Neuropsychiatric disorders have complex pathological mechanism, pronounced clinical heterogeneity, and a prolonged preclinical phase, which presents a challenge for early diagnosis and development of precise intervention strategies. With the development of large-scale multimodal neuroimaging datasets and advancement of artificial intelligence (AI) algorithms, the integration of multimodal imaging with AI techniques has emerged as a pivotal avenue for early detection and tailoring individualized treatment for neuropsychiatric disorders. To support these advances, in this review, we outline multimodal neuroimaging techniques, AI methods, and strategies for multimodal data fusion. We highlight applications of multimodal AI based on neuroimaging data in precision medicine for neuropsychiatric disorders, discussing challenges in clinical adoption, their emerging solutions, and future directions.

Automatic pancreas segmentation in CT scans is crucial for various medical applications, including early diagnosis and computer-assisted surgery. However, existing segmentation methods remain suboptimal due to significant pancreas size variations across slices and severe class imbalance caused by the pancreas's small size and CT scanner movement during imaging. Traditional computer vision techniques struggle with these challenges, while deep learning-based approaches, despite their success in other domains, still face limitations in pancreas segmentation. To address these issues, we propose a novel, three-stage workflow that enhances segmentation accuracy and computational efficiency. First, we introduce External Contour Cropping (ECC), a background cleansing technique that mitigates class imbalance. Second, we propose a Size Ratio (SR) technique that restructures the training dataset based on the relative size of the target organ, improving the robustness of the model against anatomical variations. Third, we develop MOMUNet, an ultra-lightweight segmentation model with only 1.31 million parameters, designed for optimal performance on limited computational resources. Our proposed workflow achieves an improvement in Dice Score (DSC) of 2.56% over state-of-the-art (SOTA) models in the NIH-Pancreas dataset and 2.97% in the MSD-Pancreas dataset. Furthermore, applying the proposed model to another small organ, such as colon cancer segmentation in the MSD-Colon dataset, yielded a DSC of 68.4%, surpassing the SOTA models. These results demonstrate the effectiveness of our approach in significantly improving segmentation accuracy for small abdomen organs including pancreas and colon, making deep learning more accessible for low-resource medical facilities.

The progress of artificial intelligence (AI) research in dental medicine is hindered by data acquisition challenges and imbalanced distributions. These problems are especially apparent when planning to develop AI-based diagnostic or analytic tools for various lesions, such as maxillary sinus lesions (MSL) including mucosal thickening and polypoid lesions. Traditional unsupervised generative models struggle to simultaneously control the image realism, diversity, and lesion-type specificity. This study establishes an expert-guided framework to overcome these limitations to elevate AI-based diagnostic accuracy. A StyleGAN2 framework was developed for generating clinically relevant MSL images (such as mucosal thickening and polypoid lesion) under expert control. The generated images were then integrated into training datasets to evaluate their effect on ResNet50's diagnostic performance. Here we show: 1) Both lesion subtypes achieve satisfactory fidelity metrics, with structural similarity indices (SSIM > 0.996) and maximum mean discrepancy values (MMD < 0.032), and clinical validation scores close to those of real images; 2) Integrating baseline datasets with synthetic images significantly enhances diagnostic accuracy for both internal and external test sets, particularly improving area under the precision-recall curve (AUPRC) by approximately 8% and 14% for mucosal thickening and polypoid lesions in the internal test set, respectively. The StyleGAN2-based image generation tool effectively addressed data scarcity and imbalance through high-quality MSL image synthesis, consequently boosting diagnostic model performance. This work not only facilitates AI-assisted preoperative assessment for maxillary sinus lift procedures but also establishes a methodological framework for overcoming data limitations in medical image analysis.

Platinum resistance of high-grade serous ovarian cancer (HGSOC) cannot currently be recognized by specific molecular biomarkers. We aimed to compare the predictive capacity of various models integrating MRI habitat, whole slide images (WSIs), and clinical parameters to predict platinum sensitivity in HGSOC patients. A retrospective study involving 998 eligible patients from four hospitals was conducted. MRI habitats were clustered using K-means algorithm on multi-parametric MRI. Following feature extraction and selection, a Habitat model was developed. Vision Transformer (ViT) and multi-instance learning were trained to derive the patch-level prediction and WSI-level prediction on hematoxylin and eosin (H&E)-stained WSIs, respectively, forming a Pathology model. Logistic regression (LR) was used to create a Clinic model. A multi-modal model integrating Clinic, Habitat, and Pathology (CHP) was constructed using Multi-Head Attention (MHA) and compared with the unimodal models and Ensemble multi-modal models. The area under the curve (AUC) and integrated discrimination improvement (IDI) value were used to assess model performance and gains. In the internal validation cohort and the external test cohort, the Habitat model showed the highest AUCs (0.722 and 0.685) compared to the Clinic model (0.683 and 0.681) and the Pathology model (0.533 and 0.565), respectively. The AUCs (0.789 and 0.807) of the multi-modal model interating CHP based on MHA were highest than those of any unimodal models and Ensemble multi-modal models, with positive IDI values. MRI-based habitat imaging showed potentials to predict platinum sensitivity in HGSOC patients. Multi-modal integration of CHP based on MHA was helpful to improve prediction performance.

Brain-to-image decoding has been recently propelled by the progress in generative AI models and the availability of large ultra-high field functional Magnetic Resonance Imaging (fMRI). However, current approaches depend on complicated multi-stage pipelines and preprocessing steps that typically collapse the temporal dimension of brain recordings, thereby limiting time-resolved brain decoders. Here, we introduce Dynadiff (Dynamic Neural Activity Diffusion for Image Reconstruction), a new single-stage diffusion model designed for reconstructing images from dynamically evolving fMRI recordings. Our approach offers three main contributions. First, Dynadiff simplifies training as compared to existing approaches. Second, our model outperforms state-of-the-art models on time-resolved fMRI signals, especially on high-level semantic image reconstruction metrics, while remaining competitive on preprocessed fMRI data that collapse time. Third, this approach allows a precise characterization of the evolution of image representations in brain activity. Overall, this work lays the foundation for time-resolved brain-to-image decoding.

