Accurate segmentation of 3D vascular structures is essential for various medical imaging applications. The dispersed nature of vascular structures leads to inherent spatial uncertainty and necessitates location awareness, yet most current 3D medical segmentation models rely on the patch-wise training strategy that usually loses this spatial context. In this study, we introduce the Coordinate-aware Modulated Mamba Network (COMMA) and contribute a manually labeled dataset of 570 cases, the largest publicly available 3D cerebrovascular dataset to date. COMMA leverages both entire and cropped patch data through global and local branches, ensuring robust and efficient spatial location awareness. Specifically, COMMA employs a channel-compressed Mamba (ccMamba) block to efficiently encode full-resolution image data, capturing long-range dependencies while optimizing computational costs. Additionally, we propose a coordinate-aware modulated (CaM) block to enhance interactions between the global and local branches, allowing the local branch to better perceive spatial information. We evaluate COMMA on six datasets, covering two imaging modalities and five types of vascular tissues. The results demonstrate COMMA's superior performance compared to state-of-the-art methods with computational efficiency, especially in segmenting small vessels. Ablation studies further highlight the importance of our proposed modules and spatial information. The code will be available at COMMA.

Magnetic Particle Imaging (MPI) enables noninvasive temperature imaging without depth limitations. However, due to the lack of effective calibration strategies that can simultaneously address issues such as calibration infeasibility and environmental mismatch, its practical in vivo application remains challenging. In this work, we propose a novel in vivo temperature imaging method based on a dual-mode magnetic particle spectroscopy/magnetic particle imaging (MPS/MPI) system. First, MPS is employed to capture the differences in harmonic phase responses of magnetic nanoparticles (MNPs) under in vivo and in vitro conditions, thereby enabling the construction of calibration functions that are consistent with the in vivo environment. Second, an MLP based calibration strategy is proposed, which accounts for non-ideal deviations from the approximately linear temperature-phase relationship and integrates multi-parameter information into a unified network, thereby enabling accurate and stable temperature mapping. Comprehensive simulation, in vitro, and in vivo experiments demonstrate that, compared with conventional phantom-based temperature mapping methods, the proposed method reduces the in vivo temperature reconstruction error by approximately 17.24% and achieves an average absolute temperature error below $1.257~^{\circ } $ C. These results verify the feasibility of accurate in vivo temperature imaging using MPI and provide essential technical support for temperature-sensitive applications, including magnetic hyperthermia.

Brain networks generated by functional magnetic resonance imaging (fMRI) have shown promising performance in characterizing cerebral social cognition and disorders. However, the scarcity of labeled data has hindered the application of deep graph learning in brain network analysis, accelerating the usage of extra label-free self-supervised contrastive graph learning. However, existing augmentation strategies commonly used in contrastive learning (CL), such as edge and node drop, do not fully benefit brain network learning due to the distribution differences between different modalities of brain neural imaging. To this end, we introduce a novel approach namely spatial–temporal hierarchical augmentation-based contrastive learning (ST-HACL) to enhance the representation learning of functional brain networks. ST-HACL leverages augmentation methods tailored specifically to brain networks. Our method employs an augmentation strategy from both spatial and temporal level during the brain network construction process to generate contrastive samples, enabling label-free self-supervised learning. We evaluate the performance of our approach on the orthostatic hypotension dataset (OH) and the Alzheimer's disease neuroimaging initiative dataset (ADNI). Results demonstrate that our model surpasses existing graph neural network (GNN) models and graph-CL methods, achieving F1 scores of 80.61% in OH and 73.01% in ADNI. To the best of our knowledge, our study represents the first attempt at applying brain network-specific contrastive augmentation learning to fMRI analysis.

Recently, Magnetic Particle Imaging, an emerging functional imaging modality, has exhibited outstanding spatial-temporal resolution and sensitivity. The general reconstruction pipeline of Magnetic Particle Imaging involves calibrating a System Matrix and then solving an ill-posed inverse problem combined with the measured particle signals. However, the introduction of noise during the System Matrix calibration procedure is inevitable, which degrades the detailed information in the reconstructed images. Therefore, frequency selection methods based on signal-to-noise ratio are commonly adopted. However, these methods lead to a decrease in the available high-frequency components, which damages the spatial resolution. To address this problem, we propose an unsupervised memory-guided denoising framework with unpaired noisy-clean System Matrix components, called U-N2C. Specifically, we design a Pattern Memory Block to memorize System Matrix patterns, directed by a position-aware frequency index embedding. Meanwhile, we devise a Noise Memory Block to implicitly approximate noise distributions. With the guidance of our dual memory blocks, we can disentangle the noise and content of the System Matrix in the latent space. Furthermore, benefiting from the ability to model complex noise, our method can generate pseudo but high-quality noisy-clean pairs and further enhance our denoising capability. Experiments on both synthetic and real noise demonstrate that our U-N2C achieves cutting-edge performance compared to other methods. Moreover, we conduct extensive qualitative and quantitative ablation studies to verify the effectiveness of our method. Our code has been available at U-N2C.

