Magnetic resonance imaging (MRI) is commonly used for studying infant brain development. However, due to the lengthy image acquisition time and limited subject compliance, high-quality infant MRI can be challenging. Without imposing additional burden on image acquisition, image super-resolution (SR) can be used to enhance image quality post-acquisition. Most SR techniques are supervised and trained on multiple aligned low-resolution (LR) and high-resolution (HR) image pairs, which in practice are not usually available. Unlike supervised approaches, Deep Image Prior (DIP) can be employed for unsupervised single-image SR, utilizing solely the input LR image for de novo optimization to produce an HR image. However, determining when to stop early in DIP training is non-trivial and presents a challenge to fully automating the SR process. To address this issue, we constrain the low-frequency k-space of the SR image to be similar to that of the LR image. We further improve performance by designing a dual-modal framework that leverages shared anatomical information between T1-weighted and T2-weighted images. We evaluated our model, dual-modal DIP (dmDIP), on infant MRI data acquired from birth to one year of age, demonstrating that enhanced image quality can be obtained with substantially reduced sensitivity to early stopping.

OBJECTIVE: The technological advancements in surgical robots compatible with magnetic resonance imaging (MRI) have created an indispensable demand for real-time deformable image registration (DIR) of pre- and intra-operative MRI, but there is a lack of relevant methods. Challenges arise from dimensionality mismatch, resolution discrepancy, non-rigid deformation and requirement for real-time registration.
METHODS: In this paper, we propose a real-time DIR framework called MatchMorph, specifically designed for the registration of low-resolution local intraoperative MRI and high-resolution global preoperative MRI. Firstly, a super-resolution network based on global inference is developed to enhance the resolution of intraoperative MRI to the same as preoperative MRI, thus resolving the resolution discrepancy. Secondly, a fast-matching algorithm is designed to identify the optimal position of the intraoperative MRI within the corresponding preoperative MRI to address the dimensionality mismatch. Further, a cross-attention-based dual-stream DIR network is constructed to manipulate the deformation between pre- and intra-operative MRI, real-timely.
RESULTS: We conducted comprehensive experiments on publicly available datasets IXI and OASIS to evaluate the performance of the proposed MatchMorph framework. Compared to the state-of-the-art (SOTA) network TransMorph, the designed dual-stream DIR network of MatchMorph achieved superior performance with a 1.306 mm smaller HD and a 0.07 mm smaller ASD score on the IXI dataset. Furthermore, the MatchMorph framework demonstrates an inference speed of approximately 280 ms.
CONCLUSIONS: The qualitative and quantitative registration results obtained from high-resolution global preoperative MRI and simulated low-resolution local intraoperative MRI validated the effectiveness and efficiency of the proposed MatchMorph framework.

Feature extraction plays a pivotal role in the context of single image super-resolution. Nonetheless, relying on a single feature extraction method often undermines the full potential of feature representation, hampering the model\'s overall performance. To tackle this issue, this study introduces the wide-activation feature distillation network (WFDN), which realizes single image super-resolution through dual-path learning. Initially, a dual-path parallel network structure is employed, utilizing a residual network as the backbone and incorporating global residual connections to enhance feature exploitation and expedite network convergence. Subsequently, a feature distillation block is adopted, characterized by fast training speed and a low parameter count. Simultaneously, a wide-activation mechanism is integrated to further enhance the representational capacity of high-frequency features. Lastly, a gated fusion mechanism is introduced to weight the fusion of feature information extracted from the dual branches. This mechanism enhances reconstruction performance while mitigating information redundancy. Extensive experiments demonstrate that the proposed algorithm achieves stable and superior results compared to the state-of-the-art methods, as evidenced by quantitative evaluation metrics tests conducted on four benchmark datasets. Furthermore, our WFDN excels in reconstructing images with richer detailed textures, more realistic lines, and clearer structures, affirming its exceptional superiority and robustness.

