Diabetes mellitus (DM) is a serious global health concern that poses a significant threat to human life. Beyond its direct impact, diabetes substantially increases the risk of developing severe complications such as hypertension, cardiovascular disease, and musculoskeletal disorders like arthritis and osteoporosis. The field of diabetes classification has advanced significantly with the use of diverse data modalities and sophisticated tools to identify individuals or groups as diabetic. But the task of predicting diabetes prior to its onset, particularly through the use of longitudinal multi-modal data, remains relatively underexplored. To better understand the risk factors associated with diabetes development among Qatari adults, this longitudinal research aims to investigate dual-energy X-ray absorptiometry (DXA)-derived whole-body and regional bone composition measures as potential predictors of diabetes onset. We proposed a case-control retrospective study, with a total of 1,382 participants contains 725 male participants (cases: 146, control: 579) and 657 female participants (case: 133, control: 524). We excluded participants with incomplete data points. To handle class imbalance, we augmented our data using Synthetic Minority Over-sampling Technique (SMOTE) and SMOTEENN (SMOTE with Edited Nearest Neighbors), and to further investigated the association between bones data features and diabetes status, we employed ANOVA analytical method. For diabetes onset prediction, we employed both conventional and deep learning (DL) models to predict risk factors associated with diabetes in Qatari adults. We used SHAP and probabilistic methods to investigate the association of identified risk factors with diabetes. During experimental analysis, we found that bone mineral density (BMD), bone mineral contents (BMC) in the hip, femoral neck, troch area, and lumbar spine showed an upward trend in diabetic patients with [Formula: see text]. Meanwhile, we found that patients with abnormal glucose metabolism had increased wards BMD and BMC with low Z-score compared to healthy participants. Consequently, it shows that the diabetic group has superior bone health than the control group in the cohort, because they exhibit higher BMD, muscle mass, and bone area across most body regions. Moreover, in the age group distribution analysis, we found that the diabetes prediction rate was higher among healthy participants in the younger age group 20-40 years. But as the age range increased, the model predictions became more accurate for diabetic participants, especially in the older age group 56-69 years. It is also observed that male participants demonstrated a higher susceptibility to diabetes onset compared to female participants. Shallow models outperformed the DL models by presenting improved accuracy (91.08%), AUROC (96%), and recall values (91%). This pivotal approach utilizing DXA scans highlights significant potential for the rapid and minimally invasive early detection of diabetes.

We present a novel framework for CBCT-to-MDCT translation, grounded in the Schrodinger Bridge (SB) formulation, which integrates GAN-derived priors with human-guided conditional diffusion. Unlike conventional GANs or diffusion models, our approach explicitly enforces boundary consistency between CBCT inputs and pseudo targets, ensuring both anatomical fidelity and perceptual controllability. Binary human feedback is incorporated via classifier-free guidance (CFG), effectively steering the generative process toward clinically preferred outcomes. Through iterative refinement and tournament-based preference selection, the model internalizes human preferences without relying on a reward model. Subtraction image visualizations reveal that the proposed method selectively attenuates shade artifacts in key anatomical regions while preserving fine structural detail. Quantitative evaluations further demonstrate superior performance across RMSE, SSIM, LPIPS, and Dice metrics on clinical datasets -- outperforming prior GAN- and fine-tuning-based feedback methods -- while requiring only 10 sampling steps. These findings underscore the effectiveness and efficiency of our framework for real-time, preference-aligned medical image translation.

The development of medical imaging techniques has made a significant contribution to clinical decision-making. However, the existence of suboptimal imaging quality, as indicated by irregular illumination or imbalanced intensity, presents significant obstacles in automating disease screening, analysis, and diagnosis. Existing approaches for natural image enhancement are mostly trained with numerous paired images, presenting challenges in data collection and training costs, all while lacking the ability to generalize effectively. Here, we introduce a pioneering training-free Diffusion Model for Universal Medical Image Enhancement, named UniMIE. UniMIE demonstrates its unsupervised enhancement capabilities across various medical image modalities without the need for any fine-tuning. It accomplishes this by relying solely on a single pre-trained model from ImageNet. We conduct a comprehensive evaluation on 13 imaging modalities and over 15 medical types, demonstrating better qualities, robustness, and accuracy than other modality-specific and data-inefficient models. By delivering high-quality enhancement and corresponding accuracy downstream tasks across a wide range of tasks, UniMIE exhibits considerable potential to accelerate the advancement of diagnostic tools and customized treatment plans. UniMIE represents a transformative approach to medical image enhancement, offering a versatile and robust solution that adapts to diverse imaging conditions. By improving image quality and facilitating better downstream analyses, UniMIE has the potential to revolutionize clinical workflows and enhance diagnostic accuracy across a wide range of medical applications.

