Search Results (1,189)

Street view imagery has become a vital tool for assessing urban street greenery, with the Green View Index (GVI) serving as the predominant metric. However, while GVI effectively quantifies overall greenery, it fails to capture the nuanced, human-scale experience of urban greenery. This study introduces the Front-Facing Green View Index (FFGVI), a metric designed to reflect the perspective of pedestrians traversing urban streets. The FFGVI computation involves three key steps: (1) calculating azimuths for road points, (2) retrieving front-facing street view images, and (3) applying semantic segmentation to identify green pixels in street view imagery. Building on this, this study proposes the Street Canyon Green View Index (SCGVI), a novel approach for identifying boulevards that evoke perceptions of comfort, spaciousness, and aesthetic quality akin to room-like streetscapes. Applying these indices to a case study in Nanjing, China, this study shows that (1) FFGVI exhibited a strong correlation with GVI (R = 0.88), whereas the association between SCGVI and GVI was marginally weaker (R = 0.78). GVI tends to overestimate perceived greenery due to the influence of lateral views dominated by side-facing vegetation; (2) FFGVI provides a more human-centered perspective, mitigating biases introduced by sampling point locations and obstructions such as large vehicles; and (3) SCGVI effectively identifies prominent boulevards that contribute to a positive urban experience. These findings suggest that FFGVI and SCGVI are valuable metrics for informing urban planning, enhancing urban tourism, and supporting greening strategies at the street level. Full article

Alzheimer’s disease (AD) involves the accumulation of amyloid-β (Aβ) plaques, whose quantification plays a central role in understanding disease progression. Automated segmentation of Aβ deposits in histopathological micrographs enables large-scale analyses but is hindered by the high cost of detailed pixel-level annotations. Weakly supervised learning offers a promising alternative by leveraging coarse or indirect labels to reduce the annotation burden. We evaluated a weakly supervised approach to segment and analyze thioflavin-S-positive parenchymal amyloid pathology in AD and age-matched brains. Our pipeline integrates three key components, each designed to operate under weak supervision. First, robust preprocessing (including retrospective multi-image illumination correction and gradient-based background estimation) was applied to enhance image fidelity and support training, as models rely more on image features. Second, class activation maps (CAMs), generated by a compact deep classifier SqueezeNet, were used to identify, and coarsely localize amyloid-rich parenchymal regions from patch-wise image labels, serving as spatial priors for subsequent refinement without requiring dense pixel-level annotations. Third, a patch-based convolutional neural network, U-Net, was trained on synthetic data generated from micrographs based on CAM-derived pseudo-labels via an extensive object-level augmentation strategy, enabling refined whole-image semantic segmentation and generalization across diverse spatial configurations. To ensure robustness and unbiased evaluation, we assessed the segmentation performance of the entire framework using patient-wise group k-fold cross-validation, explicitly modeling generalization across unseen individuals, critical in clinical scenarios. Despite relying on weak labels, the integrated pipeline achieved strong segmentation performance with an average Dice similarity coefficient (≈0.763) and Jaccard index (≈0.639), widely accepted metrics for assessing segmentation quality in medical image analysis. The resulting segmentations were also visually coherent, demonstrating that weakly supervised segmentation is a viable alternative in histopathology, where acquiring dense annotations is prohibitively labor-intensive and time-consuming. Subsequent morphometric analyses on automatically segmented Aβ deposits revealed size-, structural complexity-, and global geometry-related differences across brain regions and cognitive status. These findings confirm that deposit architecture exhibits region-specific patterns and reflects underlying neurodegenerative processes, thereby highlighting the biological relevance and practical applicability of the proposed image-processing pipeline for morphometric analysis. Full article

Traditional Foreign Object Debris (FOD) detection methods face challenges such as difficulties in large-size data acquisition and the ineffective application of detection algorithms with high accuracy. In this paper, image data augmentation was performed using generative adversarial networks and diffusion models, generating images of monitoring areas under different environmental conditions and FOD images of varied types. Additionally, a three-stage image blending method considering size transformation, a seamless process, and style transfer was proposed. The image quality of different blending methods was quantitatively evaluated using metrics such as structural similarity index and peak signal-to-noise ratio, as well as Depthanything. Finally, object detection models with a similarity distance strategy (SimD), including Faster R-CNN, YOLOv8, and YOLOv11, were tested on the dataset. The experimental results demonstrated that realistic FOD data were effectively generated. The Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) of the synthesized image by the proposed three-stage image blending method outperformed the other methods, reaching 0.99 and 45 dB. YOLOv11 with SimD trained on the augmented dataset achieved the mAP of 86.95%. Based on the results, it could be concluded that both data augmentation and SimD significantly improved the accuracy of FOD detection. Full article