Graph neural networks (GNNs) provide powerful insights into brain neuroimaging technology from the view of graphical networks. However, most existing GNN-based models treat the brain connectome, derived from neuroimaging, as a homogeneous graph characterized by uniform node and edge types. In fact, emerging studies have reported and emphasized the significance of heterogeneity among human brain activities, especially between the two cerebral hemispheres. Thus, homogeneous-structured brain network-based graph methods are insufficient for modeling complicated cerebral activity states. To overcome this problem, we introduce a novel heterogeneous graph neural network (HeBrainGNN) for multimodal brain neuroimaging fusion learning. HeBrainGNN first conceptualizes the brain network as a heterogeneous graph with multiple types of nodes (representing the left and right hemispheres) and edges (categorizing intra- and interhemispheric interactions). We further develop a self-supervised pretraining strategy for this heterogeneous network to address the potential overfitting problem caused by the conflict between a large parameter size and a small medical data sample size. Empirical results show the superiority of the proposed model over other existing methods in brain-related disease prediction tasks. Ablation experiments show that our heterogeneous graph-based model attaches more importance to hemispheric connections that may be neglected due to their low strength by previous homogeneous graph models. Additional experiments reveal that our pretraining strategy not only addresses the challenge of limited labeled data but also significantly enhances accuracy, affirming the potential of our approach in advancing neuroimaging analysis.

Representation learning in heterogeneous graphs with massive unlabeled data has aroused great interest. The heterogeneity of graphs not only contains rich information, but also raises difficult barriers to designing unsupervised or self-supervised learning (SSL) strategies. Existing methods such as random walk-based approaches are mainly dependent on the proximity information of neighbors and lack the ability to integrate node features into a higher-level representation. Furthermore, previous self-supervised or unsupervised frameworks are usually designed for node-level tasks, which are commonly short of capturing global graph properties and may not perform well in graph-level tasks. Therefore, a label-free framework that can better capture the global properties of heterogeneous graphs is urgently required. In this article, we propose a self-supervised heterogeneous graph neural network (GNN) based on cross-view contrastive learning (HeGCL). The HeGCL presents two views for encoding heterogeneous graphs: the meta-path view and the outline view. Compared with the meta-path view that provides semantic information, the outline view encodes the complex edge relations and captures graph-level properties by using a nonlocal block. Thus, the HeGCL learns node embeddings through maximizing mutual information (MI) between global and semantic representations coming from the outline and meta-path view, respectively. Experiments on both node-level and graph-level tasks show the superiority of the proposed model over other methods, and further exploration studies also show that the introduction of nonlocal block brings a significant contribution to graph-level tasks.

Magnetic particle imaging (MPI) is an emerging technique for determining magnetic nanoparticle distributions in biological tissues. Although system-matrix (SM)-based image reconstruction offers higher image quality than the X-space-based approach, the SM calibration measurement is time-consuming. Additionally, the SM should be recalibrated if the tracer's characteristics or the magnetic field environment change, and repeated SM measurement further increase the required labor and time. Therefore, fast SM calibration is essential for MPI. Existing calibration methods commonly treat each row of the SM as independent of the others, but the rows are inherently related through the coil channel and frequency index. As these two elements can be regarded as additional multimodal information, we leverage the transformer architecture with a self-attention mechanism to encode them. Although the transformer has shown superiority in multimodal fusion learning across several fields, its high complexity may lead to overfitting when labeled data are scarce. Compared with labeled SM (i.e., full size), low-resolution SM data can be easily obtained, and fully using such data may alleviate overfitting. Accordingly, we propose a pseudo-label-based progressive pretraining strategy to leverage unlabeled data. Our method outperforms existing calibration methods on a public real-world OpenMPI dataset and simulation dataset. Moreover, our method improves the resolution of two in-house MPI scanners without requiring full-size SM measurements. Ablation studies confirm the contributions of modeling SM inter-row relations and the proposed pretraining strategy.

Neuroimaging plays an significant role in diagnosing and pathological study of brain diseases. Considering that both functional and structural abnormalities may lead to brain dis-eases and disorders, single modal neuroimaging approach may not fully characterize brain activities and working modes. Fusion of multimodal neuroimaging data is expected to provide more comprehensive characterization of brain diseases, given that the different modalities contain more complementary information. Recently, Graph Convolutional Networks (GCNs) is shown to have powerful capacity in representation learning for graph-structure data, which is considered to integrate both graph se-mantic structure and node information. Therefore, in this paper, we propose the Weighted Graph AutoEncoder (WGAE), a GCN- driven multimodal fusion model, to learn the combinational latent node representation of fMRI and DTI neuroimaging data, which are used as node features and graph structure respectively in the graph in unsupervised manner. Experimental results on two real-world datasets show the superiority of the proposed model over other existing single-modal or multi-modal methods in learning representations for disease prediction as the downstream task. Furthermore, ablation experiments also show the collaborative contribution of multimodal neuroimaging fusion in the proposed model, and also show the feasibility of assessing the respective importance of the two modalities during the disease prediction.