Brain tumor segmentation plays a critical role in clinical diagnosis and treatment planning, yet the variability in imaging quality across different MRI scanners presents significant challenges to model generalization. To address this, we propose the Edge Iterative MRI Lesion Localization System (EdgeIMLocSys), which integrates Continuous Learning from Human Feedback to adaptively fine-tune segmentation models based on clinician feedback, thereby enhancing robustness to scanner-specific imaging characteristics. Central to this system is the Graph-based Multi-Modal Interaction Lightweight Network for Brain Tumor Segmentation (GMLN-BTS), which employs a Modality-Aware Adaptive Encoder (M2AE) to extract multi-scale semantic features efficiently, and a Graph-based Multi-Modal Collaborative Interaction Module (G2MCIM) to model complementary cross-modal relationships via graph structures. Additionally, we introduce a novel Voxel Refinement UpSampling Module (VRUM) that synergistically combines linear interpolation and multi-scale transposed convolutions to suppress artifacts while preserving high-frequency details, improving segmentation boundary accuracy. Our proposed GMLN-BTS model achieves a Dice score of 85.1% on the BraTS2017 dataset with only 4.58 million parameters, representing a 98% reduction compared to mainstream 3D Transformer models, and significantly outperforms existing lightweight approaches. This work demonstrates a synergistic breakthrough in achieving high-accuracy, resource-efficient brain tumor segmentation suitable for deployment in resource-constrained clinical environments.

Brain tumor segmentation plays a critical role in clinical diagnosis and treatment planning, yet the variability in imaging quality across different MRI scanners presents significant challenges to model generalization. To address this, we propose the Edge Iterative MRI Lesion Localization System (EdgeIMLocSys), which integrates Continuous Learning from Human Feedback to adaptively fine-tune segmentation models based on clinician feedback, thereby enhancing robustness to scanner-specific imaging characteristics. Central to this system is the Graph-based Multi-Modal Interaction Lightweight Network for Brain Tumor Segmentation (GMLN-BTS), which employs a Modality-Aware Adaptive Encoder (M2AE) to extract multi-scale semantic features efficiently, and a Graph-based Multi-Modal Collaborative Interaction Module (G2MCIM) to model complementary cross-modal relationships via graph structures. Additionally, we introduce a novel Voxel Refinement UpSampling Module (VRUM) that synergistically combines linear interpolation and multi-scale transposed convolutions to suppress artifacts while preserving high-frequency details, improving segmentation boundary accuracy. Our proposed GMLN-BTS model achieves a Dice score of 85.1% on the BraTS2017 dataset with only 4.58 million parameters, representing a 98% reduction compared to mainstream 3D Transformer models, and significantly outperforms existing lightweight approaches. This work demonstrates a synergistic breakthrough in achieving high-accuracy, resource-efficient brain tumor segmentation suitable for deployment in resource-constrained clinical environments.

F3-Net is a foundation model designed to overcome persistent challenges in clinical medical image segmentation, including reliance on complete multimodal inputs, limited generalizability, and narrow task specificity. Through flexible synthetic modality training, F3-Net maintains robust performance even in the presence of missing MRI sequences, leveraging a zero-image strategy to substitute absent modalities without relying on explicit synthesis networks, thereby enhancing real-world applicability. Its unified architecture supports multi-pathology segmentation across glioma, metastasis, stroke, and white matter lesions without retraining, outperforming CNN-based and transformer-based models that typically require disease-specific fine-tuning. Evaluated on diverse datasets such as BraTS 2021, BraTS 2024, and ISLES 2022, F3-Net demonstrates strong resilience to domain shifts and clinical heterogeneity. On the whole pathology dataset, F3-Net achieves average Dice Similarity Coefficients (DSCs) of 0.94 for BraTS-GLI 2024, 0.82 for BraTS-MET 2024, 0.94 for BraTS 2021, and 0.79 for ISLES 2022. This positions it as a versatile, scalable solution bridging the gap between deep learning research and practical clinical deployment.

