Proton therapy is commonly used for treating hepatocellular carcinoma (HCC); however, its feasibility can be challenging to assess in large tumors or those adjacent to critical organs at risk (OARs), which are typically assessed only after planning computed tomography (CT) acquisition. This study aimed to predict proton dose distributions using diagnostic CT (dCT) and diagnostic MRI (dMRI) with a convolutional neural network (CNN), enabling early treatment feasibility assessments. Dose distributions and dose-volume histograms (DVHs) were calculated for 118 patients with HCC using intensity-modulated proton therapy (IMPT) and passive proton therapy. A CPU-based CNN model was used to predict DVHs and 3D dose distributions from diagnostic images. Prediction accuracy was evaluated using mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and gamma passing rate with a 3 mm/3% criterion. The predicted DVHs and dose distributions showed high agreement with actual values. MAE remained below 3.0%, with passive techniques achieving 1.2-1.8%. MSE was below 0.004 in all cases. PSNR ranged from 24 to 28 dB, and SSIM exceeded 0.94 in most conditions. Gamma passing rates averaged 82-83% for IMPT and 92-93% for passive techniques. The model achieved comparable accuracy when using dMRI and dCT. This study demonstrates that early dose distribution prediction from diagnostic imaging is feasible and accurate using a lightweight CNN model. Despite anatomical variability between diagnostic and planning images, this approach provides timely insights into treatment feasibility, potentially supporting insurance pre-authorization, reducing unnecessary imaging, and optimizing clinical workflows for HCC proton therapy.

Pancreatic ductal adenocarcinoma (PDAC) exhibits high metastatic potential, with distinct prognoses based on metastatic sites. Radiomics enables quantitative imaging analysis for predictive modeling. To evaluate the feasibility of radiomic models in predicting PDAC metastatic patterns, specifically distinguishing between hepatic and pulmonary metastases. This retrospective study included 115 PDAC patients with either liver (n = 94) or lung (n = 21) metastases. Radiomic features were extracted from pancreatic arterial and venous phase CT scans of primary tumors using PyRadiomics. Two radiologists independently segmented tumors for inter-reader reliability assessment. Features with ICC > 0.9 underwent LASSO regularization for feature selection. Class imbalance was addressed using SMOTE and class weighting. Model performance was evaluated using fivefold cross-validation and bootstrap resampling. The multivariate logistic regression model achieved an AUC-ROC of 0.831 (95% CI: 0.752-0.910). At the optimal threshold, sensitivity was 0.762 (95% CI: 0.659-0.865) and specificity was 0.787 (95% CI: 0.695-0.879). The negative predictive value for lung metastases was 0.810 (95% CI: 0.734-0.886). LargeDependenceEmphasis showed a trend toward significance (p = 0.0566) as a discriminative feature. Precision was 0.842, recall 0.762, and F1 score 0.800. Radiomic analysis of primary pancreatic tumors demonstrates potential for predicting hepatic versus pulmonary metastatic patterns. The high negative predictive value for lung metastases may support clinical decision-making. External validation is essential before clinical implementation. These findings from a single-center study require confirmation in larger, multicenter cohorts.

We developed an MRI-based habitat radiomics model (HRM) to predict p53-abnormal (p53abn) molecular subtypes of endometrial cancer (EC). Patients with pathologically confirmed EC were retrospectively enrolled from three hospitals and categorized into a training cohort (n = 270), test cohort 1 (n = 70), and test cohort 2 (n = 154). The tumour was divided into habitat sub-regions using diffusion-weighted imaging (DWI) and contrast-enhanced (CE) images with the K-means algorithm. Radiomics features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), DWI, and CE images. Three machine learning classifiers-logistic regression, support vector machines, and random forests-were applied to develop predictive models for p53abn EC. Model performance was validated using receiver operating characteristic (ROC) curves, and the model with the best predictive performance was selected as the HRM. A whole-region radiomics model (WRM) was also constructed, and a clinical model (CM) with five clinical features was developed. The SHApley Additive ExPlanations (SHAP) method was used to explain the outputs of the models. DeLong's test evaluated and compared the performance across the cohorts. A total of 1920 habitat radiomics features were considered. Eight features were selected for the HRM, ten for the WRM, and three clinical features for the CM. The HRM achieved the highest AUC: 0.855 (training), 0.769 (test1), and 0.766 (test2). The AUCs of the WRM were 0.707 (training), 0.703 (test1), and 0.738 (test2). The AUCs of the CM were 0.709 (training), 0.641 (test1), and 0.665 (test2). The MRI-based HRM successfully predicted p53abn EC. The results indicate that habitat combined with machine learning, radiomics, and SHAP can effectively predict p53abn EC, providing clinicians with intuitive insights and interpretability regarding the impact of risk factors in the model.

Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misinterpretation. We performed the first large-scale, systematic comparison of XAI methods on ~45,000 structural brain MRIs using a novel XAI validation framework. This framework establishes verifiable ground truth by constructing prediction tasks with known signal sources - from localized anatomical features to subject-specific clinical lesions - without artificially altering input images. Our analysis reveals systematic failures in two of the most widely used methods: GradCAM consistently failed to localize predictive features, while Layer-wise Relevance Propagation generated extensive, artifactual explanations that suggest incompatibility with neuroimaging data characteristics. Our results indicate that these failures stem from a domain mismatch, where methods with design principles tailored to natural images require substantial adaptation for neuroimaging data. In contrast, the simpler, gradient-based method SmoothGrad, which makes fewer assumptions about data structure, proved consistently accurate, suggesting its conceptual simplicity makes it more robust to this domain shift. These findings highlight the need for domain-specific adaptation and validation of XAI methods, suggest that interpretations from prior neuroimaging studies using standard XAI methodology warrant re-evaluation, and provide urgent guidance for practical application of XAI in neuroimaging.

Radiology report generation (RRG) for diagnostic images, such as chest X-rays, plays a pivotal role in both clinical practice and AI. Traditional free-text reports suffer from redundancy and inconsistent language, complicating the extraction of critical clinical details. Structured radiology report generation (S-RRG) offers a promising solution by organizing information into standardized, concise formats. However, existing approaches often rely on classification or visual question answering (VQA) pipelines that require predefined label sets and produce only fragmented outputs. Template-based approaches, which generate reports by replacing keywords within fixed sentence patterns, further compromise expressiveness and often omit clinically important details. In this work, we present a novel approach to S-RRG that includes dataset construction, model training, and the introduction of a new evaluation framework. We first create a robust chest X-ray dataset (MIMIC-STRUC) that includes disease names, severity levels, probabilities, and anatomical locations, ensuring that the dataset is both clinically relevant and well-structured. We train an LLM-based model to generate standardized, high-quality reports. To assess the generated reports, we propose a specialized evaluation metric (S-Score) that not only measures disease prediction accuracy but also evaluates the precision of disease-specific details, thus offering a clinically meaningful metric for report quality that focuses on elements critical to clinical decision-making and demonstrates a stronger alignment with human assessments. Our approach highlights the effectiveness of structured reports and the importance of a tailored evaluation metric for S-RRG, providing a more clinically relevant measure of report quality.

Medical image segmentation is crucial for disease diagnosis and treatment planning, yet developing robust segmentation models often requires substantial computational resources and large datasets. Existing research shows that pre-trained and finetuned foundation models can boost segmentation performance. However, questions remain about how particular image preprocessing steps may influence segmentation performance across different medical imaging modalities. In particular, edges-abrupt transitions in pixel intensity-are widely acknowledged as vital cues for object boundaries but have not been systematically examined in the pre-training of foundation models. We address this gap by investigating to which extend pre-training with data processed using computationally efficient edge kernels, such as kirsch, can improve cross-modality segmentation capabilities of a foundation model. Two versions of a foundation model are first trained on either raw or edge-enhanced data across multiple medical imaging modalities, then finetuned on selected raw subsets tailored to specific medical modalities. After systematic investigation using the medical domains Dermoscopy, Fundus, Mammography, Microscopy, OCT, US, and XRay, we discover both increased and reduced segmentation performance across modalities using edge-focused pre-training, indicating the need for a selective application of this approach. To guide such selective applications, we propose a meta-learning strategy. It uses standard deviation and image entropy of the raw image to choose between a model pre-trained on edge-enhanced or on raw data for optimal performance. Our experiments show that integrating this meta-learning layer yields an overall segmentation performance improvement across diverse medical imaging tasks by 16.42% compared to models pre-trained on edge-enhanced data only and 19.30% compared to models pre-trained on raw data only.

