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.

Bone fracture risk assessment for osteoporotic patients is essential for implementing early countermeasures and preventing discomfort and hospitalization. Current methodologies, such as Fracture Risk Assessment Tool (FRAX), provide a risk assessment over a 5- to 10-year period rather than evaluating the bone's current health status. The database was collected by Ajou University Medical Center from 2017 to 2021. It included 9,260 patients, aged 55 to 99, comprising 242 femur fracture (FX) cases and 9,018 non-fracture (NFX) cases. To model the association of the bone's current health status with prevalent FXs, three prediction algorithms-extreme gradient boosting (XGB), support vector machine, and multilayer perceptron-were trained using two-dimensional dual-energy X-ray absorptiometry (2D-DXA) analysis results and subsequently benchmarked. The XGB classifier, which proved most effective, was then further refined using synthetic data generated by the adaptive synthetic oversampler to balance the FX and NFX classes and enhance boundary sharpness for better classification accuracy. The XGB model trained on raw data demonstrated good prediction capabilities, with an area under the curve (AUC) of 0.78 and an F1 score of 0.71 on test cases. The inclusion of synthetic data improved classification accuracy in terms of both specificity and sensitivity, resulting in an AUC of 0.99 and an F1 score of 0.98. The proposed methodology demonstrates that current bone health can be assessed through post-processed results from 2D-DXA analysis. Moreover, it was also shown that synthetic data can help stabilize uneven databases by balancing majority and minority classes, thereby significantly improving classification performance.

To evaluate the performance of large language models (LLMs) in automatically generating whole-organ MRI score (WORMS)-based structured MRI reports and predicting osteoarthritis (OA) severity for the knee. A total of 160 consecutive patients suspected of OA were included. Knee MRI reports were reviewed by three radiologists to establish the WORMS reference standard for 39 key features. GPT-4o and GPT-4o-mini were prompted using in-context knowledge (ICK) and chain-of-thought (COT) to generate WORMS-based structured reports from original reports and to automatically predict the OA severity. Four Orthopedic surgeons reviewed original and LLM-generated reports to conduct pairwise preference and difficulty tests, and their review times were recorded. GPT-4o demonstrated perfect performance in extracting the laterality of the knee (accuracy = 100%). GPT-4o outperformed GPT-4o mini in generating WORMS reports (Accuracy: 93.9% vs 76.2%, respectively). GPT-4o achieved higher recall (87.3% s 46.7%, p < 0.001), while maintaining higher precision compared to GPT-4o mini (94.2% vs 71.2%, p < 0.001). For predicting OA severity, GPT-4o outperformed GPT-4o mini across all prompt strategies (best accuracy: 98.1% vs 68.7%). Surgeons found it easier to extract information and gave more preference to LLM-generated reports over the original reports (both p < 0.001) while spending less time on each report (51.27 ± 9.41 vs 87.42 ± 20.26 s, p < 0.001). GPT-4o generated expert multi-feature, WORMS-based reports from original free-text knee MRI reports. GPT-4o with COT achieved high accuracy in categorizing OA severity. Surgeons reported greater preference and higher efficiency when using LLM-generated reports. The perfect performance of generating WORMS-based reports and the high efficiency and ease of use suggest that integrating LLMs into clinical workflows could greatly enhance productivity and alleviate the documentation burden faced by clinicians in knee OA. GPT-4o successfully generated WORMS-based knee MRI reports. GPT-4o with COT prompting achieved impressive accuracy in categorizing knee OA severity. Greater preference and higher efficiency were reported for LLM-generated reports.

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.

To investigate the clinical efficiency of an AI-based metal artefact correction algorithm (AI-MAC), for reducing dental metal artefacts in head and neck CT, compared to conventional interpolation-based MAC. We retrospectively collected 41 patients with non-removal dental hardware who underwent non-contrast head and neck CT prior to radiotherapy. All images were reconstructed with standard reconstruction algorithm (SRA), and were additionally processed with both conventional MAC and AI-MAC. The image quality of SRA, MAC and AI-MAC were compared by qualitative scoring on a 5-point scale, with scores ≥ 3 considered interpretable. This was followed by a quantitative evaluation, including signal-to-noise ratio (SNR) and artefact index (Idxartefact). Organ contouring accuracy was quantified via calculating the dice similarity coefficient (DSC) and hausdorff distance (HD) for oral cavity and teeth, using the clinically accepted contouring as reference. Moreover, the treatment planning dose distribution for oral cavity was assessed. AI-MAC yielded superior qualitative image quality as well as quantitative metrics, including SNR and Idxartefact, to SRA and MAC. The image interpretability significantly improved from 41.46% for SRA and 56.10% for MAC to 92.68% for AI-MAC (p < 0.05). Compared to SRA and MAC, the best DSC and HD for both oral cavity and teeth were obtained on AI-MAC (all p < 0.05). No significant differences for dose distribution were found among the three image sets. AI-MAC outperforms conventional MAC in metal artefact reduction, achieving superior image quality with high image interpretability for patients with dental hardware undergoing head and neck CT. Furthermore, the use of AI-MAC improves the accuracy of organ contouring while providing consistent dose calculation against metal artefacts in radiotherapy. AI-MAC is a novel deep learning-based technique for reducing metal artefacts on CT. This in-vivo study first demonstrated its capability of reducing metal artefacts while preserving organ visualization, as compared with conventional MAC.

