imbalance. The best-performing model was the Logistic Regression (LR) classifier with Recursive Feature Elimination (RFE) (recall: 0.75, specificity: 0.77). In TTP prediction, the highest concordance index was obtained using a Random Survival Forest (RSF) trained on statistically aggregated features from the top five lesions ranked by SUV_mean, selected via Univariate C-Index (UCI) (C-index = 0.68). Across both tasks, features from the Gray Level Size Zone Matrix (GLSZM) family were consistently among the most predictive, highlighting the importance of spatial heterogeneity in treatment response. Conclusions: This study demonstrates that informed lesion selection and tailored aggregation strategies significantly impact the predictive performance of radiomics-based models for progression and TTP prediction in PRRT-treated NET patients. These approaches can potentially enhance model accuracy and better capture tumor heterogeneity, supporting more personalized and practical PRRT implementation. Full article

Ship detection in remote sensing imagery is hindered by cluttered backgrounds, large variations in scale, and random orientations, limiting the performance of detectors designed for natural images. We propose RSDB-Net, a Rotation-Sensitive Dual-Branch Detection Network that introduces innovations in feature extraction, fusion, and detection. The Swin Transformer–CNN Backbone (STCBackbone) combines a Swin Transformer for global semantics with a CNN branch for local spatial detail, while the Feature Conversion and Coupling Module (FCCM) aligns and fuses heterogeneous features to handle multi-scale objects, and a Rotation-sensitive Cross-branch Fusion Head (RCFHead) enables bidirectional interaction between classification and localization, improving detection of randomly oriented targets. Additionally, an enhanced Feature Pyramid Network (eFPN) with learnable transposed convolutions restores semantic information while maintaining spatial alignment. Experiments on DOTA-v1.0 and HRSC2016 show that RSDB-Net performs better than the state of the art (SOTA), with mAP-ship values of 89.13% and 90.10% (+5.54% and +44.40% over the baseline, respectively), and reaches 72 FPS on an RTX 3090. RSDB-Net also demonstrates strong generalization and scalability, providing an effective solution for rotation-aware ship detection. Full article