Artificial intelligence (AI) is increasingly being explored as a complementary tool to traditional fracture risk assessment methods. Conventional approaches, such as bone mineral density measurement and established clinical risk calculators, provide populationlevel stratification but often fail to capture the structural nuances of bone fragility. Recent advances in AI-particularly deep learning techniques applied to imaging-enable opportunistic screening and individualized risk estimation using routinely acquired radiographs and computed tomography (CT) data. These models demonstrate improved discrimination for osteoporotic fracture detection and risk prediction, supporting applications such as time-to-event modeling and short-term prognosis. CT- and radiograph-based models have shown superiority over conventional metrics in diverse cohorts, while innovations like multitask learning and survival plots contribute to enhanced interpretability and patient-centered communication. Nevertheless, challenges related to model generalizability, data bias, and automation bias persist. Successful clinical integration will require rigorous external validation, transparent reporting, and seamless embedding into electronic medical systems. This review summarizes recent advances in AI-driven fracture assessment, critically evaluates their clinical promise, and outlines a roadmap for translation into real-world practice.

Radiotherapy treatment planning often relies on time-consuming, trial-and-error adjustments that heavily depend on the expertise of specialists, while existing deep learning methods face limitations in generalization, prediction accuracy, and clinical applicability. To tackle these challenges, we propose ADDiff-Dose, an Anatomical-Dose Dual Constraints Conditional Diffusion Model for end-to-end multi-tumor dose prediction. The model employs LightweightVAE3D to compress high-dimensional CT data and integrates multimodal inputs, including target and organ-at-risk (OAR) masks and beam parameters, within a progressive noise addition and denoising framework. It incorporates conditional features via a multi-head attention mechanism and utilizes a composite loss function combining MSE, conditional terms, and KL divergence to ensure both dosimetric accuracy and compliance with clinical constraints. Evaluation on a large-scale public dataset (2,877 cases) and three external institutional cohorts (450 cases in total) demonstrates that ADDiff-Dose significantly outperforms traditional baselines, achieving an MAE of 0.101-0.154 (compared to 0.316 for UNet and 0.169 for GAN models), a DICE coefficient of 0.927 (a 6.8% improvement), and limiting spinal cord maximum dose error to within 0.1 Gy. The average plan generation time per case is reduced to 22 seconds. Ablation studies confirm that the structural encoder enhances compliance with clinical dose constraints by 28.5%. To our knowledge, this is the first study to introduce a conditional diffusion model framework for radiotherapy dose prediction, offering a generalizable and efficient solution for automated treatment planning across diverse tumor sites, with the potential to substantially reduce planning time and improve clinical workflow efficiency.

Glioblastoma is one of the most aggressive and common brain tumors, with a median survival of 10-15 months. Predicting Overall Survival (OS) is critical for personalizing treatment strategies and aligning clinical decisions with patient outcomes. In this study, we propose a novel Artificial Intelligence (AI) approach for OS prediction using Magnetic Resonance Imaging (MRI) images, exploiting Vision Transformers (ViTs) to extract hidden features directly from MRI images, eliminating the need of tumor segmentation. Unlike traditional approaches, our method simplifies the workflow and reduces computational resource requirements. The proposed model was evaluated on the BRATS dataset, reaching an accuracy of 62.5% on the test set, comparable to the top-performing methods. Additionally, it demonstrated balanced performance across precision, recall, and F1 score, overcoming the best model in these metrics. The dataset size limits the generalization of the ViT which typically requires larger datasets compared to convolutional neural networks. This limitation in generalization is observed across all the cited studies. This work highlights the applicability of ViTs for downsampled medical imaging tasks and establishes a foundation for OS prediction models that are computationally efficient and do not rely on segmentation.

Accurately segmenting the pancreas from abdominal computed tomography (CT) images is crucial for detecting and managing pancreatic diseases, such as diabetes and tumors. Type 2 diabetes and metabolic syndrome are associated with pancreatic fat accumulation. Calculating the fat fraction aids in the investigation of β-cell malfunction and insulin resistance. The most widely used pancreas segmentation technique is a U-shaped network based on deep convolutional neural networks (DCNNs). They struggle to capture long-range biases in an image because they rely on local receptive fields. This research proposes a novel dual Self-attentive Transformer Unet (DSTUnet) model for accurate pancreatic segmentation, addressing this problem. This model incorporates dual self-attention Swin transformers on both the encoder and decoder sides to facilitate global context extraction and refine candidate regions. After segmenting the pancreas using a DSTUnet, a histogram analysis is used to estimate the fat fraction. The suggested method demonstrated excellent performance on the standard dataset, achieving a DSC of 93.7% and an HD of 2.7 mm. The average volume of the pancreas was 92.42, and its fat volume fraction (FVF) was 13.37%.