Skull stripping is an initial and critical step in the pipeline of mouse fMRI analysis. Manual labeling of the brain usually suffers from intra- and inter-rater variability and is highly time-consuming. Hence, an automatic and efficient skull-stripping method is in high demand for mouse fMRI studies. In this study, we investigated a 3D U-Net based method for automatic brain extraction in mouse fMRI studies. Two U-Net models were separately trained on T2-weighted anatomical images and T2*-weighted functional images. The trained models were tested on both interior and exterior datasets. The 3D U-Net models yielded a higher accuracy in brain extraction from both T2-weighted images (Dice > 0.984, Jaccard index > 0.968 and Hausdorff distance < 7.7) and T2*-weighted images (Dice > 0.964, Jaccard index > 0.931 and Hausdorff distance < 3.3), compared with the two widely used mouse skull-stripping methods (RATS and SHERM). The resting-state fMRI results using automatic segmentation with the 3D U-Net models are highly consistent with those obtained by manual segmentation for both the seed-based and group independent component analysis. These results demonstrate that the 3D U-Net based method can replace manual brain extraction in mouse fMRI analysis.

Diffusion tensor imaging (DTI) is a prevalent magnetic resonance imaging (MRI) technique, widely used in clinical and neuroscience research. However, the reliability of DTI is affected by the low signal-to-noise ratio inherent in diffusion-weighted (DW) images. Deep learning (DL) has shown promise in improving the quality of DTI, but its limited generalization to variable acquisition schemes hinders practical applications. This study aims to develop a generalized, accurate, and efficient DL-based DTI method. By leveraging the representation of voxel-wise diffusion MRI (dMRI) signals on the sphere using spherical harmonics (SH), we propose a novel approach that utilizes SH coefficient maps as input to a network for predicting the diffusion tensor (DT) field, enabling improved generalization. Extensive experiments were conducted on simulated and in-vivo datasets, covering various DTI application scenarios. The results demonstrate that the proposed SH-DTI method achieves advanced performance in both quantitative and qualitative analyses of DTI. Moreover, it exhibits remarkable generalization capabilities across different acquisition schemes, centers, and scanners, ensuring its broad applicability in diverse settings.

Diffusion kurtosis imaging (DKI) has been shown to be valuable in a wide range of neuroscientific and clinical applications. However, reliable estimation of DKI tensors is often compromised by noise, especially for the kurtosis tensor (KT). Here, we propose a joint denoising and estimating framework that integrates multiple sources of prior information, including nonlocal structural self-similarity (NSS), local spatial smoothness (LSS), physical relevance (PR) of the DKI model, and noise characteristics of magnitude diffusion MRI (dMRI) images for improved estimation of DKI tensors. The local and nonlocal spatial smoothing constraints are complementary to each other, making the proposed framework highly effective in reducing the noise fluctuations on DKI tensors, especially KT. As an additional refinement, we propose to impose a physically relevant constraint within our joint denoising and estimation framework. We further adopt the first-moment noise-corrected fitting model (M ¹ NCM) to remove the noncentral ${\chi }$ -distribution noise bias. The effectiveness of integrating multiple sources of priors into the joint framework is verified by comparing the proposed M ¹ NCM-NSS-LSS-PR method with various versions of M ¹ NCM-based estimators and two state-of-the-art methods. Results show that the proposed method outperformed the compared methods in simulations and in-vivo dMRI datasets of both spatially stationary and nonstationary noise distributions. The in-vivo experiments also show that the proposed M ¹ NCM-NSS-LSS-PR method was robust to the number of diffusion directions.