Since its invention, super-resolution microscopy has become a popular tool for advanced imaging of biological structures, allowing visualisation of subcellular structures at a spatial scale below the diffraction limit. Thus, it is not surprising that recently, different super-resolution techniques are being applied in neuroscience, e.g. to resolve the clustering of neurotransmitter receptors and protein complex composition in presynaptic terminals. Still, the vast majority of these experiments were carried out either in cell cultures or very thin tissue sections, while there are only a few examples of super-resolution imaging in deeper layers (30 - 50 µm) of biological samples. In that context, the mammalian whole-mount retina has rarely been studied with super-resolution microscopy. Here, we aimed at establishing a stimulated-emission-depletion (STED) microscopy protocol for imaging whole-mount retina. To this end, we developed sample preparation including horizontal slicing of retinal tissue, an immunolabeling protocol with STED-compatible fluorophores and optimised the image acquisition settings. We labelled subcellular structures in somata, dendrites, and axons of retinal ganglion cells in the inner mouse retina. By measuring the full width at half maximum of the thinnest filamentous structures in our preparation, we achieved a resolution enhancement of two or higher compared to conventional confocal images. When combined with horizontal slicing of the retina, these settings allowed visualisation of putative GABAergic horizontal cell synapses in the outer retina. Taken together, we successfully established a STED protocol for reliable super-resolution imaging in the whole-mount mouse retina at depths between 30 and 50 µm, which enables investigating, for instance, protein complex composition and cytoskeletal ultrastructure at retinal synapses in health and disease.

OBJECTIVE: To assess the feasibility and efficacy of a deep learning-based three-dimensional (3D) super-resolution diffusion-weighted imaging (DWI) radiomics model in predicting the prognosis of high-intensity focused ultrasound (HIFU) ablation of uterine fibroids.
METHODS: This retrospective study included 360 patients with uterine fibroids who received HIFU treatment, including Center A (training set: N = 240; internal testing set: N = 60) and Center B (external testing set: N = 60) and were classified as having a favorable or unfavorable prognosis based on the postoperative non-perfusion volume ratio. A deep transfer learning approach was used to construct super-resolution DWI (SR-DWI) based on conventional high-resolution DWI (HR-DWI), and 1198 radiomics features were extracted from manually segmented regions of interest in both image types. Following data preprocessing and feature selection, radiomics models were constructed for HR-DWI and SR-DWI using Support Vector Machine (SVM), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM) algorithms, with performance evaluated using area under the curve (AUC) and decision curves.
RESULTS: All DWI radiomics models demonstrated superior AUC in predicting HIFU ablated uterine fibroids prognosis compared to expert radiologists (AUC: 0.706, 95% CI: 0.647-0.748). When utilizing different machine learning algorithms, the HR-DWI model achieved AUC values of 0.805 (95% CI: 0.679-0.931) with SVM, 0.797 (95% CI: 0.672-0.921) with RF, and 0.770 (95% CI: 0.631-0.908) with LightGBM. Meanwhile, the SR-DWI model outperformed the HR-DWI model (P < 0.05) across all algorithms, with AUC values of 0.868 (95% CI: 0.775-0.960) with SVM, 0.824 (95% CI: 0.715-0.934) with RF, and 0.821 (95% CI: 0.709-0.933) with LightGBM. And decision curve analysis further confirmed the good clinical value of the models.
CONCLUSIONS: Deep learning-based 3D SR-DWI radiomics model demonstrated favorable feasibility and effectiveness in predicting the prognosis of HIFU ablated uterine fibroids, which was superior to HR-DWI model and assessment by expert radiologists.

For convenient transmission, omnidirectional images (ODIs) usually follow the equirectangular projection (ERP) format and are low-resolution. To provide better immersive experience, omnidirectional image super resolution (ODISR) is essential. However, ERP ODIs suffer from serious geometric distortion and pixel stretching across latitudes, generating massive redundant information at high latitudes. This characteristic poses a huge challenge for the traditional SR methods, which can only obtain the suboptimal ODISR performance. To address this issue, we propose a novel position attention network (PAN) for ODISR in this paper. Specifically, a two-branch structure is introduced, in which the basic enhancement branch (BE) serves to achieve coarse deep feature enhancement for extracted shallow features. Meanwhile, the position attention enhancement branch (PAE) builds a positional attention mechanism to dynamically adjust the contribution of features at different latitudes in the ERP representation according to their positions and stretching degrees, which achieves the enhancement for the differentiated information, suppresses the redundant information, and modulate the deep features with spatial distortion. Subsequently, the features of two branches are fused effectively to achieve the further refinement and adapt the distortion characteristic of ODIs. After that, we exploit a long-term memory module (LM), promoting information interactions and fusions between the branches to enhance the perception of the distortion, aggregating the prior hierarchical features to keep the long-term memory and boosting the ODISR performance. Extensive results demonstrate the state-of-the-art performance and the high efficiency of our PAN in ODISR.

