Search Results (209)

Classifying optical water types (OWTs), particularly concerning different phytoplankton bloom types, is critically important because dominant phytoplankton groups govern key marine ecosystem functions and biogeochemical processes, including nutrient cycling and carbon export. This study refines a recent OWT classification method developed for the Second-Generation Global Imager (SGLI), which was originally proposed to discriminate dinoflagellate and diatom blooms. By employing binary logistic regression (bLR) with independent in situ data from Karenia selliformis (dinoflagellate) blooms off the Kamchatka Peninsula and Skeletonema spp. (diatom) blooms in Tokyo Bay, this study establishes more robust and statistically meaningful boundaries between OWTs. The analysis confirms the diagnostic spectral shapes from SGLI data: a trough at 490 nm for K. selliformis blooms and a peak at 490 nm for diatom blooms, validating the consistency of this spectral criterion. The updated method reliably identifies waters dominated by coloured dissolved organic matter and different phytoplankton functional types in mesotrophic waters, and successfully detected a Karenia mikimotoi bloom in the Gulf St. Vincent, South Australia, demonstrating its potential for the global monitoring of red tides. By providing a reliable, satellite-based tool to distinguish between ecologically distinct phytoplankton groups, this refined OWT classification offers a valuable data product to improve the accuracy of marine ecosystem and carbon cycle models, moving beyond bulk chlorophyll-a parameterizations. Full article

The mineral deposits in Namibia’s Erongo region are renowned and frequently associated with complex geological environments, including calcrete-hosted paleochannels and hydrothermal alteration zones. Mineral extraction is hindered by high operational costs, restricted accessibility and stringent environmental regulations. To address these challenges, this study proposes an integrated approach that combines satellite remote sensing and machine learning to map and identify mineralisation-indicative zones. Sentinel 2 Multispectral Instrument (MSI) and Landsat 8 Operational Land Imager (OLI) multispectral data were employed due to their global coverage, spectral fidelity and suitability for geological investigations. Normalized Difference Vegetation Index (NDVI) masking was applied to minimise vegetation interference. Spectral indices—the Clay Index, Carbonate Index, Iron Oxide Index and Ferrous Iron Index—were developed and enhanced using false-colour composites. Principal Component Analysis (PCA) was used to reduce redundancy and extract significant spectral patterns. Supervised classification was performed using Support Vector Machine (SVM), Random Forest (RF) and Maximum Likelihood Classification (MLC), with validation through confusion matrices and metrics such as Overall Accuracy, User’s Accuracy, Producer’s Accuracy and the Kappa coefficient. The results showed that RF achieved the highest accuracy on Landsat 8 and MLC outperformed others on Sentinel 2, while SVM showed balanced performance. Sentinel 2’s higher spatial resolution enabled improved delineation of alteration zones. This approach supports efficient and low-impact mineral prospecting in remote environments. Full article

Background/Objectives: Traditional medical image analysis methods often suffer from locality bias, limiting their ability to model long-range contextual relationships between spatially distributed anatomical structures. To overcome this challenge, this study proposes SPX-GNN (Superpixel Explainable Graph Neural Network). This novel method reformulates image analysis as a structural graph learning problem, capturing both local anomalies and global topological patterns in a holistic manner. Methods: The proposed framework decomposes images into semantically coherent superpixel regions, converting them into graph nodes that preserve topological relationships. Each node is enriched with a comprehensive feature vector encoding complementary diagnostic clues, including colour (CIELAB), texture (LBP and Haralick), shape (Hu moments), and spatial location. A Graph Neural Network is then employed to learn the relational dependencies between these enriched nodes. The method was rigorously evaluated using 5-fold stratified cross-validation on a public dataset comprising 4200 chest X-ray images. Results: SPX-GNN demonstrated exceptional performance in tuberculosis classification, achieving a mean accuracy of 99.82%, an F1-score of 99.45%, and a ROC-AUC of 100.00%. Furthermore, an integrated Explainable Artificial Intelligence module addresses the black box problem by generating semantic importance maps, which illuminate the decision mechanism and enhance clinical reliability. Conclusions: SPX-GNN offers a novel approach that successfully combines high diagnostic accuracy with methodological transparency. By providing a robust and interpretable workflow, this study presents a promising solution for medical imaging tasks where structural information is critical, paving the way for more reliable clinical decision support systems. Full article

