Alzheimer's disease (AD) classification models usually segment the entire brain image into voxel blocks and assign them labels consistent with the entire image, but not every voxel block is closely related to the disease. To this end, an AD auxiliary diagnosis framework based on weakly supervised multi-instance learning (MIL) and multi-scale feature fusion is proposed, and the framework is designed from three aspects: within the voxel block, between voxel blocks, and high-confidence voxel blocks. First, a three-dimensional convolutional neural network was used to extract deep features within the voxel block; then the spatial correlation information between voxel blocks was captured through position encoding and attention mechanism; finally, high-confidence voxel blocks were selected and combined with multi-scale information fusion strategy to integrate key features for classification decision. The performance of the model was evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies (OASIS) datasets. Experimental results showed that the proposed framework improved ACC and AUC by 3% and 4% on average compared with other mainstream frameworks in the two tasks of AD classification and mild cognitive impairment conversion classification, and could find the key voxel blocks that trigger the disease, providing an effective basis for AD auxiliary diagnosis.
Alzheimer Disease/diagnosis* ; Humans ; Neuroimaging/methods* ; Neural Networks, Computer ; Brain/diagnostic imaging* ; Magnetic Resonance Imaging ; Deep Learning ; Machine Learning

The gradient field, one of the core magnetic fields in magnetic resonance imaging (MRI) systems, is generated by gradient coils and plays a critical role in spatial encoding and the generation of echo signals. The uniformity or linearity of the gradient field directly impacts the quality and distortion level of MRI images. However, traditional point measurement methods lack accuracy in assessing the linearity of gradient fields, making it difficult to provide effective parameters for image distortion correction. This paper introduced a spherical measurement-based method that involved measuring the magnetic field distribution on a sphere, followed by detailed magnetic field calculations and linearity analysis. This study, applied to assess the nonlinearity of asymmetric head gradient coils, demonstrated more comprehensive and precise results compared to point measurement methods. This advancement not only strengthens the scientific basis for the design of gradient coils but also provides more reliable parameters and methods for the accurate correction of MRI image distortions.
Magnetic Resonance Imaging/instrumentation* ; Humans ; Image Processing, Computer-Assisted/methods* ; Nonlinear Dynamics ; Magnetic Fields ; Algorithms ; Phantoms, Imaging

Depression, a mental health disorder, has emerged as one of the significant challenges in the global public health domain. Investigating the pathogenesis of depression and accurately assessing the symptomatic changes are fundamental to formulating effective clinical diagnosis and treatment strategies. Utilizing non-invasive brain imaging technologies such as functional magnetic resonance imaging and scalp electroencephalography, existing studies have confirmed that the onset of depression is closely associated with abnormal neural activities and altered functional connectivity in multiple brain regions. Magnetoencephalography, unaffected by tissue conductivity and skull thickness, boasts high spatial resolution and signal-to-noise ratio, offering unique advantages and significant value in revealing the abnormal brain mechanisms and neural characteristics of depression. This review, starting from the rhythmic characteristics, nonlinear dynamic features, and connectivity characteristics of magnetoencephalography in depression patients, revisits the research progress on magnetoencephalography features related to depression, discusses current issues and future development trends, and provides insights for the study of pathophysiological mechanisms, as well as for clinical diagnosis and treatment of depression.
Humans ; Magnetoencephalography/methods* ; Brain/physiopathology* ; Depression/diagnosis* ; Electroencephalography ; Magnetic Resonance Imaging

Aiming at the problems of low accuracy and large difference of segmentation boundary distance in anterior cruciate ligament (ACL) image segmentation of knee joint, this paper proposes an ACL image segmentation model by fusing dilated convolution and residual hybrid attention U-shaped network (DRH-UNet). The proposed model builds upon the U-shaped network (U-Net) by incorporating dilated convolutions to expand the receptive field, enabling a better understanding of the contextual relationships within the image. Additionally, a residual hybrid attention block is designed in the skip connections to enhance the expression of critical features in key regions and reduce the semantic gap, thereby improving the representation capability for the ACL area. This study constructs an enhanced annotated ACL dataset based on the publicly available Magnetic Resonance Imaging Network (MRNet) dataset. The proposed method is validated on this dataset, and the experimental results demonstrate that the DRH-UNet model achieves a Dice similarity coefficient (DSC) of (88.01±1.57)% and a Hausdorff distance (HD) of 5.16±0.85, outperforming other ACL segmentation methods. The proposed approach further enhances the segmentation accuracy of ACL, providing valuable assistance for subsequent clinical diagnosis by physicians.
Humans ; Magnetic Resonance Imaging/methods* ; Anterior Cruciate Ligament/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; Knee Joint/diagnostic imaging* ; Neural Networks, Computer ; Algorithms ; Deep Learning

