Search Results (1,090)

Non-linear least squares (NLS) methods are commonly used for quantitative magnetic resonance imaging (MRI), especially for multi-exponential T1ρ mapping, which provides precise parameter estimation for different relaxation models in tissues, such as mono-exponential (ME), bi-exponential (BE), and stretched-exponential (SE) models. However, NLS may suffer from problems like sensitivity to initial guesses, slow convergence speed, and high computational cost. While deep learning (DL)-based T1ρ fitting methods offer faster alternatives, they often face challenges such as noise sensitivity and reliance on NLS-generated reference data for training. To address these limitations of both approaches, we propose the HDNLS, a hybrid model for fast multi-component parameter mapping, particularly targeted for T1ρ mapping in the knee joint. HDNLS combines voxel-wise DL, trained with synthetic data, with a few iterations of NLS to accelerate the fitting process, thus eliminating the need for reference MRI data for training. Due to the inverse-problem nature of the parameter mapping, certain parameters in a specific model may be more sensitive to noise, such as the short component in the BE model. To address this, the number of NLS iterations in HDNLS can act as a regularization, stabilizing the estimation to obtain meaningful solutions. Thus, in this work, we conducted a comprehensive analysis of the impact of NLS iterations on HDNLS performance and proposed four variants that balance estimation accuracy and computational speed. These variants are Ultrafast-NLS, Superfast-HDNLS, HDNLS, and Relaxed-HDNLS. These methods allow users to select a suitable configuration based on their specific speed and performance requirements. Among these, HDNLS emerges as the optimal trade-off between performance and fitting time. Extensive experiments on synthetic data demonstrate that HDNLS achieves comparable performance to NLS and regularized-NLS (RNLS) with a minimum of a 13-fold improvement in speed. HDNLS is just a little slower than DL-based methods; however, it significantly improves estimation quality, offering a solution for T1ρ fitting that is fast and reliable. Full article

With the advancement of service robot technology, the demand for higher boundary precision in indoor semantic segmentation has increased. Traditional methods of extracting Euclidean features using point cloud and voxel data often neglect geodesic information, reducing boundary accuracy for adjacent objects and consuming significant computational resources. This study proposes a novel network, the Euclidean–geodesic network (EGNet), which uses point cloud–voxel–mesh data to characterize detail, contour, and geodesic features, respectively. The EGNet performs feature fusion through Euclidean and geodesic branches. In the Euclidean branch, the features extracted from point cloud data compensate for the detail features lost by voxel data. In the geodesic branch, geodesic features from mesh data are extracted using inter-domain fusion and aggregation modules. These geodesic features are then combined with contextual features from the Euclidean branch, and the simplified trajectory map of the grid is used for up-sampling to produce the final semantic segmentation results. The Scannet and Matterport datasets were used to demonstrate the effectiveness of the EGNet through visual comparisons with other models. The results demonstrate the effectiveness of integrating Euclidean and geodesic features for improved semantic segmentation. This approach can inspire further research combining these feature types for enhanced segmentation accuracy. Full article

Several approaches have been developed to generate synthetic object points using real LiDAR point cloud data for advanced driver-assistance system (ADAS) applications. The synthetic object points generated from a scene (both the near and distant objects) are essential for several ADAS tasks. However, generating points from distant objects using sparse LiDAR data with precision is still a challenging task. Although there are a few state-of-the-art techniques to generate points from synthetic objects using LiDAR point clouds, limitations such as the need for intense compute power still persist in most cases. This paper suggests a new framework to address these limitations in the existing literature. The proposed framework contains three major modules, namely position determination, object generation, and synthetic annotation. The proposed framework uses a spherical point-tracing method that augments 3D LiDAR distant objects using point cloud object projection with point-wall generation. Also, the pose determination module facilitates scenarios such as platooning carried out by the synthetic object points. Furthermore, the proposed framework improves the ability to describe distant points from synthetic object points using multiple LiDAR systems. The performance of the proposed framework is evaluated on various 3D detection models such as PointPillars, PV-RCNN, and Voxel R-CNN for the KITTI dataset. The results indicate an increase in mAP (mean average precision) by 1.97%, 1.3%, and 0.46% from the original dataset values of 82.23%, 86.72%, and 87.05%, respectively. Full article

In recent years, navigation has attracted widespread attention across various fields, such as geomatics, robotics, photogrammetry, and transportation. Modeling the navigation environment is a key step in building successful navigation services. While traditional navigation systems have relied solely on 2D data, advancements in 3D sensing technology have made more 3D data available, enabling more realistic environmental modeling. This paper primarily focuses on voxel-based navigation and reviews the existing literature that covers various aspects of using voxel data or models to support navigation. The paper first discusses key technologies related to voxel-based navigation, including voxel-based modeling, voxel segmentation, voxel-based analysis, and voxel storage and management. It then distinguishes and discusses indoor and outdoor navigation based on the application scenarios. Additionally, various issues related to voxel-based navigation are addressed. Finally, the paper presents several potential research opportunities that may be useful for researchers or companies in developing more advanced navigation systems for pedestrians, robots, and vehicles. Full article

