High-field MRI offers superior SNR but is constrained by the trade-off between spatial resolution and acquisition time. Existing global deep learning super-resolution (SR) methods often incur computational overhead by ignoring regional image content. This motivates an adaptive local SR strategy to optimize efficiency and detail preservation. To address this, we developed a local SR method that adaptively allocates computational resources to information-rich regions. The proposed framework regularized an entropy-based local region processing strategy with a diffusion model fortified by frequency-domain and structural constraints. We retrospectively evaluated our method on two diverse datasets: a proprietary 7.0 T dental MRI dataset (25 T2-weighted DESS sequences from 10 beagle dogs) and a public 5.0 T brain MRI dataset (Diff5T, 50 diffusion-weighted sequences). Image quality was quantified using PSNR, SSIM, LPIPS, and FID. On the 7.0 T dental test dataset (2 subjects), our method achieved a PSNR of 27.31 [26.83, 27.79] dB and the lowest LPIPS of 0.19 [0.18, 0.20]. On the 5.0 T brain test dataset (10 subjects), the method achieved a PSNR of 27.15 ± 0.10 dB, an LPIPS of 0.14 ± 0.00 and an FID of 54.01, with lower perceptual metrics than the evaluated baselines. Ablation studies indicated that the proposed frequency-domain and structural constraints reduced LPIPS and FID, with trade-offs in PSNR and SSIM. In conclusion, the evaluated framework showed improvements in perceptual metrics by integrating targeted local processing with frequency-domain and structural regularization, accompanied by a trade-off in pixel-wise fidelity metrics, supporting the technical feasibility of addressing the resolution-time trade-off in high-field MRI. Future work will focus on expanding the dataset and evaluating the framework in human dental cohorts to address anatomical differences between the current canine model and human dental anatomy.
Background Although several quantitative methods are available for evaluating hyperuricemia-associated brain dysfunction, diffusion kurtosis imaging (DKI) exhibits greater sensitivity to subtle microstructural tissue changes, potentially enabling earlier detection of damage. Purpose To investigate the feasibility of hyperuricemia on cognitive impairment in rats using DKI. Materials and methods Fifty male rats were randomly divided into the normal control (CON) group and hyperuricemia model (HUA) group. Ten rats from each group were randomly selected and underwent longitudinal DKI scanning at baseline (week 0) and at weeks 2, 4, 6, and 8. DKI indicators were acquired with selecting bilateral symmetric regions of interest (ROI) in the hippocampal region, including, mean diffusivity (MD), fractional anisotropy (FA) and mean kurtosis (MK). The HE staining, GFAP and Iba-1 immunofluorescence staining were employed to reveal hippocampal histopathological changes. Additionally, the Morris water maze (MWM) test was applied to assess cognitive ability of rats at week 8th. Result In this study, the MD and FA values of hippocampal in HUA group exhibited a gradually decreasing trend, while the MK value gradually increased. Longitudinal analysis revealed earlier MK differences (weeks 4th–8th) and later FA divergences (weeks 6th–8th) between HUA and CON groups (p < 0.05). During weeks 4th–8th, the relative fluorescence intensity (RFI) of GFAP and, Iba-1 exhibited an inverse trend with FA value, whereas their changing trend was similar to that of MK value. Compared with controls, HUA rats showed the progressively longer latencies across training days, and fewer traversals and shorter durations of the platform in spatial exploration experiments. Conclusion DKI imaging was a non-invasive and sensitive method for identifying the HUA-induced hippocampal alterations and cognitive damage.
Neoadjuvant chemotherapy (NAC) is widely used for locally advanced breast cancer. Imaging monitoring during NAC facilitates timely treatment adjustments and leads to improved patient outcomes. Dynamic contrast-enhanced MRI plays a key role in assessing NAC response; however, early during treatment, tumor volume changes lag behind intracellular microstructural and functional alterations. Diffusion-weighted imaging (DWI) provides average tissue diffusion information based on Gaussian water motion but fails to capture intratumoral heterogeneity. Advanced DWI techniques, including intravoxel incoherent motion (IVIM), stretched exponential modeling (SEM), diffusion kurtosis imaging (DKI), diffusion tensor imaging (DTI), and DWI-based virtual magnetic resonance elastography (vMRE), have attracted growing interest in evaluating breast cancer during NAC. These techniques require no gadolinium-based contrast agents and can provide valuable information on tumor microstructure, heterogeneity, and microcirculation. However, a notable gap persists between the potential benefits of advanced DWI and their actual clinical utility. This review assesses the current applications and limitations of advanced DWI techniques in NAC for breast cancer.