Purpose: To assess the performance of 2D T2-weighted (w) Turbo Spin Echo (TSE) MRI reconstructed with a deep learning (DL)-powered super resolution reconstruction (SRR) algorithm combining compressed sensing (CS) denoising and resolution upscaling for high-resolution hippocampal imaging in patients with (epileptic) seizures and suspected hippocampal pathology. Methods: A 2D T2w TSE coronal hippocampal sequence with compressed sense (CS) factor 1 (scan time 270 s) and a CS-accelerated sequence with a CS factor of 3 (scan time 103 s) were acquired in 28 patients. Reconstructions using the SRR algorithm (CS 1-SSR-s and CS 3-SSR-s) were additionally obtained in real time. Two readers graded the images twice, based on several metrics (image quality; artifacts; visualization of anatomical details of the internal hippocampal architecture (HIA); visibility of dentate gyrus/pes hippocampi/fornix/mammillary bodies; delineation of gray and white matter). Results: Inter-readout agreement was almost perfect (Krippendorff’s alpha coefficient = 0.933). Compared to the CS 1 sequence, the CS 3 sequence significantly underperformed in all 11 metrics (p < 0.001-p = 0.04), while the CS 1-SRR-s sequence outperformed in terms of overall image quality and visualization of the left HIA and right pes hippocampi (p < 0.001-p < 0.04) but underperformed in terms of presence of artifacts (p < 0.01). Lastly, relative to the CS 1 sequence, the CS 3-SRR-s sequence was graded worse in terms of presence of artifacts (p < 0.003) but with improved visualization of the right pes hippocampi (p = 0.02). Conclusion: DL-powered SSR demonstrates its capacity to enhance imaging performance by introducing flexibility in T2w hippocampal imaging; it either improves image quality for non-accelerated imaging or preserves acceptable quality in accelerated imaging, with the additional benefit of a reduced scan time. Full article

During the long-term preservation of murals, the degradation of mural image information poses significant challenges to the restoration and conservation of world cultural heritage. Currently, mural conservation scholars focus on image segmentation techniques for mural restoration and protection. However, existing image segmentation methods suffer from suboptimal segmentation quality. To improve mural image segmentation, this study proposes an efficient mural image segmentation method termed Adaptive Nonlinear Bernstein-guided Parrot Optimizer (ANBPO) by integrating an adaptive learning strategy, a nonlinear factor, and a third-order Bernstein-guided strategy into the Parrot Optimizer (PO). In ANBPO, First, to address PO’s limited global exploration capability, the adaptive learning strategy is introduced. By considering individual information disparities and learning behaviors, this strategy effectively enhances the algorithm’s global exploration, enabling a thorough search of the solution space. Second, to mitigate the imbalance between PO’s global exploration and local exploitation phases, the nonlinear factor is proposed. Leveraging its adaptability and nonlinear curve characteristics, this factor improves the algorithm’s ability to escape local optimal segmentation thresholds. Finally, to overcome PO’s inadequate local exploitation capability, the third-order Bernstein-guided strategy is introduced. By incorporating the weighted properties of third-order Bernstein polynomials, this strategy comprehensively evaluates individuals with diverse characteristics, thereby enhancing the precision of mural image segmentation. ANBPO was applied to segment twelve mural images. The results demonstrate that, compared to competing algorithms, ANBPO achieves a 91.6% win rate in fitness function values while outperforming them by 67.6%, 69.4%, and 69.7% in PSNR, SSIM, and FSIM metrics, respectively. These results confirm that the ANBPO algorithm can effectively segment mural images while preserving the original feature information. Thus, it can be regarded as an efficient mural image segmentation algorithm. Full article

