The rapid advancement of Large Language Models (LLMs) has stimulated interest in multi-agent collaboration for addressing complex medical tasks. However, the practical advantages of multi-agent collaboration approaches remain insufficiently understood. Existing evaluations often lack generalizability, failing to cover diverse tasks reflective of real-world clinical practice, and frequently omit rigorous comparisons against both single-LLM-based and established conventional methods. To address this critical gap, we introduce MedAgentBoard, a comprehensive benchmark for the systematic evaluation of multi-agent collaboration, single-LLM, and conventional approaches. MedAgentBoard encompasses four diverse medical task categories: (1) medical (visual) question answering, (2) lay summary generation, (3) structured Electronic Health Record (EHR) predictive modeling, and (4) clinical workflow automation, across text, medical images, and structured EHR data. Our extensive experiments reveal a nuanced landscape: while multi-agent collaboration demonstrates benefits in specific scenarios, such as enhancing task completeness in clinical workflow automation, it does not consistently outperform advanced single LLMs (e.g., in textual medical QA) or, critically, specialized conventional methods that generally maintain better performance in tasks like medical VQA and EHR-based prediction. MedAgentBoard offers a vital resource and actionable insights, emphasizing the necessity of a task-specific, evidence-based approach to selecting and developing AI solutions in medicine. It underscores that the inherent complexity and overhead of multi-agent collaboration must be carefully weighed against tangible performance gains. All code, datasets, detailed prompts, and experimental results are open-sourced at https://medagentboard.netlify.app/.

Multimodal medical image fusion plays a crucial role in medical diagnosis by integrating complementary information from different modalities to enhance image readability and clinical applicability. However, existing methods mainly follow computer vision standards for feature extraction and fusion strategy formulation, overlooking the rich semantic information inherent in medical images. To address this limitation, we propose a novel semantic-guided medical image fusion approach that, for the first time, incorporates medical prior knowledge into the fusion process. Specifically, we construct a publicly available multimodal medical image-text dataset, upon which text descriptions generated by BiomedGPT are encoded and semantically aligned with image features in a high-dimensional space via a semantic interaction alignment module. During this process, a cross attention based linear transformation automatically maps the relationship between textual and visual features to facilitate comprehensive learning. The aligned features are then embedded into a text-injection module for further feature-level fusion. Unlike traditional methods, we further generate diagnostic reports from the fused images to assess the preservation of medical information. Additionally, we design a medical semantic loss function to enhance the retention of textual cues from the source images. Experimental results on test datasets demonstrate that the proposed method achieves superior performance in both qualitative and quantitative evaluations while preserving more critical medical information.

Low-dose CT (LDCT) images are often accompanied by significant noise, which negatively impacts image quality and subsequent diagnostic accuracy. To address the challenges of multi-scale feature fusion and diverse noise distribution patterns in LDCT denoising, this paper introduces an innovative model, CTLformer, which combines convolutional structures with transformer architecture. Two key innovations are proposed: a multi-scale attention mechanism and a dynamic attention control mechanism. The multi-scale attention mechanism, implemented through the Token2Token mechanism and self-attention interaction modules, effectively captures both fine details and global structures at different scales, enhancing relevant features and suppressing noise. The dynamic attention control mechanism adapts the attention distribution based on the noise characteristics of the input image, focusing on high-noise regions while preserving details in low-noise areas, thereby enhancing robustness and improving denoising performance. Furthermore, CTLformer integrates convolutional layers for efficient feature extraction and uses overlapping inference to mitigate boundary artifacts, further strengthening its denoising capability. Experimental results on the 2016 National Institutes of Health AAPM Mayo Clinic LDCT Challenge dataset demonstrate that CTLformer significantly outperforms existing methods in both denoising performance and model efficiency, greatly improving the quality of LDCT images. The proposed CTLformer not only provides an efficient solution for LDCT denoising but also shows broad potential in medical image analysis, especially for clinical applications dealing with complex noise patterns.

Combined Pulmonary Fibrosis and Emphysema (CPFE), formally recognized as a distinct pulmonary syndrome in 2022, is characterized by unique clinical features and pathogenesis that may lead to respiratory failure and death. However, the diagnosis of CPFE presents significant challenges that hinder effective treatment. Here, we assembled three-dimensional (3D) reconstruction data of the chest High-Resolution Computed Tomography (HRCT) of patients from multiple hospitals across different provinces in China, including Xiangya Hospital, West China Hospital, and Fujian Provincial Hospital. Using this dataset, we developed CPFENet, a deep learning-based diagnostic model for CPFE. It accurately differentiates CPFE from COPD, with performance comparable to that of professional radiologists. Additionally, we developed a CPFE score based on radiomic analysis of 3D CT images to quantify disease characteristics. Notably, female patients demonstrated significantly higher CPFE scores than males, suggesting potential sex-specific differences in CPFE. Overall, our study establishes the first diagnostic framework for CPFE, providing a diagnostic model and clinical indicators that enable accurate classification and characterization of the syndrome.