In medical diagnosis, relying on only one type of biomarker is insufficient to accurately identify cancer. Blood-based multicancer early detection can help identify more than one type of cancer from a single blood sample. In this study, a super-resolution multispectral imaging nanoimmunosensor (srMINI) based on three quantum dots (QDs) of different color conjugated with streptavidin was developed for the simultaneous screening of various cancer biomarkers in blood at the single-molecule level. In the experiment, the srMINI chip was used to simultaneously detect three key cancer biomarkers: carcinoembryonic antigen (CEA), C-reactive protein (CRP), and alpha-fetoprotein (AFP). The srMINI chip exhibited 108 times higher detection sensitivity of 0.18-0.5 ag/mL (1.1-2.6 zM) for these cancer biomarkers than commercial enzyme-linked immunosorbent assay kits because of the absence of interfering signals from the substrate, establishing considerable potential for multiplex detection of cancer biomarkers in blood. Therefore, the simultaneous detection of various cancer biomarkers using the developed srMINI chip with high diagnostic precision and accuracy is expected to play a decisive role in early diagnosis or community screening as a single-molecule biosensor.

Recently, multi-resolution pyramid-based techniques have emerged as the prevailing research approach for image super-resolution. However, these methods typically rely on a single mode of information transmission between levels. In our approach, a wavelet pyramid recursive neural network (WPRNN) based on wavelet energy entropy (WEE) constraint is proposed. This network transmits previous-level wavelet coefficients and additional shallow coefficient features to capture local details. Besides, the parameter of low- and high-frequency wavelet coefficients within each pyramid level and across pyramid levels is shared. A multi-resolution wavelet pyramid fusion (WPF) module is devised to facilitate information transfer across network pyramid levels. Additionally, a wavelet energy entropy loss is proposed to constrain the reconstruction of wavelet coefficients from the perspective of signal energy distribution. Finally, our method achieves the competitive reconstruction performance with the minimal parameters through an extensive series of experiments conducted on publicly available datasets, which demonstrates its practical utility.

Lysosomes are dynamic cellular structures that adaptively remodel their membrane in response to stimuli, including membrane damage. We previously uncovered a process we term LYTL (LYsosomal Tubulation/sorting driven by Leucine-Rich Repeat Kinase 2 [LRRK2]), wherein damaged lysosomes generate tubules sorted into mobile vesicles. LYTL is orchestrated by the Parkinson\'s disease-associated kinase LRRK2 that recruits the motor adaptor protein and RHD family member JIP4 to lysosomes via phosphorylated RAB proteins. To identify new players involved in LYTL, we performed unbiased proteomics on isolated lysosomes after LRRK2 kinase inhibition. Our results demonstrate that there is recruitment of RILPL1 to ruptured lysosomes via LRRK2 activity to promote phosphorylation of RAB proteins at the lysosomal surface. RILPL1, which is also a member of the RHD family, enhances the clustering of LRRK2-positive lysosomes in the perinuclear area and causes retraction of LYTL tubules, in contrast to JIP4 which promotes LYTL tubule extension. Mechanistically, RILPL1 binds to p150Glued, a dynactin subunit, facilitating the transport of lysosomes and tubules to the minus end of microtubules. Further characterization of the tubulation process revealed that LYTL tubules move along tyrosinated microtubules, with tubulin tyrosination proving essential for tubule elongation. In summary, our findings emphasize the dynamic regulation of LYTL tubules by two distinct RHD proteins and pRAB effectors, serving as opposing motor adaptor proteins: JIP4, promoting tubulation via kinesin, and RILPL1, facilitating tubule retraction through dynein/dynactin. We infer that the two opposing processes generate a metastable lysosomal membrane deformation that facilitates dynamic tubulation events.

With the introduction of deep learning, a significant amount of research has been conducted in the field of computer vision in the past decade. In particular, research on object detection (OD) continues to progress rapidly. However, despite these advances, some limitations need to be overcome to enable real-world applications of deep learning-based OD models. One such limitation is inaccurate OD when image quality is poor or a target object is small. The performance degradation phenomenon for small objects is similar to the fundamental limitations of an OD model, such as the constraint of the receptive field, which is a difficult problem to solve using only an OD model. Therefore, OD performance can be hindered by low image quality or small target objects. To address this issue, this study investigates the compatibility of super-resolution (SR) and OD techniques to improve detection, particularly for small objects. We analyze the combination of SR and OD models, classifying them based on architectural characteristics. The experimental results show a substantial improvement when integrating OD detectors with SR models. Overall, it was demonstrated that, when the evaluation metrics (PSNR, SSIM) of the SR models are high, the performance in OD is correspondingly high as well. Especially, evaluations on the MS COCO dataset reveal that the enhancement rate for small objects is 9.4% higher compared to all objects. This work provides an analysis of SR and OD model compatibility, demonstrating the potential benefits of their synergistic combination. The experimental code can be found on our GitHub repository.