Background/Objectives: Differentiating atypical lipomatous tumours (ALT) from lipomas remains challenging, as both share similar clinical and radiological features but require different forms of management. We previously proposed a clinical–radiological score integrating routine parameters to improve preoperative discrimination. This study aimed to externally validate the score in an independent cohort and refine it for enhanced robustness. Methods: We retrospectively analysed 119 patients with lipomatous tumours treated between 2022 and 2024 at an external university hospital. Diagnostic performance of the original models was assessed using receiver operating characteristic analysis. Data were then combined with the initial development cohort (n = 106) to recalibrate the models and define new cut-offs. Results: In the external validation cohort, predictive accuracy decreased compared to the derivation cohort, especially in extremity tumours assessed without contrast (AUC 0.830 vs. 0.942). Across four recalibrated models in the combined dataset (n = 225), diagnostic accuracy remained high (AUCs 0.918–0.954). Models combining clinical and imaging parameters consistently outperformed single-parameter approaches, with contrast enhancement providing the greatest incremental value. Accuracy was lower in trunk-localised tumours, highlighting the need for molecular confirmation in selected subgroups. Conclusions: The re-modelled score demonstrated robust diagnostic accuracy and practicality for routine use, offering a resource-efficient tool to support preoperative risk stratification. While molecular testing remains essential in high-risk cases, the refined score may reduce unnecessary testing and facilitate tailored diagnostic strategies. To support clinical adoption, the score is available as a web application that automatically selects the appropriate model and presents results in a colour-coded format. Full article

An early and accurate detection of retinal lesions is imperative to intercept the course of sight-threatening ailments, such as Diabetic Retinopathy (DR) or Age-related Macular Degeneration (AMD). Manual expert annotation of all such lesions would take a long time and would be subject to interobserver tendencies, especially in large screening projects. This work introduces an end-to-end deep learning pipeline for automated retinal lesion segmentation, tailored to datasets without available expert pixel-level reference annotations. The approach is specifically designed for our needs. A novel multi-stage automated ground truth mask generation method, based on colour space analysis, entropy filtering and morphological operations, and creating reliable pseudo-labels from raw retinal images. These pseudo-labels then serve as the training input for a U-Net architecture, a convolutional encoder–decoder architecture for biomedical image segmentation. To address the inherent class imbalance often encountered in medical imaging, we employ and thoroughly evaluate a novel hybrid loss function combining Focal Loss and Dice Loss. The proposed pipeline was rigorously evaluated on the ‘Eye Image Dataset’ from Kaggle, achieving a state-of-the-art segmentation performance with a Dice Similarity Coefficient of 0.932, Intersection over Union (IoU) of 0.865, Precision of 0.913, and Recall of 0.897. This work demonstrates the feasibility of achieving high-quality retinal lesion segmentation even in resource-constrained environments where extensive expert annotations are unavailable, thus paving the way for more accessible and scalable ophthalmological diagnostic tools. Full article

