Radiogenomics holds promise in identifying molecular alterations in nonsmall cell lung cancer (NSCLC) using imaging features. Previously, we developed a radiogenomics model to predict epidermal growth factor receptor (EGFR) mutations based on contrast-enhanced computed tomography (CECT) in NSCLC patients. The current study aimed to externally validate this model using a publicly available National Institutes of Health (NIH)-based NSCLC dataset and assess the effect of EGFR mutation prevalence on model performance through synthetic minority oversampling technique (SMOTE). The original radiogenomics model was validated on an independent NIH cohort (n=140). For assessing the influence of disease prevalence, six SMOTE-augmented datasets were created, simulating EGFR mutation prevalence from 25% to 50%. Seven models were developed (one from original data, six SMOTE-augmented), each undergoing rigorous cross-validation, feature selection, and logistic regression modeling. Models were tested against the NIH cohort. Performance was compared using area under the receiver operating characteristic curve (Area Under the Curve [AUC]), and differences between radiomic-only, clinical-only, and combined models were statistically assessed. External validation revealed poor diagnostic performance for both our model and a previously published EGFR radiomics model (AUC ∼0.5). The clinical model alone achieved higher diagnostic accuracy (AUC 0.74). SMOTE-augmented models showed increased sensitivity but did not improve overall AUC compared to the clinical-only model. Changing EGFR mutation prevalence had minimal impact on AUC, challenging previous assumptions about the influence of sample imbalance on model performance. External validation failed to reproduce prior radiogenomics model performance, while clinical variables alone retained strong predictive value. SMOTE-based oversampling did not improve diagnostic accuracy, suggesting that, in EGFR prediction, radiomics may offer limited value beyond clinical data. Emphasis on robust external validation and data-sharing is essential for future clinical implementation of radiogenomic models.

Hepatocellular carcinoma (HCC) is an aggressive cancer with limited biomarkers for predicting immunotherapy response. Recent advancements in large language models (LLMs) like GPT-4, GPT-4o, and Gemini offer the potential for enhancing clinical decision-making through multimodal data analysis. However, their effectiveness in predicting immunotherapy response, especially compared to human experts, remains unclear. This study assessed the performance of GPT-4, GPT-4o, and Gemini in predicting immunotherapy response in unresectable HCC, compared to radiologists and oncologists of varying expertise. A retrospective analysis of 186 patients with unresectable HCC utilized multimodal data (clinical and CT images). LLMs were evaluated with zero-shot prompting and two strategies: the 'voting method' and the 'OR rule method' for improved sensitivity. Performance metrics included accuracy, sensitivity, area under the curve (AUC), and agreement across LLMs and physicians.GPT-4o, using the 'OR rule method,' achieved 65% accuracy and 47% sensitivity, comparable to intermediate physicians but lower than senior physicians (accuracy: 72%, p = 0.045; sensitivity: 70%, p < 0.0001). Gemini-GPT, combining GPT-4, GPT-4o, and Gemini, achieved an AUC of 0.69, similar to senior physicians (AUC: 0.72, p = 0.35), with 68% accuracy, outperforming junior and intermediate physicians while remaining comparable to senior physicians (p = 0.78). However, its sensitivity (58%) was lower than senior physicians (p = 0.0097). LLMs demonstrated higher inter-model agreement (κ = 0.59-0.70) than inter-physician agreement, especially among junior physicians (κ = 0.15). This study highlights the potential of LLMs, particularly Gemini-GPT, as valuable tools in predicting immunotherapy response for HCC.

Deep learning has been widely used in research on sparse-view computed tomography (CT) image reconstruction. While sufficient training data can lead to high accuracy, collecting medical images is often challenging due to legal or ethical concerns, making it necessary to develop methods that perform well with limited data. To address this issue, we explored the use of nonmedical images for pre-training. Therefore, in this study, we investigated whether fractal images could improve the quality of sparse-view CT images, even with a reduced number of medical images. Fractal images generated by an iterated function system (IFS) were used for nonmedical images, and medical images were obtained from the CHAOS dataset. Sinograms were then generated using 36 projections in sparse-view and the images were reconstructed by filtered back-projection (FBP). FBPConvNet and WNet (first module: learning fractal images, second module: testing medical images, and third module: learning output) were used as networks. The effectiveness of pre-training was then investigated for each network. The quality of the reconstructed images was evaluated using two indices: structural similarity (SSIM) and peak signal-to-noise ratio (PSNR). The network parameters pre-trained with fractal images showed reduced artifacts compared to the network trained exclusively with medical images, resulting in improved SSIM. WNet outperformed FBPConvNet in terms of PSNR. Pre-training WNet with fractal images produced the best image quality, and the number of medical images required for main-training was reduced from 5000 to 1000 (80% reduction). Using fractal images for network training can reduce the number of medical images required for artifact reduction in sparse-view CT. Therefore, fractal images can improve accuracy even with a limited amount of training data in deep learning.