Large language models (LLMs) are increasingly used by physicians for diagnostic support. A key advantage of LLMs is the ability to generate explanations that can help physicians understand the reasoning behind a diagnosis. However, the best-suited format for LLM-generated explanations remains unclear. In this large-scale study, we examined the effect of different formats for LLM explanations on clinical decision-making. For this, we conducted a randomized experiment with radiologists reviewing patient cases with radiological images (N = 2020 assessments). Participants received either no LLM support (control group) or were supported by one of three LLM-generated explanations: (1) a standard output providing the diagnosis without explanation; (2) a differential diagnosis comparing multiple possible diagnoses; or (3) a chain-of-thought explanation offering a detailed reasoning process for the diagnosis. We find that the format of explanations significantly influences diagnostic accuracy. The chain-of-thought explanations yielded the best performance, improving the diagnostic accuracy by 12.2% compared to the control condition without LLM support (P = 0.001). The chain-of-thought explanations are also superior to the standard output without explanation (+7.2%; P = 0.040) and the differential diagnosis format (+9.7%; P = 0.004). We further assessed the robustness of these findings across case difficulty and different physician backgrounds such as general vs. specialized radiologists. Evidently, explaining the reasoning for a diagnosis helps physicians to identify and correct potential errors in LLM predictions and thus improve overall decisions. Altogether, the results highlight the importance of how explanations in medical LLMs are generated to maximize their utility in clinical practice. By designing explanations to support the reasoning processes of physicians, LLMs can improve diagnostic performance and, ultimately, patient outcomes.

Breast cancer remains a significant global health issue. Despite advances in detection and treatment, its complexity is driven by genetic, environmental, and structural factors. Computational methods like Finite Element Modeling (FEM) have transformed our understanding of breast cancer risk and progression. Advanced computational approaches in breast cancer research are the focus, with an emphasis on FEM's role in simulating breast tissue mechanics and enhancing precision in therapies such as radiofrequency ablation (RFA). Machine learning (ML), particularly Convolutional Neural Networks (CNNs), has revolutionized imaging modalities like mammograms and MRIs, improving diagnostic accuracy and early detection. AI applications in analyzing histopathological images have advanced tumor classification and grading, offering consistency and reducing inter-observer variability. Explainability tools like Grad-CAM, SHAP, and LIME enhance the transparency of AI-driven models, facilitating their integration into clinical workflows. Integrating FEM and ML represents a paradigm shift in breast cancer management. FEM offers precise modeling of tissue mechanics, while ML excels in predictive analytics and image analysis. Despite challenges such as data variability and limited standardization, synergizing these approaches promises adaptive, personalized care. These computational methods have the potential to redefine diagnostics, optimize treatment, and improve patient outcomes.

To evaluate diagnostic accuracy and image quality of deep learning (DL) cine sequences for LV and RV parameters compared to conventional balanced steady-state free precession (bSSFP) cine sequences in cardiovascular magnetic resonance (CMR). From January to April 2024, patients with clinically indicated CMR were prospectively included. LV and RV were segmented from short-axis bSSFP and DL cine sequences. LV and RV end-diastolic volume (EDV), end-systolic volume (EDV), stroke volume (SV), ejection fraction, and LV end-diastolic mass were calculated. The acquisition time of both sequences was registered. Results were compared with paired-samples t test or Wilcoxon signed-rank test. Agreement between DL cine and bSSFP was assessed using Bland-Altman plots. Image quality was graded by two readers based on blood-to-myocardium contrast, endocardial edge definition, and motion artifacts, using a 5-point Likert scale (1 = insufficient quality; 5 = excellent quality). Sixty-two patients were included (mean age: 47 ± 17 years, 41 men). No significant differences between DL cine and bSSFP were found for all LV and RV parameters (P ≥ .176). DL cine was significantly faster (1.35 ± .55 m vs 2.83 ± .79 m; P < .001). The agreement between DL cine and bSSFP was strong, with bias ranging from 45 to 1.75% for LV and from - 0.38 to 2.43% for RV. Among LV parameters, the highest agreement was obtained for ESV and SV, which fell within the acceptable limit of agreement (LOA) in 84% of cases. EDV obtained the highest agreement among RV parameters, falling within the acceptable LOA in 90% of cases. Overall image quality was comparable (median: 5, IQR: 4-5; P = .330), while endocardial edge definition of DL cine (median: 4, IQR: 4-5) was lower than bSSFP (median: 5, IQR: 4-5; P = .002). DL cine allows fast and accurate quantification of LV and RV parameters and comparable image quality with conventional bSSFP.