This study introduces a non-destructive, quantitative method using low-field MRI to assess moisture mobility and content distribution in cherry tomatoes. This study developed an advanced 3D non-local mean denoising model to enhance tissue feature analysis and applied an optimized TransUNet model for structural segmentation, obtaining multi-echo data from six tissue types. The structural T2 relaxation inversion was refined by integrating an ACS-CIPSO algorithm. This approach addresses the challenge of low signal-to-noise ratios in multi-echo MRI images from low-field equipment by introducing an innovative solution that effectively reduces voxel noise while retaining structural relaxation variability. The study reveals that there are consistent patterns in the changes in moisture mobility and content across different structures of cherry tomatoes during their ripening process. Mono-exponential analysis reveals the patterns of changes in moisture mobility (T2) and content (A) across various structures. Furthermore, tri-exponential analysis elucidates the patterns of changes in bound water (T21), semi-bound water (T22), and free water (T23), along with their respective contents. These insights offer a novel perspective on the changes in moisture mobility throughout the ripening process of tomato fruit, thereby providing a research pathway for the precise assessment of moisture status and ripening expression in fruits. Full article

Major depressive disorder (MDD) exhibits notable sex differences in prevalence and clinical and neurobiological manifestations. Though the relationship between peripheral inflammation and MDD-related brain changes is well studied, the role of sex as a modifying factor is underexplored. This study aims to assess how sex influences brain and inflammatory markers in MDD. We utilized voxel-based and surface-based morphometry to analyze gray matter (GM) structure, along with GM-based spatial statistics (GBSS) to examine GM microstructure among treatment-naive patients with depression (n = 174) and age-matched healthy controls (n = 133). We uncovered sex-by-diagnosis interactions in several limbic system structures, the frontoparietal operculum and temporal regions. Post hoc analyses revealed that male patients exhibit pronounced brain abnormalities, while no significant differences were noted in females despite their higher depressive scores. Additionally, heightened inflammation levels in MDD were observed in both sexes, with sex-specific effects on sex-specific brain phenotypes, particularly including a general negative correlation in males. Intriguingly, mediation analyses highlight the specific role of the parahippocampal gyrus (PHG) in mediating interleukin (IL)-8 and depression in men. The findings suggest that in clinical practice, it would be beneficial to prioritize sex-specific assessments and interventions for MDD. This includes recognizing the possibility that male patients may experience significant brain alterations, especially when identifying male patients who may underreport symptoms. Possible limitations encompass a small sample size and the cross-sectional design. In future research, the incorporation of longitudinal studies or diverse populations, while considering illness duration, will enhance our understanding of how inflammation interacts with brain changes in depression. Full article

Since conventional photogrammetric approaches struggle with with low-texture, reflective, and transparent regions, this study explores the application of Neural Radiance Fields (NeRFs) for large-scale 3D reconstruction of outdoor scenes, since NeRF-based methods have recently shown very impressive results in these areas. We evaluate three approaches: Mega-NeRF, Block-NeRF, and Direct Voxel Grid Optimization, focusing on their accuracy and completeness compared to ground truth point clouds. In addition, we analyze the effects of using multiple sub-modules, estimating the visibility by an additional neural network and varying the density threshold for the extraction of the point cloud. For performance evaluation, we use benchmark datasets that correspond to the setting off standard flight campaigns and therefore typically have nadir camera perspective and relatively little image overlap, which can be challenging for NeRF-based approaches that are typically trained with significantly more images and varying camera angles. We show that despite lower quality compared to classic photogrammetric approaches, NeRF-based reconstructions provide visually convincing results in challenging areas. Furthermore, our study shows that in particular increasing the number of sub-modules and predicting the visibility using an additional neural network improves the quality of the resulting reconstructions significantly. Full article