MRI of effective transverse relaxation rate (R2*) measurement is a reliable method for liver iron concentration quantification. However, R2* mapping can be degraded by noise, especially in the case of iron overload. This study aimed to develop a deep learning method for MRI R2* relaxometry of an iron-loaded liver using a two-stage cascaded neural network. The proposed method, named CadamNet, combines two convolutional neural networks separately designed for image denoising and parameter mapping into a cascade framework, and the physics-based R2* decay model was incorporated in training the mapping network to enforce data consistency further. CadamNet was trained using simulated liver data with Rician noise, which was constructed from clinical liver data. The performance of CadamNet was quantitatively evaluated on simulated data with varying noise levels as well as clinical liver data and compared with the single-stage parameter mapping network (MappingNet) and two conventional model-based R2* mapping methods. CadamNet consistently achieved high-quality R2* maps and outperformed MappingNet at varying noise levels. Compared with conventional R2* mapping methods, CadamNet yielded R2* maps with lower errors, higher quality, and substantially increased efficiency. In conclusion, the proposed CadamNet enables accurate and efficient iron-loaded liver R2* mapping, especially in the presence of severe noise.

Background: Diffusion kurtosis imaging (DKI) and neurite orientation dispersion and density imaging (NODDI) provide more comprehensive and informative perspective on microstructural alterations of cerebral white matter (WM) than single-shell diffusion tensor imaging (DTI), especially in the detection of crossing fiber. However, studies on systemic lupus erythematosus patients without neuropsychiatric symptoms (non-NPSLE patients) using multi-shell diffusion imaging remain scarce. Methods: Totally 49 non-NPSLE patients and 41 age-, sex-, and education-matched healthy controls underwent multi-shell diffusion magnetic resonance imaging. Totally 10 diffusion metrics based on DKI (fractional anisotropy, mean diffusivity, axial diffusivity, radial diffusivity, mean kurtosis, axial kurtosis and radial kurtosis) and NODDI (neurite density index, orientation dispersion index and volume fraction of the isotropic diffusion compartment) were evaluated. Tract-based spatial statistics (TBSS) and atlas-based region-of-interest (ROI) analyses were performed to determine group differences in brain WM microstructure. The associations of multi-shell diffusion metrics with clinical indicators were determined for further investigation. Results: TBSS analysis revealed reduced FA, AD and RK and increased ODI in the WM of non-NPSLE patients (P < 0.05, family-wise error corrected), and ODI showed the best discriminative ability. Atlas-based ROI analysis found increased ODI values in anterior thalamic radiation (ATR), inferior frontal-occipital fasciculus (IFOF), forceps major (F_major), forceps minor (F_minor) and uncinate fasciculus (UF) in non-NPSLE patients, and the right ATR showed the best discriminative ability. ODI in the F_major was positively correlated to C3. Conclusion: This study suggested that DKI and NODDI metrics can complementarily detect WM abnormalities in non-NPSLE patients and revealed ODI as a more sensitive and specific biomarker than DKI, guiding further understanding of the pathophysiological mechanism of normal-appearing WM injury in SLE.

Diffusion MRI tractography technique enables non-invasive visualization of the white matter pathways in the brain. It plays a crucial role in neuroscience and clinical fields by facilitating the study of brain connectivity and neurological disorders. However, the accuracy of reconstructed tractograms has been a longstanding challenge. Recently, deep learning methods have been applied to improve tractograms for better white matter coverage, but often comes at the expense of generating excessive false-positive connections. This is largely due to their reliance on local information to predict long-range streamlines. To improve the accuracy of streamline propagation predictions, we introduce a novel deep learning framework that integrates image-domain spatial information and anatomical information along tracts, with the former extracted through convolutional layers and the latter modeled via a Transformer-decoder. Additionally, we employ a weighted loss function to address fiber class imbalance encountered during training. We evaluate the proposed method on the simulated ISMRM 2015 Tractography Challenge dataset, achieving a valid streamline rate of 66.2 %, white matter coverage of 63.8 %, and successfully reconstructing 24 out of 25 bundles. Furthermore, on the multi-site Tractoinferno dataset, the proposed method demonstrates its ability to handle various diffusion MRI acquisition schemes, achieving a 5.7 % increase in white matter coverage and a 4.1 % decrease in overreach compared to RNN-based methods.