Background: MRI-based radiomics has emerged as a promising approach to enhance the non-invasive, presurgical assessment of lymph node staging in rectal cancer (RC). However, its clinical implementation remains limited due to methodological variability in published studies. We conducted a systematic review and meta-analysis to synthesize the diagnostic performance of MRI-based radiomics models for predicting pathological nodal status (pN) in RC. Methods: A systematic literature search was conducted in PubMed, Web of Science, and Scopus for studies published until 31 December 2024. Eligible studies applied MRI-based radiomics for pN prediction in RC patients. We excluded other imaging sources and models combining radiomics and other data (e.g., clinical). All models with available outcome metrics were included in data analysis. Data extraction and quality assessment (QUADAS-2) were performed independently by two reviewers. Random-effects meta-analyses including hierarchical summary receiver operating characteristic (HSROC) and restricted maximum likelihood estimator (REML) analyses were conducted to pool sensitivity, specificity, area under the curve (AUC), and diagnostic odds ratios (DORs). Sensitivity analyses and publication bias evaluation were also performed. Results: Sixteen studies (n = 3157 patients) were included. The HSROC showed pooled sensitivity, specificity, and AUC values of 0.68 (95% CI, 0.63–0.72), 0.73 (95% CI, 0.68–0.78), and 0.70 (95% CI, 0.65–0.75), respectively. The mean pooled AUC and DOR obtained by REML were 0.78 (95% CI, 0.75–0.80) and 6.03 (95% CI, 4.65–7.82). Funnel plot asymmetry and Egger’s test (p = 0.025) indicated potential publication bias. Conclusions: Overall, MRI-based radiomics models demonstrated moderate accuracy in predicting pN status in RC, with some studies reporting outstanding results. However, heterogeneity in relevant methodological approaches such as the source of MRI sequences or machine learning methods applied along with possible publication bias call for further standardization and preclude their translation to clinical practice. Full article

A key aspect driving advancements in machine learning applications in medicine is the availability of publicly accessible datasets. Evidently, there are studies conducted in the past with promising results, but they are not reproducible due to the fact that the data used are closed or proprietary or the authors were not able to publish them. The current study aims to narrow this gap for researchers who focus on image recognition tasks in microbiology, specifically in fungal identification and classification. An open database named OpenFungi is made available in this work; it contains high-quality images of macroscopic and microscopic fungal genera. The fungal cultures were grown from food products such as green leaf spices and cereals. The quality of the dataset is demonstrated by solving a classification problem with a simple convolutional neural network. A thorough experimental analysis was conducted, where six performance metrics were measured in three distinct validation scenarios. The results obtained demonstrate that in the fungal species classification task, the model achieved an overall accuracy of 99.79%, a true-positive rate of 99.55%, a true-negative rate of 99.96%, and an F1 score of 99.63% on the macroscopic dataset. On the microscopic dataset, the model reached a 97.82% accuracy, a 94.89% true-positive rate, a 99.19% true-negative rate, and a 95.20% F1 score. The results also reveal that the model maintains promising performance even when trained on smaller datasets, highlighting its robustness and generalization capabilities. Full article

Magnetic tiles are an important component of permanent magnet motors, and the quality of magnetic tiles directly affects the performance and service life of a motor. It is necessary to perform defect detection on magnetic tiles in industrial production and remove those with defects. The YOLOv8-AHF algorithm is proposed to improve the ability of network feature information extraction and solve the problem of missed detection or poor detection results in surface defect detection due to the small volume of permanent magnet motor tiles, which reduces the deviation between the predicted box and the true box simultaneously. Firstly, a hybrid module of a combination of atrous convolution and depthwise separable convolution (ADConv) is introduced in the backbone of the model to capture global and local features in magnet tile detection images. In the neck section, a hybrid attention module (HAM) is introduced to focus on the regions of interest in the magnetic tile surface defect images, which improves the ability of information transmission and fusion. The Focal-Enhanced Intersection over Union loss function (Focal-EIoU) is optimized to effectively achieve localization. We conducted comparative experiments, ablation experiments, and corresponding generalization experiments on the magnetic tile surface defect dataset. The experimental results show that the evaluation metrics of YOLOv8-AHF surpass mainstream single-stage object detection algorithms. Compared to the You Only Look Once version 8 (YOLOv8) algorithm, the performance of the YOLOv8-AHF algorithm was improved by 5.9%, 4.1%, 5%, 5%, and 5.8% in terms of mAP@0.5, mAP@0.5:0.95, F1-Score, precision, and recall, respectively. This algorithm achieved significant performance improvement in the task of detecting surface defects on magnetic tiles. Full article

Land–sea segmentation is a fundamental task in remote sensing image analysis, and plays a vital role in dynamic coastline monitoring. The complex morphology and blurred boundaries of coastlines in remote sensing imagery make fast and accurate segmentation challenging. Recent deep learning approaches lack the ability to model spatial continuity effectively, thereby limiting a comprehensive understanding of coastline features in remote sensing imagery. To address this issue, we have developed VMMT-Net, a novel dual-branch semantic segmentation framework. By constructing a parallel heterogeneous dual-branch encoder, VMMT-Net integrates the complementary strengths of the Mix Transformer and the Visual State Space Model, enabling comprehensive modeling of local details, global semantics, and spatial continuity. We design a Cross-Branch Fusion Module to facilitate deep feature interaction and collaborative representation across branches, and implement a customized decoder module that enhances the integration of multiscale features and improves boundary refinement of coastlines. Extensive experiments conducted on two benchmark remote sensing datasets, GF-HNCD and BSD, demonstrate that the proposed VMMT-Net outperforms existing state-of-the-art methods in both quantitative metrics and visual quality. Specifically, the model achieves mean F1-scores of 98.48% (GF-HNCD) and 98.53% (BSD) and mean intersection-over-union values of 97.02% (GF-HNCD) and 97.11% (BSD). The model maintains reasonable computational complexity, with only 28.24 M parameters and 25.21 GFLOPs, striking a favorable balance between accuracy and efficiency. These results indicate the strong generalization ability and practical applicability of VMMT-Net in real-world remote sensing segmentation tasks. Full article