Background: Pathogenic variants in interphotoreceptor matrix proteoglycan 1 (IMPG1) have been associated with autosomal dominant and recessive retinitis pigmentosa (RP) and autosomal dominant adult vitelliform macular dystrophy (AVMD). Monoallelic pathogenic variants in IMPG2 have been linked to maculopathy and biallelic variants to RP with early onset macular atrophy. Herein we characterise the phenotypic and genotypic features of patients with IMPG1/IMPG2 retinopathy and report novel variants. Methods: Patients with IMPG1 and IMPG2 variants and compatible phenotypes were retrospectively identified. Clinical data were obtained from reviewing the medical records. Phenotypic data included visual acuity, imaging included ultra-widefield pseudo-colour, fundus autofluorescence, and optical coherence tomography (OCT). Genetic testing was performed using next generation sequencing (NGS). Variant pathogenicity was investigated using in silico analysis (SIFT, PolyPhen-2, mutation taster, SpliceAI). The evolutionary conservation of novel missense variants was also investigated. Results: A total of 13 unrelated patients were identified: 2 (1 male; 1 female) with IMPG1 retinopathy and 11 (7 male; 4 female) with IMPG2 retinopathy. Both IMPG1 retinopathy patients were monoallelic: one patient had adult vitelliform macular dystrophy (AVMD) with drusenoid changes while the other had pattern dystrophy (PD), and they presented to clinic at age 81 and 72 years, respectively. There were 5 monoallelic IMPG2 retinopathy patients with a maculopathy phenotype, of whom 1 had PD and 4 had AVMD. The mean age of symptom onset of this group was 54.2 ± 11.8 years, mean age at presentation was 54.8 ± 11.5 years, and mean BCVAs were 0.15 ± 0.12 logMAR OD and −0.01 ± 0.12 logMAR OS. Six biallelic IMPG2 patients had RP with maculopathy, where the mean age of onset symptom onset was 18.4 years, mean age at examination was 68.7 years, and mean BCVAs were 1.90 logMAR OD and 1.82 logMAR OS. Variants in IMPG1 included one missense and one exon deletion. A total of 11 different IMPG2 variants were identified (4 missense, 7 truncating). A splicing defect was predicted for the c.871C>A p.(Arg291Ser) missense IMPG2 variant. One IMPG1 and five IMPG2 variants were novel. Conclusions: This study describes the phenotypic spectrum of IMPG1/IMPG2 retinopathy and six novel variants are reported. The phenotypes of PD and AVMD in monoallelic IMPG2 patients may result from haploinsufficiency, supported by the presence of truncating variants in both monoallelic and biallelic cases. The identification of novel variants expands the known genetic landscape of IMPG1 and IMPG2 retinopathies. These findings contribute to diagnostic accuracy, informed patient counselling regarding inheritance pattern, and may help guide recruitment for future therapeutic interventions. Full article

The spectral characteristics of harmful insect pests in wheat fields were characterised using hyperspectral imaging for the first time. The analysis of spectral profiles revealed that reflectance is determined by the structure of the insect’s chitin and the colouration of its body surface. Insects with lighter or more vivid colours (white, yellow, or green) showed higher reflectance values compared to those with predominantly dark pigmentation. Reflectance was also influenced by the presence of wings, surface roughness, and the age of the insect. Each species exhibited distinct spectral patterns that allowed for differentiation not only from other insect species but also from the plant background. A classification model using PLS-DA was developed and demonstrated high accuracy in identifying 12 pest species, confirming the strong potential of hyperspectral imaging for species-level classification. The results validate the PLS-DA method for differentiating insects based on spectral characteristics and underscore the reliability of this approach for automated monitoring systems to detect phytophagous pests in crop fields. This technology could reduce insecticide use by 30–40% through targeted application. The research has both scientific and economic significance, laying the groundwork for integrating machine learning and computer vision into agricultural monitoring. It supports the advancement of precision farming and contributes to improved global food security. Full article