Among numerous medical imaging modalities, diffusion weighted imaging (DWI) is extremely sensitive to acute ischemic stroke lesions, especially small infarcts. However, magnetic resonance imaging is time-consuming and expensive, and it is also prone to interference from metal implants. Therefore, the aim of this study is to design a medical image synthesis method based on generative adversarial network, Stroke-p2pHD, for synthesizing DWI images from computed tomography (CT). Stroke-p2pHD consisted of a generator that effectively fused local image features and global context information (Global_to_Local) and a multi-scale discriminator (M ²Dis). Specifically, in the Global_to_Local generator, a fully convolutional Transformer (FCT) and a local attention module (LAM) were integrated to achieve the synthesis of detailed information such as textures and lesions in DWI images. In the M ²Dis discriminator, a multi-scale convolutional network was adopted to perform the discrimination function of the input images. Meanwhile, an optimization balance with the Global_to_Local generator was ensured and the consistency of features in each layer of the M ²Dis discriminator was constrained. In this study, the public Acute Ischemic Stroke Dataset (AISD) and the acute cerebral infarction dataset from Yantaishan Hospital were used to verify the performance of the Stroke-p2pHD model in synthesizing DWI based on CT. Compared with other methods, the Stroke-p2pHD model showed excellent quantitative results (mean-square error = 0.008, peak signal-to-noise ratio = 23.766, structural similarity = 0.743). At the same time, relevant experimental analyses such as computational efficiency verify that the Stroke-p2pHD model has great potential for clinical applications.
Humans ; Tomography, X-Ray Computed/methods* ; Diffusion Magnetic Resonance Imaging/methods* ; Cerebral Infarction/diagnostic imaging* ; Stroke/diagnostic imaging* ; Neural Networks, Computer ; Image Processing, Computer-Assisted/methods* ; Algorithms

In different stages of schizophrenia (SZ), alterations in gray matter volume (GMV) of patients are normally regulated by various pathological mechanisms. Instead of analyzing stage-specific changes, this study employed a multivariate structural covariance model and sliding-window approach to investigate the illness duration-related developmental trajectory of GMV in SZ. The trajectory is defined as a sequence of brain regions activated by illness duration, represented as a sparsely directed matrix. By applying this approach to structural magnetic resonance imaging data from 145 patients with SZ, we observed a continuous developmental trajectory of GMV from cortical to subcortical regions, with an average change occurring every 0.208 years, covering a time window of 20.176 years. The starting points were widely distributed across all networks, except for the ventral attention network. These findings provide insights into the neuropathological mechanism of SZ with a neuroprogressive model and facilitate the development of process for aided diagnosis and intervention with the starting points.
Humans ; Schizophrenia/pathology* ; Gray Matter/pathology* ; Magnetic Resonance Imaging ; Disease Progression ; Male ; Female ; Brain/pathology* ; Cerebral Cortex/pathology* ; Adult