Inhalation injuries face a challenge in clinical diagnosis and grading due to the limitations of traditional methods, such as Abbreviated Injury Score (AIS), which rely on subjective assessments and show weak correlations with clinical outcomes. This study introduces a novel deep learning-based framework for grading inhalation injuries using bronchoscopy images with the duration of mechanical ventilation as an objective metric. To address the scarcity of medical imaging data, we propose enhanced StarGAN, a generative model that integrates Patch Loss and SSIM Loss to improve synthetic images' quality and clinical relevance. The augmented dataset generated by enhanced StarGAN significantly improved classification performance when evaluated using the Swin Transformer, achieving an accuracy of 77.78%, an 11.11% improvement over the original dataset. Image quality was assessed using the Fr\'echet Inception Distance (FID), where Enhanced StarGAN achieved the lowest FID of 30.06, outperforming baseline models. Burn surgeons confirmed the realism and clinical relevance of the generated images, particularly the preservation of bronchial structures and color distribution. These results highlight the potential of enhanced StarGAN in addressing data limitations and improving classification accuracy for inhalation injury grading.

Inhalation injuries present a challenge in clinical diagnosis and grading due to Conventional grading methods such as the Abbreviated Injury Score (AIS) being subjective and lacking robust correlation with clinical parameters like mechanical ventilation duration and patient mortality. This study introduces a novel deep learning-based diagnosis assistant tool for grading inhalation injuries using bronchoscopy images to overcome subjective variability and enhance consistency in severity assessment. Our approach leverages data augmentation techniques, including graphic transformations, Contrastive Unpaired Translation (CUT), and CycleGAN, to address the scarcity of medical imaging data. We evaluate the classification performance of two deep learning models, GoogLeNet and Vision Transformer (ViT), across a dataset significantly expanded through these augmentation methods. The results demonstrate GoogLeNet combined with CUT as the most effective configuration for grading inhalation injuries through bronchoscopy images and achieves a classification accuracy of 97.8%. The histograms and frequency analysis evaluations reveal variations caused by the augmentation CUT with distribution changes in the histogram and texture details of the frequency spectrum. PCA visualizations underscore the CUT substantially enhances class separability in the feature space. Moreover, Grad-CAM analyses provide insight into the decision-making process; mean intensity for CUT heatmaps is 119.6, which significantly exceeds 98.8 of the original datasets. Our proposed tool leverages mechanical ventilation periods as a novel grading standard, providing comprehensive diagnostic support.

Automatic radiology report generation can alleviate the workload for physicians and minimize regional disparities in medical resources, therefore becoming an important topic in the medical image analysis field. It is a challenging task, as the computational model needs to mimic physicians to obtain information from multi-modal input data (i.e., medical images, clinical information, medical knowledge, etc.), and produce comprehensive and accurate reports. Recently, numerous works have emerged to address this issue using deep-learning-based methods, such as transformers, contrastive learning, and knowledge-base construction. This survey summarizes the key techniques developed in the most recent works and proposes a general workflow for deep-learning-based report generation with five main components, including multi-modality data acquisition, data preparation, feature learning, feature fusion and interaction, and report generation. The state-of-the-art methods for each of these components are highlighted. Additionally, we summarize the latest developments in large model-based methods and model explainability, along with public datasets, evaluation methods, current challenges, and future directions in this field. We have also conducted a quantitative comparison between different methods in the same experimental setting. This is the most up-to-date survey that focuses on multi-modality inputs and data fusion for radiology report generation. The aim is to provide comprehensive and rich information for researchers interested in automatic clinical report generation and medical image analysis, especially when using multimodal inputs, and to assist them in developing new algorithms to advance the field.

Artificial intelligence applications in oncology imaging often struggle with diagnosing rare tumors. We identify significant gaps in detecting uncommon thyroid cancer types with ultrasound, where scarce data leads to frequent misdiagnosis. Traditional augmentation strategies do not capture the unique disease variations, hindering model training and performance. To overcome this, we propose a text-driven generative method that fuses clinical insights with image generation, producing synthetic samples that realistically reflect rare subtypes. In rigorous evaluations, our approach achieves substantial gains in diagnostic metrics, surpasses existing methods in authenticity and diversity measures, and generalizes effectively to other private and public datasets with various rare cancers. In this work, we demonstrate that text-guided image augmentation substantially enhances model accuracy and robustness for rare tumor detection, offering a promising avenue for more reliable and widespread clinical adoption.

Artificial Intelligence (AI) has transformed society and chatbots using Large Language Models (LLM) are playing an increasing role in scientific research. This study aims to assess and compare the efficacy of newer DeepSeek R1 and ChatGPT-4 and 4o models in answering scientific questions about recent research. We compared output generated from ChatGPT-4, ChatGPT-4o, and DeepSeek-R1 in response to ten standardized questions in the setting of musculoskeletal (MSK) radiology. These were independently analyzed by one MSK radiologist and one final-year MSK radiology trainee and graded using a Likert scale from 1 to 5 (1 being inaccurate to 5 being accurate). Five DeepSeek answers were significantly inaccurate and provided fictitious references only on prompting. All ChatGPT-4 and 4o answers were well-written with good content, the latter including useful and comprehensive references. ChatGPT-4o generates structured research answers to questions on recent MSK radiology research with useful references in all our cases, enabling reliable usage. DeepSeek-R1 generates articles that, on the other hand, may appear authentic to the unsuspecting eye but contain a higher amount of falsified and inaccurate information in the current version. Further iterations may improve these accuracies.