United International University

Brain tumor segmentation remains a significant challenge in medical image analytics due to the limited ability of current models to detect small lesions, capture spectral information, and represent anatomical context effectively. This study introduces the Frequency-Quantum-Graph Network (FQG-Net), an analytical framework that integrates quantum computing principles, adaptive frequency-domain processing, and graph-based contextual learning to enhance segmentation precision. The model employs quantum entanglement and superposition effects to enrich feature representation, an adaptive frequency enhancement mechanism to amplify tumor-specific spectral characteristics, and a graph neural contextual memory to preserve spatial and anatomical relationships. Multimodal MRI data are processed through selective quantum residual blocks that dynamically activate network components based on analytical requirements, ensuring both efficiency and stability. Empirical evaluations across multiple benchmark datasets demonstrate that FQG-Net delivers consistent improvements over state-of-the-art segmentation models, achieving higher accuracy, stronger generalization across datasets, and superior performance in detecting small and heterogeneous tumor regions. These findings highlight the analytical strength of quantum-enhanced deep learning and its potential to advance precision diagnostics in healthcare imaging. • Present an analytical model combining quantum learning and graph memory for brain tumor segmentation. • Develop an adaptive frequency module to enhance tumor feature detection in medical imaging. • Integrate quantum attention with contextual graph learning for precise lesion identification. • Employ multimodal imaging analytics to improve diagnostic accuracy and generalizability. • Demonstrate consistent cross-dataset performance, validating robustness in clinical analytics.

Abstract This article examines the doctrinal stability and practical fragility of the international legal prohibition of annexation and evaluates how the UN Charter system has operated against annexation in practice. It clarifies the taxonomy of annexation—distinguishing de jure and de facto annexation from belligerent occupation—and traces the sources grounding the non-acquisition rule and the corresponding duties of non-recognition and non-assistance. Building on Brunk and Hakimi’s argument that the prohibition of annexation is an autonomous norm not reducible to Article 2(4), this article assesses how far the Charter-era jus ad bellum architecture has nevertheless treated ‘force’ as its organizing centre, and what this has meant for enforcement. It then evaluates effectiveness across selected cases using three criteria: deterrence ex ante, remedy ex post, and consistency across like cases. The study finds a mixed record: while doctrine is comparatively stable, inconsistent enforcement and selective (non-) recognition have limited deterrence, complicated reversals, and produced uneven treatment, with implications for self-determination and customary law. Rather than proposing to redefine Article 2(4), this article argues that today’s principal risks lie in post-force consolidation, pretextual justifications, and other strategies that shift contestation to the ‘force’ characterization while annexation’s autonomous consequences remain engaged. The conclusion urges more consistent application of non-recognition and non-assistance to prevent faits accomplis from hardening into tolerated title.

Damaged road surfaces have a significant effect on infrastructure costs, vehicle performance, and public transportation safety. For extensive road monitoring, nations like Bangladesh rely entirely on manual inspection, which is much more time-consuming and unreliable. Every year, a large number of people in Bangladesh lose their lives in traffic accidents. Road degradation is one of the primary causes of these accidents. Roads in Bangladesh suffer significant damage during the rainy season, with deep potholes appearing everywhere and flaws that are difficult for models to see. In this study, an automated method for identifying and categorizing road damage is presented. Road damage comes in numerous forms, including cracks, potholes, surface wear, rutting, and repair. Given how badly damaged Bangladeshi roads are, we divide the damage into two categories: potholes are given special consideration, while cracks are simply called cracks. Due to road quality, we did not use public datasets from other countries in contrast to previous research. Since potholes are the primary issue on Bangladeshi roads, this study contributes a custom data set of 12,650 images that are divided into two classes: pothole and crack. In addition, there are 13,051 images that focus solely on potholes, which are gathered under a variety of lighting conditions, camera angles, and environmental factors. Damages are plainly annotated because each image is manually labeled. In the pothole-only dataset, the model’s mAP@50 was 83.4%, its precision was 85.12%, and its recall was 74.22%. In the two-class data set, it was 50.9%, its precision was 57.6% and its recall was 49.2%.