Purpose: This study aims to develop a method for detecting referable (intermediate and advanced) age-related macular degeneration (AMD) and neovascular AMD, as well as providing an automatic segmentation of choroidal neovascularisation (CNV) on colour fundus retinal images. We also demonstrated that brain health risk scores estimated by AI-based Retinal Image Analysis (ARIA), such as white matter hyperintensities and depression, are significantly associated with AMD and neovascular AMD. Methods: A primary dataset of 1480 retinal images was collected from Zhongshan Hospital of Fudan University for training and 10-fold cross-validation. Additionally, two validation subdataset comprising 238 images (retinal images and wide-field images) were used. Using fluorescein angiography-based labels, we applied the InceptionResNetV2 deep network with the ARIA method to detect AMD, and a transfer ResNet50_Unet was used to segment CNV. The risks of cerebral white matter hyperintensities and depression were estimated using an AI-based Retinal Image Analysis approach. Results: In a 10-fold cross-validation, we achieved sensitivities of 97.4% and 98.1%, specificities of 96.8% and 96.1%, and accuracies of 97.0% and 96.4% in detecting referable AMD and neovascular AMD, respectively. In the external validation, we achieved accuracies of 92.9% and 93.7% and AUCs of 0.967 and 0.967, respectively. The performances on two validation sub-datasets show no statistically significant difference in detecting referable AMD (p = 0.704) and neovascular AMD (p = 0.213). In the segmentation of CNV, we achieved a global accuracy of 93.03%, a mean accuracy of 91.83%, a mean intersection over union (IoU) of 68.7%, a weighted IoU of 89.63%, and a mean boundary F1 (BF) of 67.77%. Conclusions: The proposed method shows promising results as a highly efficient and cost-effective screening tool for detecting neovascular and referable AMD on both retinal and wide-field images, and providing critical insights into CNV. Its implementation could be particularly valuable in resource-limited settings, enabling timely referrals, enhancing patient care, and supporting decision-making across AMD classifications. In addition, we demonstrated that AMD and neovascular AMD are significantly associated with increased risks of WMH and depression. Full article

Apple purée is a processed food typically obtained from ground apples, where quality depends on colour, consistency, and shelf-life. Thermal treatments are commonly applied to adjust rheology and deactivate enzymes responsible for post-packaging deterioration. This study evaluated the effects of heating temperature (87–102 °C) and duration (6–17 min) on the physical and chemical properties of Golden Delicious apple purée. Three independent batches were processed to examine intra-varietal variability. Chemical analyses assessed enzyme activity and nutritional profile, while physical tests focused on rheology. Image analysis was employed to characterise colour and syneresis. Results showed that short-duration heating at higher temperatures (>100 °C, <12 min) achieved desirable rheological properties but intensified browning. No significant correlations were found between residual enzymatic activity, polyphenol content, antioxidant activity, and thermal treatment conditions. This suggests that changes in colour and texture are primarily related to the physical parameters of heating independently of the origin batch. In contrast, the batch had a significant impact on enzymatic and nutritional profiles, highlighting the need for strict monitoring of incoming fruit. Overall, the heating conditions influenced the visual and textural quality of the purée, while the variability in raw materials remained a significant factor affecting its biochemical characteristics. Full article

Purpose: Luggage X-rays suffer from low contrast, material overlap, and noise; dual-energy imaging reduces ambiguity but creates colour biases that impair segmentation. This study aimed to (1) employ connotative fusion by embedding realistic detonator patches into real X-rays to simulate threats and enhance unattended detection without requiring ground-truth labels; (2) thoroughly evaluate fusion techniques in terms of balancing image quality, information content, contrast, and the preservation of meaningful features. Methods: A total of 1000 X-ray luggage images and 150 detonator images were used for fusion experiments based on deep learning, transform-based, and feature-driven methods. The proposed approach does not need ground truth supervision. Deep learning fusion techniques, including VGG, FusionNet, and AttentionFuse, enable the dynamic selection and combination of features from multiple input images. The transform-based fusion methods convert input images into different domains using mathematical transforms to enhance fine structures. The Nonsubsampled Contourlet Transform (NSCT), Curvelet Transform, and Laplacian Pyramid (LP) are employed. Feature-driven image fusion methods combine meaningful representations for easier interpretation. Singular Value Decomposition (SVD), Principal Component Analysis (PCA), Random Forest (RF), and Local Binary Pattern (LBP) are used to capture and compare texture details across source images. Entropy (EN), Standard Deviation (SD), and Average Gradient (AG) assess factors such as spatial resolution, contrast preservation, and information retention and are used to evaluate the performance of the analysed methods. Results: The results highlight the strengths and limitations of the evaluated techniques, demonstrating their effectiveness in producing sharpened fused X-ray images with clearly emphasized targets and enhanced structural details. Conclusions: The Laplacian Pyramid fusion method emerges as the most versatile choice for applications demanding a balanced trade-off. This is evidenced by its overall multi-criteria balance, supported by a composite (geometric mean) score on normalised metrics. It consistently achieves high performance across all evaluated metrics, making it reliable for detecting concealed threats under diverse imaging conditions. Full article