This study aimed to develop deep learning algorithms (DLAs) utilising convolutional neural networks (CNNs) to classify cervical spondylotic myelopathy (CSM) and cervical spondylotic radiculopathy (CSR) from plain cervical spine radiographs. Data from 300 patients (150 with CSM and 150 with CSR) were used for internal validation (IV) using five-fold cross-validation strategy. Additionally, 100 patients (50 with CSM and 50 with CSR) were included in the external validation (EV). Two DLAs were trained using CNNs on plain radiographs from C3-C6 for the binary classification of CSM and CSR, and for the prediction of the spinal canal area rate using magnetic resonance imaging. Model performance was evaluated on external data using metrics such as area under the curve (AUC), accuracy, and likelihood ratios. For the binary classification, the AUC ranged from 0.84 to 0.96, with accuracy between 78% and 95% during IV. In the EV, the AUC and accuracy were 0.96 and 90%, respectively. For the spinal canal area rate, correlation coefficients during five-fold cross-validation ranged from 0.57 to 0.64, with a mean correlation of 0.61 observed in the EV. DLAs developed with CNNs demonstrated promising accuracy for classifying CSM and CSR from plain radiographs. These algorithms have the potential to assist non-specialists in identifying patients who require further evaluation or referral to spine specialists, thereby reducing delays in the diagnosis and treatment of CSM.

Artifacts in clinical MRI can compromise the performance of AI models. This study evaluates how different data augmentation strategies affect an AI model's segmentation performance under variable artifact severity. We used an AI model based on the nnU-Net architecture to automatically quantify lower limb alignment using axial T2-weighted MR images. Three versions of the AI model were trained with different augmentation strategies: (1) no augmentation ("baseline"), (2) standard nnU-net augmentations ("default"), and (3) "default" plus augmentations that emulate MR artifacts ("MRI-specific"). Model performance was tested on 600 MR image stacks (right and left; hip, knee, and ankle) from 20 healthy participants (mean age, 23 ± 3 years, 17 men), each imaged five times under standardized motion to induce artifacts. Two radiologists graded each stack's artifact severity as none, mild, moderate, and severe, and manually measured torsional angles. Segmentation quality was assessed using the Dice similarity coefficient (DSC), while torsional angles were compared between manual and automatic measurements using mean absolute deviation (MAD), intraclass correlation coefficient (ICC), and Pearson's correlation coefficient (r). Statistical analysis included parametric tests and a Linear Mixed-Effects Model. MRI-specific augmentation resulted in slightly (yet not significantly) better performance than the default strategy. Segmentation quality decreased with increasing artifact severity, which was partially mitigated by default and MRI-specific augmentations (e.g., severe artifacts, proximal femur: DSC_baseline = 0.58 ± 0.22; DSC_default = 0.72 ± 0.22; DSC_MRI-specific = 0.79 ± 0.14 [p < 0.001]). These augmentations also maintained precise torsional angle measurements (e.g., severe artifacts, femoral torsion: MAD_baseline = 20.6 ± 23.5°; MAD_default = 7.0 ± 13.0°; MAD_MRI-specific = 5.7 ± 9.5° [p < 0.001]; ICC_baseline = -0.10 [p = 0.63; 95% CI: -0.61 to 0.47]; ICC_default = 0.38 [p = 0.08; -0.17 to 0.76]; ICC_MRI-specific = 0.86 [p < 0.001; 0.62 to 0.95]; r_baseline = 0.58 [p < 0.001; 0.44 to 0.69]; r_default = 0.68 [p < 0.001; 0.56 to 0.77]; r_MRI-specific = 0.86 [p < 0.001; 0.81 to 0.9]). Motion artifacts negatively impact AI models, but general-purpose augmentations enhance robustness effectively. MRI-specific augmentations offer minimal additional benefit. Question Motion artifacts negatively impact the performance of diagnostic AI models for MRI, but mitigation methods remain largely unexplored. Findings Domain-specific augmentation during training can improve the robustness and performance of a model for quantifying lower limb alignment in the presence of severe artifacts. Clinical relevance Excellent robustness and accuracy are crucial for deploying diagnostic AI models in clinical practice. Including domain knowledge in model training can benefit clinical adoption.

Voice disorders (VD) are often linked to vocal fold structural pathologies (VFSP). Laryngeal imaging plays a vital role in assessing VFSPs and VD in clinical and research settings, but challenges like scarce and imbalanced datasets can limit the generalizability of findings. Denoising Diffusion Probabilistic Models (DDPMs), a subtype of Generative AI, has gained attention for its ability to generate high-quality and realistic synthetic images to address these challenges. This study explores the feasibility of improving VFSP image classification by generating synthetic images using DDPMs. 404 laryngoscopic images depicting VF without and with VFSP were included. DDPMs were used to generate synthetic images to augment the original dataset. Two convolutional neural network architectures, VGG16 and ResNet50, were applied for model training. The models were initially trained only on the original dataset. Then, they were trained on the augmented datasets. Evaluation metrics were analyzed to assess the performance of the models for both binary classification (with/without VFSPs) and multi-class classification (seven specific VFSPs). Realistic and high-quality synthetic images were generated for dataset augmentation. The model first failed to converge when trained only on the original dataset, but they successfully converged and achieved low loss and high accuracy when trained on the augmented datasets. The best performance was gained for both binary and multi-class classification when the models were trained on an augmented dataset. Generating realistic images of VFSP using DDPMs is feasible and can enhance the classification of VFSPs by an AI model and may support VD screening and diagnosis.