This research investigates the metric accuracy of 3D transparent object reconstruction, a task where conventional photogrammetry often fails. The topic is especially relevant in cultural heritage (CH), where accurate digital documentation of glass and transparent artifacts is important. The work proposes a practical methodology using existing tools to verify metric accuracy standards. The study compares three methods, conventional photogrammetry, 3D Gaussian splatting (3DGS), and 2D Gaussian splatting (2DGS), to assess their ability to produce complete and metrically reliable 3D models suitable for measurement and geometric analysis. A transparent glass artifact serves as the case study. Results show that 2DGS captures fine surface and internal details with better geometric consistency than 3DGS and photogrammetry. Although 3DGS offers high visual quality, it introduces surface artifacts that affect metric reliability. Photogrammetry fails to reconstruct the object entirely. The study highlights that visual quality does not ensure geometric accuracy, which is critical for measurement applications. In this work, ground truth comparisons confirm that 2DGS offers the best trade-off between accuracy and appearance, despite higher computational demands. These findings suggest extending the experimentation to other sets of images featuring transparent objects, and possibly also reflective ones. Full article

Generative image models have revolutionized artificial intelligence by enabling the synthesis of high-quality, realistic images. These models utilize deep learning techniques to learn complex data distributions and generate novel images that closely resemble the training dataset. Recent advancements, particularly in diffusion models, have led to remarkable improvements in image fidelity, diversity, and controllability. In this work, we investigate the application of a conditional latent diffusion model in the healthcare domain. Specifically, we trained a latent diffusion model using unlabeled histopathology images. Initially, these images were embedded into a lower-dimensional latent space using a Vector Quantized Generative Adversarial Network (VQ-GAN). Subsequently, a diffusion process was applied within this latent space, and clustering was performed on the resulting latent features. The clustering results were then used as a conditioning mechanism for the diffusion model, enabling conditional image generation. Finally, we determined the optimal number of clusters using cluster validation metrics and assessed the quality of the synthetic images through quantitative methods. To enhance the interpretability of the synthetic image generation process, expert input was incorporated into the cluster assignments. Full article

Alzheimer’s disease (AD) is a progressive, non-curable neurodegenerative disorder that poses persistent challenges for early diagnosis due to its gradual onset and the difficulty in distinguishing pathological changes from normal aging. Neuroimaging, particularly MRI and PET, plays a key role in detection; however, limitations in data availability and the complexity of early structural biomarkers constrain traditional diagnostic approaches. This review investigates the use of generative models, specifically Generative Adversarial Networks (GANs) and Diffusion Models, as emerging tools to address these challenges. These models are capable of generating high-fidelity synthetic brain images, augmenting datasets, and enhancing machine learning performance in classification tasks. The review synthesizes findings across multiple studies, revealing that GAN-based models achieved diagnostic accuracies up to 99.70%, with image quality metrics such as SSIM reaching 0.943 and PSNR up to 33.35 dB. Diffusion Models, though relatively new, demonstrated strong performance with up to 92.3% accuracy and FID scores as low as 11.43. Integrating generative models with convolutional neural networks (CNNs) and multimodal inputs further improved diagnostic reliability. Despite these advancements, challenges remain, including high computational demands, limited interpretability, and ethical concerns regarding synthetic data. This review offers a comprehensive perspective to inform future AI-driven research in early AD detection. Full article