Real-time rendering is increasingly used in augmented and virtual reality (AR/VR), interactive design, and product visualisation, where materials must prioritise efficiency and consistency rather than the extreme accuracy required in offline rendering. In parallel, the growing demand for personalised and customised products has created a need for digital materials that can be generated in-house without relying on expensive commercial systems. To address these requirements, this paper presents a low-cost digitisation workflow based on photometric stereo. The system integrates a custom-built scanner with cross-polarised illumination, automated multi-light image acquisition, a dual-stage colour calibration process, and a node-based reconstruction pipeline that produces albedo and normal maps. A reproducible evaluation methodology is also introduced, combining perceptual colour-difference analysis using the CIEDE2000 ($\Delta E_{00}$) metric with angular-error assessment of normal maps on known-geometry samples. By openly providing the workflow, bill of materials, and implementation details, this work delivers a practical and replicable solution for reliable material capture in real-time rendering and product customisation scenarios. Full article

Halophytes such as Salicornia europaea rely on biochemical and structural mechanisms to survive in saline environments. This study aimed to evaluate oxidative stress and structural defense responses in four inland populations—Poland (Inowrocław, Ciechocinek), Germany (Salzgraben-Salzdahlum, Salz), and Soltauquelle (Soltq)—subjected to 0, 200, 400, and 1000 mM NaCl, using non-destructive, image-based approaches. Lipid peroxidation was assessed via malondialdehyde (MDA) detected with Schiff’s reagent, and hydrogen peroxide (H₂O₂) accumulation was visualized with 3,3′-diaminobenzidine (DAB). Roots and shoots were analyzed through colour image analysis and quantified using a computer vision system (CVS). MDA accumulation revealed population-specific differences, with Salz tending to exhibit lower peroxidation, characterized by lower L* ≈ 42–43 and higher b* ≈ 37–18 in shoots at 200–400 mM, which may reflect a potentially more effective salt-management strategy. Although H₂O₂ responses deviated from a direct salinity-dependent trend, particularly in the tolerant Salz and Soltq populations, both approaches effectively tracked population-specific adaptation, with German populations displaying detectable basal H₂O₂ levels, consistent with its multifunctional signalling role in salt management and growth regulation. Structural defences were further explored through histochemical mapping and image analysis of pectin and lignin distribution, which revealed population-specific patterns consistent with cell wall remodelling under stress. Non-destructive, image-based methods proved effective for detecting oxidative and structural responses in halophytes. Such a non-destructive, cost-efficient, and reproducible approach can accelerate the identification of salt-tolerant ecotypes for saline agriculture and reinforce S. europaea as a model species for elucidating salt-tolerance mechanisms. Full article