Current challenges in developing foundational models for volumetric imaging data, such as magnetic resonance imaging (MRI), stem from the computational complexity of training state-of-the-art architectures in high dimensions and curating sufficiently large datasets of volumes. To address these challenges, we introduce Raptor (Random Planar Tensor Reduction), a train-free method for generating semantically rich embeddings for volumetric data. Raptor leverages a frozen 2D foundation model, pretrained on natural images, to extract visual tokens from individual cross-sections of medical volumes. These tokens are then spatially compressed using random projections, significantly reducing computational complexity while retaining semantic information. Extensive experiments on ten diverse medical volume tasks verify the superior performance of Raptor over state-of-the-art methods, including those pretrained exclusively on medical volumes (+3% SuPreM, +6% MISFM, +10% Merlin, +13% VoCo, and +14% SLIViT), while entirely bypassing the need for costly training. Our results highlight the effectiveness and versatility of Raptor as a foundation for advancing deep learning-based methods for medical volumes.

Lung cancer remains the leading cause of cancer-related mortality worldwide, largely due to late-stage diagnosis. Early detection is critical for improving patient outcomes, yet current screening methods, such as low-dose computed tomography (CT), often lack the sensitivity and specificity required for early-stage detection. Here, we present a multimodal early screening platform that integrates a multiplexed laser-induced graphene (LIG) immunosensor with machine learning to enhance the accuracy of lung cancer diagnosis. Our platform enables the rapid, cost-effective, and simultaneous detection of four tumor markers─neuron-specific enolase (NSE), carcinoembryonic antigen (CEA), p53, and SOX2─with limits of detection (LOD) as low as 1.62 pg/mL. By combining proteomic data from the immunosensor with deep learning-based CT imaging features and clinical data, we developed a multimodal predictive model that achieves an area under the curve (AUC) of 0.936, significantly outperforming single-modality approaches. This platform offers a transformative solution for early lung cancer screening, particularly in resource-limited settings, and provides potential technical support for precision medicine in oncology.

In pediatric orthodontics, accurate estimation of growth potential is essential for developing effective treatment strategies. Our research aims to predict this potential by identifying the growth peak and analyzing cervical vertebra morphology solely through lateral cephalometric radiographs. We accomplish this by comprehensively analyzing cervical vertebral maturation (CVM) features from these radiographs. This methodology provides clinicians with a reliable and efficient tool to determine the optimal timings for orthodontic interventions, ultimately enhancing patient outcomes. A crucial aspect of this approach is the meticulous annotation of keypoints on the cervical vertebrae, a task often challenged by its labor-intensive nature. To mitigate this, we introduce Attend-and-Refine Network (ARNet), a user-interactive, deep learning-based model designed to streamline the annotation process. ARNet features Interaction-guided recalibration network, which adaptively recalibrates image features in response to user feedback, coupled with a morphology-aware loss function that preserves the structural consistency of keypoints. This novel approach substantially reduces manual effort in keypoint identification, thereby enhancing the efficiency and accuracy of the process. Extensively validated across various datasets, ARNet demonstrates remarkable performance and exhibits wide-ranging applicability in medical imaging. In conclusion, our research offers an effective AI-assisted diagnostic tool for assessing growth potential in pediatric orthodontics, marking a significant advancement in the field.

Background: Accurate forecasting of lung tumor motion is essential for precise dose delivery in proton therapy. While current markerless methods mostly rely on deep learning, transformer-based architectures remain unexplored in this domain, despite their proven performance in trajectory forecasting. Purpose: This work introduces a markerless forecasting approach for lung tumor motion using Vision Transformers (ViT). Two training strategies are evaluated under clinically realistic constraints: a patient-specific (PS) approach that learns individualized motion patterns, and a multi-patient (MP) model designed for generalization. The comparison explicitly accounts for the limited number of images that can be generated between planning and treatment sessions. Methods: Digitally reconstructed radiographs (DRRs) derived from planning 4DCT scans of 31 patients were used to train the MP model; a 32nd patient was held out for evaluation. PS models were trained using only the target patient's planning data. Both models used 16 DRRs per input and predicted tumor motion over a 1-second horizon. Performance was assessed using Average Displacement Error (ADE) and Final Displacement Error (FDE), on both planning (T1) and treatment (T2) data. Results: On T1 data, PS models outperformed MP models across all training set sizes, especially with larger datasets (up to 25,000 DRRs, p < 0.05). However, MP models demonstrated stronger robustness to inter-fractional anatomical variability and achieved comparable performance on T2 data without retraining. Conclusions: This is the first study to apply ViT architectures to markerless tumor motion forecasting. While PS models achieve higher precision, MP models offer robust out-of-the-box performance, well-suited for time-constrained clinical settings.