While the acute phase of the COVID-19 pandemic has subsided, its long-term effects persist through Post-Acute Sequelae of COVID-19 (PASC), commonly known as Long COVID. There remains substantial uncertainty regarding both its duration and optimal management strategies. PASC manifests as a diverse array of persistent or newly emerging symptoms--ranging from fatigue, dyspnea, and neurologic impairments (e.g., brain fog), to cardiovascular, pulmonary, and musculoskeletal abnormalities--that extend beyond the acute infection phase. This heterogeneous presentation poses substantial challenges for clinical assessment, diagnosis, and treatment planning. In this paper, we focus on imaging findings that may suggest fibrotic damage in the lungs, a critical manifestation characterized by scarring of lung tissue, which can potentially affect long-term respiratory function in patients with PASC. This study introduces a novel multi-center chest CT analysis framework that combines deep learning and radiomics for fibrosis prediction. Our approach leverages convolutional neural networks (CNNs) and interpretable feature extraction, achieving 82.2% accuracy and 85.5% AUC in classification tasks. We demonstrate the effectiveness of Grad-CAM visualization and radiomics-based feature analysis in providing clinically relevant insights for PASC-related lung fibrosis prediction. Our findings highlight the potential of deep learning-driven computational methods for early detection and risk assessment of PASC-related lung fibrosis--presented for the first time in the literature.

The aim of this study was to develop and validate CT venous phase image-based radiomics to predict BRAF gene mutation status in preoperative colorectal cancer patients. In this study, 301 patients with pathologically confirmed colorectal cancer were retrospectively enrolled, comprising 225 from Centre I (73 mutant and 152 wild-type) and 76 from Centre II (36 mutant and 40 wild-type). The Centre I cohort was randomly divided into a training set (n = 158) and an internal validation set (n = 67) in a 7:3 ratio, while Centre II served as an independent external validation set (n = 76). The whole tumor region of interest was segmented, and radiomics characteristics were extracted. To explore whether tumor expansion could improve the performance of the study objectives, the tumor contour was extended by 3 mm in this study. Finally, a t-test, Pearson correlation, and LASSO regression were used to screen out features strongly associated with BRAF mutations. Based on these features, six classifiers-Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), K-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost)-were constructed. The model performance and clinical utility were evaluated using receiver operating characteristic (ROC) curves, decision curve analysis, accuracy, sensitivity, and specificity. Gender was an independent predictor of BRAF mutations. The unexpanded RF model, constructed using 11 imaging histologic features, demonstrated the best predictive performance. For the training cohort, it achieved an AUC of 0.814 (95% CI 0.732-0.895), an accuracy of 0.810, and a sensitivity of 0.620. For the internal validation cohort, it achieved an AUC of 0.798 (95% CI 0.690-0.907), an accuracy of 0.761, and a sensitivity of 0.609. For the external validation cohort, it achieved an AUC of 0.737 (95% CI 0.616-0.847), an accuracy of 0.658, and a sensitivity of 0.667. A machine learning model based on CT radiomics can effectively predict BRAF mutations in patients with colorectal cancer. The unexpanded RF model demonstrated optimal predictive performance.

Score-based diffusion models have shown significant promise in the field of sparse-view CT reconstruction. However, the projection dataset is large and riddled with redundancy. Consequently, applying the diffusion model to unprocessed data results in lower learning effectiveness and higher learning difficulty, frequently leading to reconstructed images that lack fine details. To address these issues, we propose the ordered-subsets multi-diffusion model (OSMM) for sparse-view CT reconstruction. The OSMM innovatively divides the CT projection data into equal subsets and employs multi-subsets diffusion model (MSDM) to learn from each subset independently. This targeted learning approach reduces complexity and enhances the reconstruction of fine details. Furthermore, the integration of one-whole diffusion model (OWDM) with complete sinogram data acts as a global information constraint, which can reduce the possibility of generating erroneous or inconsistent sinogram information. Moreover, the OSMM's unsupervised learning framework provides strong robustness and generalizability, adapting seamlessly to varying sparsity levels of CT sinograms. This ensures consistent and reliable performance across different clinical scenarios. Experimental results demonstrate that OSMM outperforms traditional diffusion models in terms of image quality and noise resilience, offering a powerful and versatile solution for advanced CT imaging in sparse-view scenarios.