As the world adjusts to the current SARS-CoV-2 epidemic, another zoonotic disease caused by a monkeypox virus has emerged across the world poses a major public health issues, demanding the use of precise and efficient diagnostic methods for detection and classification. In this paper, we offer a new deep learning framework that combines ensemble modeling with mechanisms of attention to improve monkeypox disease detection and classification. We extracted discriminative features from Monkeypox Skin Lesion Dataset version 2.0 using ten pre-trained convolutional neural network models enhanced with attention mechanisms. Later we combined the best models into ensemble model for further improvement of model performance. We proposed a majority voting ensemble model of ResNet50V2, DenseNet121, DenseNet201 where each standalone model is modified with Convolutional Block Attention Mechanism. Our approach produced remarkable results with an accuracy of 94.43% for multiclass and 96.95% for binary classification which proving our proposed model’s robustness and effectiveness in identifying monkeypox skin lesions. We used explainable artificial intelligence approaches such as Grad-CAM, SHAP, and LIME to ensure transparency and interpretability. These methods provided insights into the model’s decision-making process by emphasizing significant locations and features that contributed to the predictions. This study not only advances the field of automated monkeypox diagnosis, but it also emphasizes the need of using attention processes and ensemble strategy to improve classification performance while preserving model interpretability.

Diabetic Retinopathy (DR), a retinal condition associated with diabetes mellitus, is a leading global cause of blindness. Early detection and treatment is crucial to prevent or mitigate vision loss. Researchers have developed various artificial intelligence-based methods to detect diabetic retinopathy from fundus images, aiming to enhance diagnostic accuracy and efficiency, thereby improving patient outcomes. In this paper, we have introduced a custom convolutional neural network (CNN) architecture for detecting diabetic retinopathy. We have used an open-source “Diabetic Retinopathy 224×224 Gaussian Filtered” dataset from Kaggle, comprising of 3,668 images. The images are then labelled into two classes where one class represents “No Diabetic Retinopathy (No_DR)” and the other class represents “Diabetic Retinopathy (DR)”. Then we have applied min-max normalization to scale pixel values to a specified range [0, 1]. Afterwards, the dataset is divided into three parts to train, validate and test the proposed CNN model. Our method has achieved a testing accuracy of 95.27% and F1 score of 95.29%. Then we have performed 5-fold cross validation to observe the performance of the proposed automatic DR detection method. We have also compared our proposed method with some pre-trained models and some existing methods. In observation, it has been shown that the proposed technique outperformed many other existing techniques.

Parkinson’s disease (PD) is one of the fastest‐growing neurodegenerative disorders, where timely diagnosis is essential for optimizing treatment. In this study, we created a radiomics–MDS‐UPDRS, a robust dataset by integrating DaTscan SPECT radiomics data with the clinical characteristics of MDS‐UPDRS collected from Parkinson’s progression markers initiative (PPMI) to monitor dopamine depletion in the striatum (caudate and putamen) and allow classification and progression analysis of PD. To construct the dataset, the striatum was segmented using a modified K‐means clustering algorithm, extracting 25 radiomics features combined with 59 clinical features. In addition, linear discriminant analysis was used to select 22 significant characteristics, and a four‐way feature selection method was used to identify 30 significant clinical features, resulting in a refined set of 52. Classification with machine learning models improved performance after LDA, achieving over 91% accuracy. We evaluated feature behavior across six PD severity stages and four clinical visits for progression analysis. The clinical features of MDS‐UPDRS were more sensitive to changes in the severity of the initial PD. At the same time, the integrated dataset, radiomics–MDS‐UPDRS, provided more balanced insights, showing a progression of 33.30%–83.30% and 36.36%–45.50% from the first visit to the fourth visit among the clinical and radiomics features and a progression of 73.33%–96.67% and 13.64%–54.55% between the minimal vs mild and minimal vs very severe stage. Our analysis also revealed practical links between progression features and real‐life scenarios, which highlights the practical value of our study for clinical decision‐making.