To address the issues of difficulty in preserving anatomical structures, low realism of generated images, and loss of high-frequency image information in medical image cross-modal translation, this paper proposes a medical image cross-modal translation method based on diffusion generative adversarial networks. First, an unsupervised translation module is used to convert magnetic resonance imaging (MRI) into pseudo-computed tomography (CT) images. Subsequently, a nonlinear frequency decomposition module is used to extract high-frequency CT images. Finally, the pseudo-CT image is input into the forward process, while the high-frequency CT image as a conditional input is used to guide the reverse process to generate the final CT image. The proposed model is evaluated on the SynthRAD2023 dataset, which is used for CT image generation for radiotherapy planning. The generated brain CT images achieve a Fréchet Inception Distance (FID) score of 33.159 7, a structure similarity index measure (SSIM) of 89.84%, a peak signal-to-noise ratio (PSNR) of 35.596 5 dB, and a mean squared error (MSE) of 17.873 9. The generated pelvic CT images yield an FID score of 33.951 6, a structural similarity index of 91.30%, a PSNR of 34.870 7 dB, and an MSE of 17.465 8. Experimental results show that the proposed model generates highly realistic CT images while preserving anatomical accuracy as much as possible. The transformed CT images can be effectively used in radiotherapy planning, further enhancing diagnostic efficiency.
Humans ; Tomography, X-Ray Computed/methods* ; Magnetic Resonance Imaging/methods* ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Brain/diagnostic imaging* ; Algorithms ; Radiotherapy Planning, Computer-Assisted ; Generative Adversarial Networks

To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region. On the second stage, the optimal path search strategy for the brain midline is employed based on the network output probability map, which effectively addresses the problem of discontinuous midline segmentation. The method proposed in this paper achieved satisfactory results on the CQ500 dataset provided by the Center for Advanced Research in Imaging, Neurosciences and Genomics, New Delhi, India. The Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and normalized surface Dice (NSD) were 67.38 ± 10.49, 24.22 ± 24.84, 1.33 ± 1.83, and 0.82 ± 0.09, respectively. The experimental results demonstrate that the proposed method can fully utilize the prior knowledge of medical images to effectively achieve accurate segmentation of the brain midline, providing valuable assistance for subsequent identification of the brain midline by clinicians.
Humans ; Brain/diagnostic imaging* ; Deep Learning ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Magnetic Resonance Imaging/methods* ; Neural Networks, Computer

Small animal multimodal biomedical imaging refers to the integration of multiple imaging techniques within the same system or device to acquire comprehensive physiological and pathological information of small animals, such as mice and rats. With the continuous advancement of biomedical research, this cutting-edge technology has attracted extensive attention. Multimodal imaging techniques, based on diverse imaging principles, overcome the limitations of single-modal imaging through information fusion, significantly enhancing the overall system's sensitivity, temporal/spatial resolution, and quantitative accuracy. In the future, the integration of new materials and artificial intelligence will further boost its sensitivity and resolution. Through interdisciplinary innovation, this technology is expected to become the core technology of personalized medicine and expand its applications to drug development, environmental monitoring, and other fields, thus reshaping the landscape of biomedical research and clinical practice. This review summarized the progress on the application and investigation of multimodal biomedical imaging techniques, and discussed its development in the future.
Animals ; Multimodal Imaging/trends* ; Rats ; Mice ; Artificial Intelligence ; Diagnostic Imaging/methods* ; Magnetic Resonance Imaging ; Tomography, X-Ray Computed

Pan-vascular diseases encompass a range of systemic conditions characterized by sharing a common pathologic basis of vascular deterioration. Due to the complexity of these diseases, a thorough understanding on their similarities and differences is essential for optimizing diagnosis and treatment strategies. Magnetic resonance imaging (MRI), as one of the commonly used medical imaging techniques, has been widely applied in the diagnosis of pan-vascular diseases. Particularly, the integration of MRI with contrast agents and multi-parameter imaging techniques significantly enhances diagnostic accuracy, reducing the likelihood of missed or incorrect diagnoses. Recently, a variety of nano-magnetic resonance contrast agents have been developed and applied to the magnetic resonance imaging diagnosis of diseases. These nanotechnology-based contrast agents provide multiple advantages, ensuring more precise and forward-looking imaging of pan-vascular conditions. In this review, the diverse application strategies of nanomaterials-enhanced MRI techniques in the diagnosis of pan-vascular diseases were systematically summarized, by classifying them into the commonly used MRI sequences in clinical practice. Additionally, the potential advantages and challenges associated with the clinical translation of nanomaterial-enhanced MRI were also discussed. This review not only offers a novel perspective on the precise diagnosis of pan-vascular diseases, but also serves as a valuable reference for future clinical practice and research in the field.
Humans ; Magnetic Resonance Imaging/methods* ; Contrast Media ; Vascular Diseases/diagnostic imaging* ; Nanostructures