Medical radiology reports play a crucial role in diagnosing various diseases, yet generating them manually is time-consuming and burdens clinical workflows. Medical radiology report generation aims to automate this process using deep learning to assist radiologists and reduce patient wait times. This study presents the most comprehensive systematic review to date on deep learning-based MRRG, encompassing recent advances that span traditional architectures to large language models. We focus on available datasets, modeling approaches, and evaluation practices. Following PRISMA guidelines, we retrieved 323 articles from major academic databases and included 78 studies after eligibility screening. We critically analyze key components such as model architectures, loss functions, datasets, evaluation metrics, and optimizers - identifying 22 widely used datasets, 14 evaluation metrics, around 20 loss functions, over 25 visual backbones, and more than 30 textual backbones. To support reproducibility and accelerate future research, we also compile links to modern models, toolkits, and pretrained resources. Our findings provide technical insights and outline future directions to address current limitations, promoting collaboration at the intersection of medical imaging, natural language processing, and deep learning to advance trustworthy AI systems in radiology.

This study aimed to systematically map the development methods, scope, and limitations of existing artificial intelligence (AI) reporting guidelines in medicine and to explore their applicability to generative AI (GAI) tools, such as large language models (LLMs). We reported a scoping review adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR). Five information sources were searched, including MEDLINE (via PubMed), EQUATOR Network, CNKI, FAIRsharing, and Google Scholar, from inception to December 31, 2024. Two reviewers independently screened records and extracted data using a predefined Excel template. Data included guideline characteristics (e.g., development methods, target audience, AI domain), adherence to EQUATOR Network recommendations, and consensus methodologies. Discrepancies were resolved by a third reviewer. 68 AI reporting guidelines were included. 48.5% focused on general AI, while only 7.4% addressed GAI/LLMs. Methodological rigor was limited: 39.7% described development processes, 42.6% involved multidisciplinary experts, and 33.8% followed EQUATOR recommendations. Significant overlap existed, particularly in medical imaging (20.6% of guidelines). GAI-specific guidelines (14.7%) lacked comprehensive coverage and methodological transparency. Existing AI reporting guidelines in medicine have suboptimal methodological rigor, redundancy, and insufficient coverage of GAI applications. Future and updated guidelines should prioritize standardized development processes, multidisciplinary collaboration, and expanded focus on emerging AI technologies like LLMs.

The prevalence of Alzheimer's disease and other dementias is increasing as populations live longer lifespans. Imaging is becoming a key component of the workup for patients with cognitive impairment or dementia. Integrated PET-MRI provides a unique opportunity for same-session multimodal characterization with many practical benefits to patients, referring physicians, radiologists, and researchers. The impact of integrated PET-MRI on clinical practice for early adopters of this technology can be profound. Classic imaging findings with integrated PET-MRI are illustrated for common neurodegenerative diseases or clinical-radiological syndromes. This review summarizes recent technical innovations that are being introduced into PET-MRI clinical practice and research for neurodegenerative disease. More recent MRI-based attenuation correction now performs similarly compared to PET-CT (e.g., whole-brain bias < 0.5%) such that early concerns for accurate PET tracer quantification with integrated PET-MRI appear resolved. Head motion is common in this patient population. MRI- and PET data-driven motion correction appear ready for routine use and should substantially improve PET-MRI image quality. PET-MRI by definition eliminates ~50% of the radiation from CT. Multiple hardware and software techniques for improving image quality with lower counts are reviewed (including motion correction). These methods can lower radiation to patients (and staff), increase scanner throughput, and generate better temporal resolution for dynamic PET. Deep learning has been broadly applied to PET-MRI. Deep learning analysis of PET and MRI data may provide accurate classification of different stages of Alzheimer's disease or predict progression to dementia. Over the past 5 years, clinical imaging of neurodegenerative disease has changed due to imaging research and the introduction of anti-amyloid immunotherapy-integrated PET-MRI is best suited for imaging these patients and its use appears poised for rapid growth outside academic medical centers. Evidence level: 5. Technical efficacy: Stage 3.