The combination of UAV-LiDAR and LiDAR-SLAM (Simultaneous Localization and Mapping) technology can overcome the scanning limitations of different platforms and obtain comprehensive 3D structural information of forest stands. To address the challenges of the traditional registration algorithms, such as high initial value requirements and susceptibility to local optima, in this paper, we propose a high-precision, robust, NDT-VGICP registration method that integrates voxel features to register UAV-LiDAR and LiDAR-SLAM point clouds at the forest stand scale. First, the point clouds are voxelized, and their normal vectors and normal distribution models are computed, then the initial transformation matrix is quickly estimated based on the point pair distribution characteristics to achieve preliminary alignment. Second, high-dimensional feature weighting is introduced, and the iterative closest point (ICP) algorithm is used to optimize the distance between the matching point pairs, adjusting the transformation matrix to reduce the registration errors iteratively. Finally, the algorithm converges when the iterative conditions are met, yielding an optimal transformation matrix and achieving precise point cloud registration. The results show that the algorithm performs well in Chinese fir forest stands of different age groups (average RMSE—horizontal: 4.27 cm; vertical: 3.86 cm) and achieves high accuracy in single-tree crown vertex detection and tree height estimation (average F-score: 0.90; R² for tree height estimation: 0.88). This study demonstrates that the NDT-VGICP algorithm can effectively fuse and collaboratively apply multi-platform LiDAR data, providing a methodological reference for accurately quantifying individual tree parameters and efficiently monitoring 3D forest stand structures. Full article

Breast cancer is a global threat to women’s health. Three-dimensional (3D) automated breast ultrasound (ABUS) offers reproducible high-resolution imaging for breast cancer diagnosis. However, 3D-input deep networks are challenged by high time costs, a lack of sufficient training samples, and the complexity of hyper-parameter optimization. For efficient ABUS tumor classification, this study explores 2D-input networks, and soft voting (SV) is proposed as a post-processing step to enhance diagnosis effectiveness. Specifically, based on the preliminary predictions made by a 2D-input network, SV employs voxel-based weighting, and hard voting (HV) utilizes slice-based weighting. Experimental results on 100 ABUS cases show a substantial improvement in classification performance. The diagnosis metric values are increased from ResNet34 (accuracy, 0.865; sensitivity, 0.942; specificity, 0.757; area under the curve (AUC), 0.936) to ResNet34 + HV (accuracy, 0.907; sensitivity, 0.990; specificity, 0.864; AUC, 0.907) and to ResNet34 + SV (accuracy, 0.986; sensitivity, 0.990; specificity, 0.963; AUC, 0.986). Notably, ResNet34 + SV achieves the state-of-the-art result on the database. The proposed SV strategy enhances ABUS tumor classification with minimal computational overhead, while its integration with 2D-input networks to improve prediction performance of other 3D object recognition tasks requires further investigation. Full article

Medical image processing has been highlighted as an area where deep-learning-based models have the greatest potential. However, in the medical field, in particular, problems of data availability and privacy are hampering research progress and, thus, rapid implementation in clinical routine. The generation of synthetic data not only ensures privacy but also allows the drawing of new patients with specific characteristics, enabling the development of data-driven models on a much larger scale. This work demonstrates that three-dimensional generative adversarial networks (GANs) can be efficiently trained to generate high-resolution medical volumes with finely detailed voxel-based architectures. In addition, GAN inversion is successfully implemented for the three-dimensional setting and used for extensive research on model interpretability and applications such as image morphing, attribute editing, and style mixing. The results are comprehensively validated on a database of three-dimensional HR-pQCT instances representing the bone micro-architecture of the distal radius. Full article

Background: The advent of artificial intelligence has significantly impacted radiology, with radiomics emerging as a transformative approach that extracts quantitative data from medical images to improve diagnostic and therapeutic accuracy. This study aimed to enhance the radiomic workflow by applying deep learning, through transfer learning, for the automatic segmentation of lung regions in computed tomography scans as a preprocessing step. Methods: Leveraging a pipeline articulated in (i) patient-based data splitting, (ii) intensity normalization, (iii) voxel resampling, (iv) bed removal, (v) contrast enhancement and (vi) model training, a DeepLabV3+ convolutional neural network (CNN) was fine tuned to perform whole-lung-region segmentation. Results: The trained model achieved high accuracy, Dice coefficient (0.97) and BF (93.06%) scores, and it effectively preserved lung region areas and removed confounding anatomical regions such as the heart and the spine. Conclusions: This study introduces a deep learning framework for the automatic segmentation of lung regions in CT images, leveraging an articulated pipeline and demonstrating excellent performance of the model, effectively isolating lung regions while excluding confounding anatomical structures. Ultimately, this work paves the way for more efficient, automated preprocessing tools in lung cancer detection, with potential to significantly improve clinical decision making and patient outcomes. Full article

