Capturing accurate dynamic information of moving organs is essential for functional assessment using non-invasive imaging modalities. Achieving high temporal resolution visualization of physiological processes remains a critical challenge in dynamic magnetic resonance imaging (MRI) when reconstructing from extremely limited acquisitions. We introduce an unsupervised zero-shot reconstruction framework combining Implicit Neural Representation (INR) with manifold learning, capable of reconstructing dynamic MRI data at unprecedented temporal resolutions (less than 10 ms per frame for 2D imaging, less than 400 ms per frame for 3D imaging). The framework employs learnable low-dimensional manifold vectors to autonomously capture motion in real time directly from undersampled data, and dynamically condition coordinate-based spatial representations to generate high-fidelity image sequences. Through a novel spatiotemporal coarse-to-fine (C2F) optimization strategy, our method outperforms current state-of-the-art (SOTA) techniques across multiple imaging scenarios, including cardiac, speech and dynamic-contrast-enhanced (DCE) abdominal MRI, demonstrating robust performance under challenging motion patterns and contrast dynamics. The learned manifolds additionally provide intuitive visualization of motion and contrast evolution during imaging. These advances indicate strong clinical potential for applications requiring extreme temporal resolution while maintaining both anatomical and temporal fidelity.

Cardiac magnetic resonance (CMR) imaging is widely used to characterize cardiac morphology and function. To accelerate CMR imaging, various methods have been proposed to recover high-quality spatiotemporal CMR images from highly undersampled k-t space data. However, current CMR reconstruction techniques either fail to achieve satisfactory image quality or are restricted by the scarcity of ground truth data, leading to limited applicability in clinical scenarios. In this work, we proposed MoCo‑INR, a new unsupervised method that integrates implicit neural representations (INR) with the conventional motion‑compensated (MoCo) framework. Using the explicit motion modeling and the continuous prior of INRs, our MoCo-INR can produce accurate cardiac motion decomposition and high-quality CMR reconstruction. Moreover, we present a new INR network architecture tailored to the CMR problem, which can greatly stabilize model optimization. Experiments on retrospective (i.e., simulated) datasets demonstrate the superiority of MoCo‑INR over state‑of‑the‑art methods, achieving fast convergence and fine‑detailed reconstructions at ultra‑high acceleration factors (e.g., 20x in VISTA sampling). In addition, evaluations on prospective (i.e., real-acquired) free‑breathing CMR scans highlight its clinical practicality for real‑time imaging. Several ablation studies also confirm the effectiveness of critical components of MoCo-INR.

Diffusion magnetic resonance imaging (dMRI) enables noninvasive mapping of tissue microstructure by probing water molecule diffusivity. While advanced multi-shell diffusion models offer improved sensitivity to cellular properties, their requirement for densely sampled q-space data leads to prohibitively long acquisition times. Current deep learning approaches for parameter estimation face three key limitations: (1) dependency on fixed acquisition protocols, (2) model-specific assumptions that constrain applicability, and (3) reliance on supervised learning paradigms that demand large labeled datasets and exhibit poor generalization to out-of-distribution cases. To address these challenges, we propose MINeR, a novel unsupervised subject-specific framework for reconstructing dense q-space data from highly undersampled acquisitions. Our method leverages direction-modulated implicit neural representation to flexibly sample diffusion signals across q-space, supporting the estimation of parameters for diverse diffusion models. Comprehensive evaluations demonstrate that MINeR maintains high fidelity in microstructural parameter estimation, particularly for advanced multi-shell diffusion models. The framework shows remarkable generalization capability, as evidenced by its robust performance on tumor data. Notably, MINeR effectively reconstructs high-quality diffusion signals by interpolating from 6 directions, significantly reducing acquisition time, while maintaining robust parameter estimation. This work presents a practical approach for enabling microstructural modeling from sparsely sampled q-space data, thereby improving the clinical applicability of diffusion MRI. The code is available at: https://github.com/AMRI-Lab/MINeR.

Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality ground-truth data hinders their applications due to the generalization problem. Recently, Implicit Neural Representation (INR) has emerged as a powerful DL-based tool for solving the inverse problem by characterizing the attributes of a signal as a continuous function of corresponding coordinates in an unsupervised manner. In this work, we proposed an INR-based method to improve dynamic MRI reconstruction from highly undersampled $\boldsymbol {k}$ -space data, which only takes spatiotemporal coordinates as inputs and does not require any training on external datasets or transfer-learning from prior images. Specifically, the proposed method encodes the dynamic MRI images into neural networks as an implicit function, and the weights of the network are learned from sparsely-acquired ( $\boldsymbol {k}$ , t)-space data itself only. Benefiting from the strong implicit continuity regularization of INR together with explicit regularization for low-rankness and sparsity, our proposed method outperforms the compared state-of-the-art methods at various acceleration factors. E.g., experiments on retrospective cardiac cine datasets show an improvement of 0.6-2.0 dB in PSNR for high accelerations (up to $40.8\times $ ). The high-quality and inner continuity of the images provided by INR exhibit great potential to further improve the spatiotemporal resolution of dynamic MRI. The code is available at: https://github.com/AMRI-Lab/INR_for_DynamicMRI.

The process of brain aging is intricate, encompassing significant structural and functional changes, including myelination and iron deposition in the brain. Brain age could act as a quantitative marker to evaluate the degree of the individual's brain evolution. Quantitative susceptibility mapping (QSM) is sensitive to variations in magnetically responsive substances such as iron and myelin, making it a favorable tool for estimating brain age. In this study, we introduce an innovative 3D convolutional network named Segmentation-Transformer-Age-Network (STAN) to predict brain age based on QSM data. STAN employs a two-stage network architecture. The first-stage network learns to extract informative features from the QSM data through segmentation training, while the second-stage network predicts brain age by integrating the global and local features. We collected QSM images from 712 healthy participants, with 548 for training and 164 for testing. The results demonstrate that the proposed method achieved a high accuracy brain age prediction with a mean absolute error (MAE) of 4.124 years and a coefficient of determination (R2) of 0.933. Furthermore, the gaps between the predicted brain age and the chronological age of Parkinson's disease patients were significantly higher than those of healthy subjects (P<0.01). We thus believe that using QSM-based predicted brain age offers a more reliable and accurate phenotype, with the potentiality to serve as a biomarker to explore the process of advanced brain aging.

Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.

In the cytopathology screening of cervical cancer, high-resolution digital cytopathological slides are critical for the interpretation of lesion cells. However, the acquisition of high-resolution digital slides requires high-end imaging equipment and long scanning time. In the study, we propose a GAN-based progressive multi-supervised super-resolution model called PathSRGAN (pathology super-resolution GAN) to learn the mapping of real low-resolution and high-resolution cytopathological images. With respect to the characteristics of cytopathological images, we design a new two-stage generator architecture with two supervision terms. The generator of the first stage corresponds to a densely-connected U-Net and achieves 4× to 10× super resolution. The generator of the second stage corresponds to a residual-in-residual DenseBlock and achieves 10× to 20× super resolution. The designed generator alleviates the difficulty in learning the mapping from 4× images to 20× images caused by the great numerical aperture difference and generates high quality high-resolution images. We conduct a series of comparison experiments and demonstrate the superiority of PathSRGAN to mainstream CNN-based and GAN-based super-resolution methods in cytopathological images. Simultaneously, the reconstructed high-resolution images by PathSRGAN improve the accuracy of computer-aided diagnosis tasks effectively. It is anticipated that the study will help increase the penetration rate of cytopathology screening in remote and impoverished areas that lack high-end imaging equipment.