The growing volume of medical imaging data has increased the need for automated diagnostic tools, especially for musculoskeletal injuries like rib fractures, commonly detected via CT scans. Manual interpretation is time-consuming and error-prone. We propose OrthoInsight, a multi-modal deep learning framework for rib fracture diagnosis and report generation. It integrates a YOLOv9 model for fracture detection, a medical knowledge graph for retrieving clinical context, and a fine-tuned LLaVA language model for generating diagnostic reports. OrthoInsight combines visual features from CT images with expert textual data to deliver clinically useful outputs. Evaluated on 28,675 annotated CT images and expert reports, it achieves high performance across Diagnostic Accuracy, Content Completeness, Logical Coherence, and Clinical Guidance Value, with an average score of 4.28, outperforming models like GPT-4 and Claude-3. This study demonstrates the potential of multi-modal learning in transforming medical image analysis and providing effective support for radiologists.

Mild Cognitive Impairment (MCI) serves as a prodromal stage of Alzheimer's Disease (AD), where early identification and intervention can effectively slow the progression to dementia. However, diagnosing AD remains a significant challenge in neurology due to the confounders caused mainly by the selection bias of multimodal data and the complex relationships between variables. To address these issues, we propose a novel visual-language causal intervention framework named Alzheimer's Disease Prediction with Cross-modal Causal Intervention (ADPC) for diagnostic assistance. Our ADPC employs large language model (LLM) to summarize clinical data under strict templates, maintaining structured text outputs even with incomplete or unevenly distributed datasets. The ADPC model utilizes Magnetic Resonance Imaging (MRI), functional MRI (fMRI) images and textual data generated by LLM to classify participants into Cognitively Normal (CN), MCI, and AD categories. Because of the presence of confounders, such as neuroimaging artifacts and age-related biomarkers, non-causal models are likely to capture spurious input-output correlations, generating less reliable results. Our framework implicitly eliminates confounders through causal intervention. Experimental results demonstrate the outstanding performance of our method in distinguishing CN/MCI/AD cases, achieving state-of-the-art (SOTA) metrics across most evaluation metrics. The study showcases the potential of integrating causal reasoning with multi-modal learning for neurological disease diagnosis.

Accurate 3D aortic construction is crucial for clinical diagnosis, preoperative planning, and computational fluid dynamics (CFD) simulations, as it enables the estimation of critical hemodynamic parameters such as blood flow velocity, pressure distribution, and wall shear stress. Existing construction methods often rely on large annotated training datasets and extensive manual intervention. While the resulting meshes can serve for visualization purposes, they struggle to produce geometrically consistent, well-constructed surfaces suitable for downstream CFD analysis. To address these challenges, we introduce AortaDiff, a diffusion-based framework that generates smooth aortic surfaces directly from CT/MRI volumes. AortaDiff first employs a volume-guided conditional diffusion model (CDM) to iteratively generate aortic centerlines conditioned on volumetric medical images. Each centerline point is then automatically used as a prompt to extract the corresponding vessel contour, ensuring accurate boundary delineation. Finally, the extracted contours are fitted into a smooth 3D surface, yielding a continuous, CFD-compatible mesh representation. AortaDiff offers distinct advantages over existing methods, including an end-to-end workflow, minimal dependency on large labeled datasets, and the ability to generate CFD-compatible aorta meshes with high geometric fidelity. Experimental results demonstrate that AortaDiff performs effectively even with limited training data, successfully constructing both normal and pathologically altered aorta meshes, including cases with aneurysms or coarctation. This capability enables the generation of high-quality visualizations and positions AortaDiff as a practical solution for cardiovascular research.

Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic interpretability, particularly through the use of sparse autoencoders (SAEs), offers a promising approach for uncovering human-interpretable features within large transformer-based models. In this study, we apply Matryoshka-SAE to the radiology-specialised multimodal large language model, MAIRA-2, to interpret its internal representations. Using large-scale automated interpretability of the SAE features, we identify a range of clinically relevant concepts - including medical devices (e.g., line and tube placements, pacemaker presence), pathologies such as pleural effusion and cardiomegaly, longitudinal changes and textual features. We further examine the influence of these features on model behaviour through steering, demonstrating directional control over generations with mixed success. Our results reveal practical and methodological challenges, yet they offer initial insights into the internal concepts learned by MAIRA-2 - marking a step toward deeper mechanistic understanding and interpretability of a radiology-adapted multimodal large language model, and paving the way for improved model transparency. We release the trained SAEs and interpretations: https://huggingface.co/microsoft/maira-2-sae.

Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute in magnetic resonance imaging (MRI), where image appearance varies widely across pulse sequences and scanner hardware. A recent domain-randomization strategy addresses the generalization problem by training deep neural networks on synthetic images with randomized intensities and anatomical content. By generating diverse data from anatomical segmentation maps, the approach enables models to accurately process image types unseen during training, without retraining or fine-tuning. It has demonstrated effectiveness across modalities including MRI, computed tomography, positron emission tomography, and optical coherence tomography, as well as beyond neuroimaging in ultrasound, electron and fluorescence microscopy, and X-ray microtomography. This tutorial paper reviews the principles, implementation, and potential of the synthesis-driven training paradigm. It highlights key benefits, such as improved generalization and resistance to overfitting, while discussing trade-offs such as increased computational demands. Finally, the article explores practical considerations for adopting the technique, aiming to accelerate the development of generalizable tools that make deep learning more accessible to domain experts without extensive computational resources or machine learning knowledge.

Accurate diagnosis of pancreatic cystic lesions (PCLs) is essential to guide appropriate management and reduce unnecessary surgeries. Despite multiple guidelines in PCL management, a substantial proportion of patients still undergo major resections for benign cysts, and a majority of resected intraductal papillary mucinous neoplasms (IPMNs) show only low-grade dysplasia, leading to significant clinical, financial, and psychological burdens. This review highlights emerging endoscopic approaches that enhance diagnostic accuracy and support organ-sparing, minimally invasive management of PCLs. Recent studies suggest that endoscopic ultrasound (EUS) and its accessory techniques, such as contrast-enhanced EUS and needle-based confocal laser endomicroscopy, as well as next-generation sequencing analysis of cyst fluid, not only accurately characterize PCLs but are also well tolerated and cost-effective. Additionally, emerging therapeutics such as EUS-guided radiofrequency ablation (RFA) and EUS-chemoablation are promising as minimally invasive treatments for high-risk mucinous PCLs in patients who are not candidates for surgery. Accurate diagnosis of PCLs remains challenging, leading to many patients undergoing unnecessary surgery. Emerging endoscopic imaging biomarkers, artificial intelligence analysis, and molecular biomarkers enhance diagnostic precision. Additionally, novel endoscopic ablative therapies offer safe, minimally invasive, organ-sparing treatment options, thereby reducing the healthcare resource burdens associated with overtreatment.

BackgroundArtificial Intelligence (AI) has evolved through various trends, with different subfields gaining prominence over time. Currently, Conversational Artificial Intelligence (CAI)--particularly Generative AI--is at the forefront. CAI models are primarily focused on text-based tasks and are commonly deployed as chatbots. Recent advancements by OpenAI have enabled the integration of external, independently developed models, allowing chatbots to perform specialized, task-oriented functions beyond general language processing. ObjectiveThis study aims to develop a smart chatbot that integrates large language models (LLMs) from OpenAI with specialized domain-specific models, such as those used in medical image diagnostics. The system leverages transfer learning via Googles Teachable Machine to construct image-based classifiers and incorporates a diabetes detection model developed in TensorFlow.js. A key innovation is the chatbots ability to extract relevant parameters from user input, trigger the appropriate diagnostic model, interpret the output, and deliver responses in natural language. The overarching goal is to demonstrate the potential of combining LLMs with external models to build multimodal, task-oriented conversational agents. MethodsTwo image-based models were developed and integrated into the chatbot system. The first analyzes chest X-rays to detect viral and bacterial pneumonia. The second uses optical coherence tomography (OCT) images to identify ocular conditions such as drusen, choroidal neovascularization (CNV), and diabetic macular edema (DME). Both models were incorporated into the chatbot to enable image-based medical query handling. In addition, a text-based model was constructed to process physiological measurements for diabetes prediction using TensorFlow.js. The architecture is modular: new diagnostic models can be added without redesigning the chatbot, enabling straightforward functional expansion. ResultsThe findings demonstrate effective integration between the chatbot and the diagnostic models, with only minor deviations from expected behavior. Additionally, a stub function was implemented within the chatbot to schedule medical appointments based on the severity of a patients condition, and it was specifically tested with the OCT and X-ray models. ConclusionsThis study demonstrates the feasibility of developing advanced AI systems--including image-based diagnostic models and chatbot integration--by leveraging Artificial Intelligence as a Service (AIaaS). It also underscores the potential of AI to enhance user experiences in bioinformatics, paving the way for more intuitive and accessible interfaces in the field. Looking ahead, the modular nature of the chatbot allows for the integration of additional diagnostic models as the system evolves.