Introduction: We developed a computed tomography (CT)-based tool designed for automated segmentation of deltoid muscles, enabling quantification of radiomic features and muscle fatty infiltration. Prior to use in a clinical setting, this machine learning (ML)-based segmentation algorithm requires rigorous validation. The aim of this study is to conduct shoulder expert validation of a novel deltoid ML auto-segmentation and quantification tool. Materials and Methods: A SwinUnetR-based ML model trained on labeled CT scans is validated by three expert shoulder surgeons for 32 unique patients. The validation evaluates the quality of the auto-segmented deltoid images. Specifically, each of the three surgeons reviewed the auto-segmented masks relative to CT images, rated masks for clinical acceptance, and performed a correction on the ML-generated deltoid mask if the ML mask did not completely contain the full deltoid muscle, or if the ML mask included any tissue other than the deltoid. Non-inferiority of the ML model was assessed by comparing ML-generated to surgeon-corrected deltoid masks versus the inter-surgeon variation in metrics, such as volume and fatty infiltration. Results: The results of our expert shoulder surgeon validation demonstrates that 97% of ML-generated deltoid masks were clinically acceptable. Only two of the ML-generated deltoid masks required major corrections and only one was deemed clinically unacceptable. These corrections had little impact on the deltoid measurements, as the median error in the volume and fatty infiltration measurements was <1% between the ML-generated deltoid masks and the surgeon-corrected deltoid masks. The non-inferiority analysis demonstrates no significant difference between the ML-generated to surgeon-corrected masks relative to inter-surgeon variations. Conclusions: Shoulder expert validation of this CT image analysis tool demonstrates clinically acceptable performance for deltoid auto-segmentation, with no significant differences observed between deltoid image-based measurements derived from the ML generated masks and those corrected by surgeons. These findings suggest that this CT image analysis tool has potential to reliably quantify deltoid muscle size, shape, and quality. Incorporating these CT image-based measurements into the pre-operative planning process may facilitate more personalized treatment decision making, and help orthopedic surgeons make more evidence-based clinical decisions. Full article

As the resolution and data volume of remote sensing imagery continue to grow, achieving efficient compression without sacrificing reconstruction quality remains a major challenge, given that traditional handcrafted codecs often fail to balance rate-distortion performance and computational complexity, while deep learning-based approaches offer superior representational capacity. However, challenges remain in achieving a balance between fine-detail adaptation and computational efficiency. Mamba, a state–space model (SSM)-based architecture, offers linear-time complexity and excels at capturing long-range dependencies in sequences. It has been adopted in remote sensing compression tasks to model long-distance dependencies between pixels. However, despite its effectiveness in global context aggregation, Mamba’s uniform bidirectional scanning is insufficient for capturing high-frequency structures such as edges and textures. Moreover, existing visual state–space (VSS) models built upon Mamba typically treat all channels equally and lack mechanisms to dynamically focus on semantically salient spatial regions. To address these issues, we present an innovative architecture for distant sensing image compression, called the Multi-scale Channel Global Mamba Network (MGMNet). MGMNet integrates a spatial–channel dynamic weighting mechanism into the Mamba architecture, enhancing global semantic modeling while selectively emphasizing informative features. It comprises two key modules. The Wavelet Transform-guided Local Structure Decoupling (WTLS) module applies multi-scale wavelet decomposition to disentangle and separately encode low- and high-frequency components, enabling efficient parallel modeling of global contours and local textures. The Channel–Global Information Modeling (CGIM) module enhances conventional VSS by introducing a dual-path attention strategy that reweights spatial and channel information, improving the modeling of long-range dependencies and edge structures. We conducted extensive evaluations on three distinct remote sensing datasets to assess the MGMNet. The results of the investigations revealed that MGMNet outperforms the current SOTA models across various performance metrics. Full article

Background/Objective: The approach to the clinical management of metastatic melanoma patients is undergoing a significant transformation. The availability of a large amount of data from medical images has made Artificial Intelligence (AI) applications an innovative and cutting-edge solution that could revolutionize the surveillance and management of these patients. In this study, we develop and validate a machine-learning model based on radiomic data extracted from a computed tomography (CT) analysis of patients with metastatic melanoma (MM). This approach was designed to accurately predict prognosis and identify the potential key factors associated with prognosis. Methods: To achieve this goal, we used radiomic pipelines to extract the quantitative features related to lesion texture, morphology, and intensity from high-quality CT images. We retrospectively collected a cohort of 58 patients with metastatic melanoma, from which a total of 60 CT series were used for model training, and 70 independent CT series were employed for external testing. Model performance was evaluated using metrics such as sensitivity, specificity, and AUC (area under the curve), demonstrating particularly favorable results compared to traditional methods. Results: The model used in this study presented a ROC-AUC curve of 82% in the internal test and, in combination with AI, presented a good predictive ability regarding lesion outcome. Conclusions: Although the cohort size was limited and the data were collected retrospectively from a single institution, the findings provide a promising basis for further validation in larger and more diverse patient populations. This approach could directly support clinical decision-making by providing accurate and personalized prognostic information. Full article