Introduction: Oral squamous cell carcinoma (OSCC) is one of the most common tumours worldwide. This study investigated the suitability of visible and near-infrared hyperspectral imaging compared to visual assessment and conventional digital image analysis for quantifying immunohistochemical staining on the example of Dickkopf-3 (DKK-3) in OSCC. Materials and methods: A retrospective analysis of TMAs containing DKK-3 stained OSCC of 50 patients was retrieved from the archives at the Institute of Pathology, Medical University of Innsbruck. TMAs were first evaluated visually, followed by digital image analysis using QuPath (version 0.3.2, open-source software). For hyperspectral imaging, six exemplary cases were selected (three cases with strong expression and three cases with weak expression) and evaluated. The collected hyperspectral images were visualised using TIVITA (Tissue Imaging System). The resulting true-colour images and the classified HSI images were then assessed using the QuPath software. The Allred score and the H-score were used for all analyses. Results: 97 tissue cores were used for visual and digital image analysis. No significant difference was found between the evaluations of visual and digital image analysis using the H-score (pWilcoxon = 0.278), and both H-scores correlated significantly with each other (p^Spearman < 0.001). Similar results were also found using the Allred score. The kappa value was 0.67, which represents a “substantial” correlation. Finally, the H-scores and Allred scores were compared for visual, digital, and HSI imaging. No significant differences were found between the three groups concerning the H-score (pWilcoxon > 0.1). Using Cohen’s Kappa, a “fair” to “moderate” correlation was observed between the three evaluations. Conclusion: Visible and near-infrared hyperspectral imaging (VIS-NIR-HSI) is a promising complementary tool for digital pathology workflows. This proof-of-concept study suggests that HSI offers the potential for more objective quantification of DKK-3 expression in oropharyngeal squamous cell carcinoma, particularly in cases with weak staining. However, given the small sample size and exploratory design, the findings should be regarded as hypothesis-generating. Future studies with larger, clinically annotated cohorts and standardised workflows are needed before any consideration of routine clinical application. Full article

In the face of the challenge of urban water resource degradation, green infrastructure construction has become a core strategy in modern urban water resource management. Urban aquatic horticulture (UAH), as an important component of this strategy, possesses the dual value of ecological purification and landscape aesthetics. However, its practical implementation is often constrained by public awareness and acceptance. This study aims to address the mismatch between the dual values of urban aquatic horticulture and public perception, and to develop an optimised plant selection strategy that integrates purification functions with public perception. Based on literature reviews, 18 images of aquatic plant landscapes showcasing different ornamental forms, species richness, and life types were created. A questionnaire survey was conducted on 320 participants to assess their perceptions of landscape aesthetic appeal and visual preferences, and a quantitative relationship model was established using multiple stepwise linear regression analysis. The public’s aesthetic perception of aquatic plant landscapes with different ornamental forms and species richness varies significantly, with flowering plant landscapes more likely to evoke aesthetic perception than non-flowering landscapes. The public’s visual preferences for landscape attributes significantly influence their aesthetic perception of aquatic plant landscapes. A multiple stepwise linear regression equation was established to model the relationship between the aesthetic perception of aquatic plant community landscapes and the public’s visual preferences for landscape attributes. There is no significant association between species richness and perceived landscape aesthetic appeal. The study developed an optimised selection strategy for aquatic plants that integrates purification functions with public perception, providing theoretical basis and practical guidance for the scientific configuration of aquatic horticultural systems in urban green infrastructure. In landscape design, flowering plants with ornamental value should be prioritised, with emphasis on landscape layers, colour, and spatial shaping to enhance public acceptance and promote the sustainable development of urban water resource management. Full article

Urban parks often represent the last viable habitats for wildlife in city centres, functioning as crucial refuges and biodiversity hotspots for a wide array of plant and animal species. This study investigates the issue of light pollution in urban parks in selected Polish cities from the perspective of sustainable urban development and dark-sky friendly ordinances. Field data conducted in 2024 and 2025 include measurements of Upward Light Output Ratio (ULOR), illuminance, luminance, correlated colour temperature (CCT), and spectral characteristics of light sources. In addition, an analysis of changes in the level of light pollution in the studied parks and their surroundings between 2012 and 2025 was performed using data from the VIIRS (Visible Infrared Imaging Radiometer Suite) located on the Suomi NPP satellite. Results highlight the mismatch between sustainable development objectives and the current practice of lighting in most of the analysed parks. The study emphasises the need for better integration of light pollution mitigation in urban spatial policies and provides recommendations for environmentally and socially responsible lighting design in urban parks. Full article