In glioma surgery, maximizing the extent of resection while preserving cognitive functions requires an understanding of the unique architecture of the white matter (WM) pathways of the single patient and of their spatial relationship with the tumor. Tractography enables the reconstruction of WM pathways, and bundle segmentation allows the identification of critical connections for functional preservation. This study evaluates the effectiveness of a streamline-based approach for bundle segmentation on a clinical dataset as compared to the traditional ROI-based approach. We performed bundle segmentation of the arcuate fasciculus, of its indirect anterior and posterior segments, and of the inferior fronto-occipital fasciculus in the healthy hemisphere of 25 high-grade glioma patients using both ROI- and streamline-based approaches. ROI-based segmentation involved manually delineating ROIs on MR anatomical images in Trackvis (V0.6.2.1). Streamline-based segmentations were performed in Tractome, which integrates clustering algorithms with the visual inspection and manipulation of streamlines. Shape analysis was conducted on each bundle. A paired t-test was performed on the irregularity measurement to compare segmentations achieved with the two approaches. Qualitative differences were evaluated through visual inspection. Streamline-based segmentation consistently yielded significantly lower irregularity scores (p < 0.001) compared to ROI-based segmentation for all the examined bundles, indicating more compact and accurate bundle reconstructions. Qualitative assessment identified common biases in ROI-based segmentations, such as the inclusion of anatomically implausible streamlines or streamlines with undesired trajectories. Streamline-based bundle segmentation with Tractome provides reliable and more accurate reconstructions compared to the ROI-based approach. By directly manipulating streamlines rather than relying on voxel-based ROI delineations, Tractome allows us to discern and discard implausible or undesired streamlines and to identify the course of WM bundles even when the anatomy is distorted by the lesion. These features make Tractome a robust tool for bundle segmentation in clinical contexts. Full article

4-aminopyridine (4-AP) is a non-selective blocker of voltage-dependent K⁺ channels used to improve walking in multiple sclerosis patients, and it may be useful in the treatment of cerebellar diseases. In animal models, 4-AP is used as a convulsant agent. When administered intrahippocampally, 4-AP induces acute local glucose hypermetabolism and significant brain damage, while i.p. administration causes less neuronal damage. This study aimed to investigate the effects of a single i.p. administration of 4-AP on acute brain glucose metabolism as well as on neuronal viability and signs of neuroinflammation 3 days after the insult. Brain glucose metabolism was evaluated by [¹⁸F]FDG PET neuroimaging. [¹⁸F]FDG uptake was analyzed based on volumes of interest (VOIs) as well as by voxel-based (SPM) analyses. The results showed that independently of the type of data analysis used (VOIs or SPM), 4-AP induced acute generalized brain glucose hypometabolism, except in the cerebellum. Furthermore, the SPM analysis normalized by the whole brain uptake revealed a significant cerebellar hypermetabolism. The neurohistochemical assays showed that 4-AP induced hippocampal astrocyte reactivity 3 days after the insult, without inducing changes in neuronal integrity or microglia-mediated neuroinflammation. Thus, acute brain glucose metabolic and neuroinflammatory profiles in response to i.p. 4-AP clearly differed from that reported for intrahippocampal administration. Finally, the results suggest that the cerebellum might be more resilient to the 4-AP-induced hypometabolism. Full article

As the combination of panoramic images and laser point clouds becomes more and more widely used as a technique, the accurate determination of external parameters has become essential. However, due to the relative position change of the sensor and the time synchronization error, the automatic and accurate matching of the panoramic image and the point cloud is very challenging. In order to solve this problem, this paper proposes an automatic and accurate registration method for panoramic images and point clouds of urban large scenes based on line features. Firstly, the multi-modal point cloud line feature extraction algorithm is used to extract the edge of the point cloud. Based on the point cloud intensity orthoimage (an orthogonal image based on the point cloud’s intensity values), the edge of the road markings is extracted, and the geometric feature edge is extracted by the 3D voxel method. Using the established virtual projection correspondence for the panoramic image, the panoramic image is projected onto the virtual plane for edge extraction. Secondly, the accurate matching relationship is constructed by using the feature constraint of the direction vector, and the edge features from both sensors are refined and aligned to realize the accurate calculation of the registration parameters. The experimental results show that the proposed method shows excellent registration results in challenging urban scenes. The average registration error is better than 3 pixels, and the root mean square error (RMSE) is less than 1.4 pixels. Compared with the mainstream methods, it has advantages and can promote the further research and application of panoramic images and laser point clouds. Full article

This study innovatively employs drones equipped with air quality sensors to collect three-dimensional air quality data in a campus microenvironment. Data are accurately corrected using a BP neural network, and a cubic model is constructed using three-dimensional interpolation. Combining photogrammetry technology, this study analyzes air quality patterns, finding significant differences from macro trends. Construction activities and large electronic experimental equipment significantly increase PM_2.5 levels in the air. In rainy weather, the respiration of vegetation is enhanced, leading to higher CO₂ concentrations, while water bodies exhibit higher temperatures in rainy weather due to their high specific heat capacity. This research not only provides a new perspective for microenvironment air quality monitoring but also offers a scientific basis for future air quality monitoring and management. Full article