Semi-supervised learning (SSL) has achieved significant progress in medical image segmentation (SSMIS) through effective utilization of limited labeled data. While current SSL methods for medical images predominantly rely on consistency regularization and pseudo-labeling, they often overlook transferable semantic relationships across different clinical domains and imaging modalities. To address this, we propose TransMedSeg, a novel transferable semantic framework for semi-supervised medical image segmentation. Our approach introduces a Transferable Semantic Augmentation (TSA) module, which implicitly enhances feature representations by aligning domain-invariant semantics through cross-domain distribution matching and intra-domain structural preservation. Specifically, TransMedSeg constructs a unified feature space where teacher network features are adaptively augmented towards student network semantics via a lightweight memory module, enabling implicit semantic transformation without explicit data generation. Interestingly, this augmentation is implicitly realized through an expected transferable cross-entropy loss computed over the augmented teacher distribution. An upper bound of the expected loss is theoretically derived and minimized during training, incurring negligible computational overhead. Extensive experiments on medical image datasets demonstrate that TransMedSeg outperforms existing semi-supervised methods, establishing a new direction for transferable representation learning in medical image analysis.

Medical image captioning is a challenging task that requires generating clinically accurate and semantically meaningful descriptions of radiology images. While recent vision-language models (VLMs) such as BLIP, BLIP2, Gemini and ViT-GPT2 show strong performance on natural image datasets, they often produce generic or imprecise captions when applied to specialized medical domains. In this project, we explore the effectiveness of fine-tuning the BLIP model on the ROCO dataset for improved radiology captioning. We compare the fine-tuned BLIP against its zero-shot version, BLIP-2 base, BLIP-2 Instruct and a ViT-GPT2 transformer baseline. Our results demonstrate that domain-specific fine-tuning on BLIP significantly improves performance across both quantitative and qualitative evaluation metrics. We also visualize decoder cross-attention maps to assess interpretability and conduct an ablation study to evaluate the contributions of encoder-only and decoder-only fine-tuning. Our findings highlight the importance of targeted adaptation for medical applications and suggest that decoder-only fine-tuning (encoder-frozen) offers a strong performance baseline with 5% lower training time than full fine-tuning, while full model fine-tuning still yields the best results overall.

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, including radiology report generation. Previous approaches have attempted to utilize multimodal LLMs for this task, enhancing their performance through the integration of domain-specific knowledge retrieval. However, these approaches often overlook the knowledge already embedded within the LLMs, leading to redundant information integration and inefficient utilization of learned representations. To address this limitation, we propose RADAR, a framework for enhancing radiology report generation with supplementary knowledge injection. RADAR improves report generation by systematically leveraging both the internal knowledge of an LLM and externally retrieved information. Specifically, it first extracts the model's acquired knowledge that aligns with expert image-based classification outputs. It then retrieves relevant supplementary knowledge to further enrich this information. Finally, by aggregating both sources, RADAR generates more accurate and informative radiology reports. Extensive experiments on MIMIC-CXR, CheXpert-Plus, and IU X-ray demonstrate that our model outperforms state-of-the-art LLMs in both language quality and clinical accuracy

This study explores the use of Federated Learning (FL) for tuberculosis (TB) diagnosis using chest X-rays in low-resource settings across Africa. FL allows hospitals to collaboratively train AI models without sharing raw patient data, addressing privacy concerns and data scarcity that hinder traditional centralized models. The research involved hospitals and research centers in eight African countries. Most sites used local datasets, while Ghana and The Gambia used public ones. The study compared locally trained models with a federated model built across all institutions to evaluate FL's real-world feasibility. Despite its promise, implementing FL in sub-Saharan Africa faces challenges such as poor infrastructure, unreliable internet, limited digital literacy, and weak AI regulations. Some institutions were also reluctant to share model updates due to data control concerns. In conclusion, FL shows strong potential for enabling AI-driven healthcare in underserved regions, but broader adoption will require improvements in infrastructure, education, and regulatory support.

In many real-world applications, deployed models encounter inputs that differ from the data seen during training. Out-of-distribution detection identifies whether an input stems from an unseen distribution, while open-world recognition flags such inputs to ensure the system remains robust as ever-emerging, previously $unknown$ categories appear and must be addressed without retraining. Foundation and vision-language models are pre-trained on large and diverse datasets with the expectation of broad generalization across domains, including medical imaging. However, benchmarking these models on test sets with only a few common outlier types silently collapses the evaluation back to a closed-set problem, masking failures on rare or truly novel conditions encountered in clinical use. We therefore present $NOVA$, a challenging, real-life $evaluation-only$ benchmark of $\sim$900 brain MRI scans that span 281 rare pathologies and heterogeneous acquisition protocols. Each case includes rich clinical narratives and double-blinded expert bounding-box annotations. Together, these enable joint assessment of anomaly localisation, visual captioning, and diagnostic reasoning. Because NOVA is never used for training, it serves as an $extreme$ stress-test of out-of-distribution generalisation: models must bridge a distribution gap both in sample appearance and in semantic space. Baseline results with leading vision-language models (GPT-4o, Gemini 2.0 Flash, and Qwen2.5-VL-72B) reveal substantial performance drops across all tasks, establishing NOVA as a rigorous testbed for advancing models that can detect, localize, and reason about truly unknown anomalies.