CBCT has become an essential tool in orthodontics, although its use must remain judicious and evidence-based. This study provides an updated analysis of international recommendations concerning the use of CBCT in orthodontics, with a particular focus on clinical indications, radiation dose reduction, and recent technological advancements. A systematic review of guidelines published between 2015 and 2025 was conducted following the PRISMA methodology. Inclusion criteria comprised official directives from recognized scientific societies and clinical studies evaluating low dose protocols in orthodontics. The analysis of the 19 retained recommendations reveals a consensus regarding the primary indications for CBCT in orthodontics, particularly for impacted teeth, skeletal anomalies, periodontal and upper airways assessment. Dose optimization and the integration of artificial intelligence emerge as major advancements, enabling significant radiation reduction while preserving diagnostic accuracy. The development of low dose protocols and advanced reconstruction algorithms presents promising perspectives for safer and more efficient imaging, increasingly replacing conventional 2D radiographic techniques. However, an international harmonization of recommendations for these new imaging sequences is imperative to standardize clinical practices and enhance patient radioprotection.

To compare the diagnostic performance of three proprietary large language models (LLMs)-Claude, GPT, and Gemini-in structuring free-text Japanese radiology reports for intracranial hemorrhage and skull fractures, and to assess the impact of three different prompting approaches on model accuracy. In this retrospective study, head CT reports from the Japan Medical Imaging Database between 2018 and 2023 were collected. Two board-certified radiologists established the ground truth regarding intracranial hemorrhage and skull fractures through independent review and consensus. Each radiology report was analyzed by three LLMs using three prompting strategies-Standard, Chain of Thought, and Self Consistency prompting. Diagnostic performance (accuracy, precision, recall, and F1-score) was calculated for each LLM-prompt combination and compared using McNemar's tests with Bonferroni correction. Misclassified cases underwent qualitative error analysis. A total of 3949 head CT reports from 3949 patients (mean age 59 ± 25 years, 56.2% male) were enrolled. Across all institutions, 856 patients (21.6%) had intracranial hemorrhage and 264 patients (6.6%) had skull fractures. All nine LLM-prompt combinations achieved very high accuracy. Claude demonstrated significantly higher accuracy for intracranial hemorrhage than GPT and Gemini, and also outperformed Gemini for skull fractures (p < 0.0001). Gemini's performance improved notably with Chain of Thought prompting. Error analysis revealed common challenges including ambiguous phrases and findings unrelated to intracranial hemorrhage or skull fractures, underscoring the importance of careful prompt design. All three proprietary LLMs exhibited strong performance in structuring free-text head CT reports for intracranial hemorrhage and skull fractures. While the choice of prompting method influenced accuracy, all models demonstrated robust potential for clinical and research applications. Future work should refine the prompts and validate these approaches in prospective, multilingual settings.

Introduction: Timely identification of intracranial hemorrhage (ICH) subtypes on non-contrast computed tomography is critical for prognosis prediction and therapeutic decision-making, yet remains challenging due to low contrast and blurring boundaries. This study evaluates the performance of zero-shot multi-modal large language models (MLLMs) compared to traditional deep learning methods in ICH binary classification and subtyping. Methods: We utilized a dataset provided by RSNA, comprising 192 NCCT volumes. The study compares various MLLMs, including GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet V2, with conventional deep learning models, including ResNet50 and Vision Transformer. Carefully crafted prompts were used to guide MLLMs in tasks such as ICH presence, subtype classification, localization, and volume estimation. Results: The results indicate that in the ICH binary classification task, traditional deep learning models outperform MLLMs comprehensively. For subtype classification, MLLMs also exhibit inferior performance compared to traditional deep learning models, with Gemini 2.0 Flash achieving an macro-averaged precision of 0.41 and a macro-averaged F1 score of 0.31. Conclusion: While MLLMs excel in interactive capabilities, their overall accuracy in ICH subtyping is inferior to deep networks. However, MLLMs enhance interpretability through language interactions, indicating potential in medical imaging analysis. Future efforts will focus on model refinement and developing more precise MLLMs to improve performance in three-dimensional medical image processing.

Cardiac image segmentation is an important step in many cardiac image analysis and modeling tasks such as motion tracking or simulations of cardiac mechanics. While deep learning has greatly advanced segmentation in clinical settings, there is limited work on pre-clinical imaging, notably in porcine models, which are often used due to their anatomical and physiological similarity to humans. However, differences between species create a domain shift that complicates direct model transfer from human to pig data. Recently, foundation models trained on large human datasets have shown promise for robust medical image segmentation; yet their applicability to porcine data remains largely unexplored. In this work, we investigate whether foundation models can generate sufficiently accurate pseudo-labels for pig cardiac CT and propose a simple self-training approach to iteratively refine these labels. Our method requires no manually annotated pig data, relying instead on iterative updates to improve segmentation quality. We demonstrate that this self-training process not only enhances segmentation accuracy but also smooths out temporal inconsistencies across consecutive frames. Although our results are encouraging, there remains room for improvement, for example by incorporating more sophisticated self-training strategies and by exploring additional foundation models and other cardiac imaging technologies.