Medical imaging denoising faces great challenges, yet is in great demand. With its distinctive characteristics, medical imaging denoising in the image domain requires innovative deep learning strategies. In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily. A medical image denoising pipeline based on the CNCL strategy is presented, and is implemented as a generative adversarial network, where various representative networks (including U-Net, DnCNN, and SRDenseNet) are investigated as the predictors. The performance of these implemented models has been validated on medical imaging datasets including CT, MR, and PET. The results show that this strategy outperforms state-of-the-art denoising algorithms in terms of visual quality and quantitative metrics, and the strategy demonstrates a robust generalization capability. These findings validate that this simple yet effective strategy demonstrates promising potential for medical image denoising tasks, which could exert a clinical impact in the future. Code is available at: https://github.com/gengmufeng/CNCL-denoising .

Optical coherence tomography (OCT) is susceptible to the coherent noise, which is the speckle noise that deteriorates contrast and the detail structural information of OCT images, thus imposing significant limitations on the diagnostic capability of OCT. In this paper, we propose a novel OCT image denoising method by using an end-to-end deep learning network with a perceptually-sensitive loss function. The method has been validated on OCT images acquired from healthy volunteers’ eyes. The label images for training and evaluating OCT denoising deep learning models are images generated by averaging 50 frames of respective registered B-scans acquired from a region with scans occurring in one direction. The results showed that the new approach can outperform other related denoising methods on the aspects of preserving detail structure information of retinal layers and improving the perceptual metrics in the human visual perception.

In this study, a series of hybrid membranes with high separation performance and superior swelling-resistance were fabricated by incorporating metal ion-chelated dopamine nanoaggregates into a poly(dimethylsiloxane) (PDMS) bulk matrix membrane. The concomitant hydrogen bond, metal-organic coordination and π-complexation interactions render the synergy of a favorable free volume property, reinforced chain rigidity and facilitated transport function within the membranes. The membranes displayed simultaneously enhanced permeation flux and enrichment factors when utilized for model gasoline separation. Especially, when the weight fraction of dopamine/Cu reached 5.0 wt%, the membrane displayed an optimum separation performance with a permeation flux of 7.42 kg m⁻² h⁻¹ (2.7 times as much as that of the PDMS control membrane) and an enrichment factor of 4.81 (11% more than that of the PDMS control membrane). Thanks to the elevated cohesive energy and the chain extension effect, the swelling degree of the PDMS-dopamine/Cu membranes decreased remarkably with the dopamine/Cu content. This study may provide a novel route to the design and fabrication of robust, high-performance hybrid membranes to meet diverse energy and environment-related application requirements.

Nanozymes that mimic natural enzyme–like activities have gradually emerged in cancer therapy. To overcome the bottlenecks of single-mode nanozymes, including “off-target” toxicity and ineffectiveness toward metastatic cancers, we designed magnetic nanoparticle–based multifunctional visualized immunomodulatory nanozymes. Besides the partial initiation of the prime immune response by intrinsic immunogenicity, as a smart drug delivery system with a temperature- and pH-sensitive dual response to the tumor microenvironment, these nanozymes released immune agonists to boost enhanced systemic immune response, eventually ameliorating the cancer immune microenvironment through many aspects: activating dendritic cells, improving the function of CD8 ⁺ T cells, and decreasing the population of myeloid-derived suppressor cells, which inhibited both primary and metastatic cancers. Mechanistically, these nanozymes regulated the reactive oxygen species–related Akt signaling pathway and consequently activated cell apoptosis–related signaling pathways, which provided a deeper understanding of the synergistic mechanism of multifunctional nanozymes. Our findings offer a promising imaging-guided cocktail therapy strategy through immunomodulatory nanozymes.