TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers.

Medical image segmentation is crucial for healthcare, yet convolution-based methods like U-Net face limitations in modeling long-range dependencies. To address this, Transformers designed for sequence-to-sequence predictions have been integrated into medical image segmentation. However, a comprehensive understanding of Transformers' self-attention in U-Net components is lacking. TransUNet, first introduced in 2021, is widely recognized as one of the first models to integrate Transformer into medical image analysis. In this study, we present the versatile framework of TransUNet that encapsulates Transformers' self-attention into two key modules: (1) a Transformer encoder tokenizing image patches from a convolution neural network (CNN) feature map, facilitating global context extraction, and (2) a Transformer decoder refining candidate regions through cross-attention between proposals and U-Net features. These modules can be flexibly inserted into the U-Net backbone, resulting in three configurations: Encoder-only, Decoder-only, and Encoder+Decoder. TransUNet provides a library encompassing both 2D and 3D implementations, enabling users to easily tailor the chosen architecture. Our findings highlight the encoder's efficacy in modeling interactions among multiple abdominal organs and the decoder's strength in handling small targets like tumors. It excels in diverse medical applications, such as multi-organ segmentation, pancreatic tumor segmentation, and hepatic vessel segmentation. Notably, our TransUNet achieves a significant average Dice improvement of 1.06% and 4.30% for multi-organ segmentation and pancreatic tumor segmentation, respectively, when compared to the highly competitive nn-UNet, and surpasses the top-1 solution in the BrasTS2021 challenge. 2D/3D Code and models are available at https://github.com/Beckschen/TransUNet and https://github.com/Beckschen/TransUNet-3D, respectively.

Hair Derived Microneedle Patches for Both Diabetic Foot Ulcer Prevention and Healing.

The large amount of reactive oxygen species (ROS) produced by high glucose metabolism in diabetic patients not only induces inflammation but also damages blood vessels, finally resulting in low limb temperature, and the high glucose environment in diabetic patients also makes them susceptible to bacterial infection. Therefore, diabetic foot ulcer (DFU) usually presents as a nonhealing wound. To efficaciously prevent and treat DFU, we proposed a near-infrared (NIR) responsive microneedle (MN) patch hierarchical microparticle (HMP)-ZnO-MN-vascular endothelial growth factor and basic fibroblast growth factor (H-Z-MN-VEGF&bFGF), which could deliver drugs to the limbs painlessly, accurately, and controllably under NIR irradiation. Therein, the hair-derived HMPs exhibited the capacity of scavenging ROS, thereby preventing damage to the blood vessels. Meanwhile, zinc oxide (ZnO) nanoparticles endowed the MN patch with excellent antibacterial activity which could be further enhanced with the photothermal effect of HMPs under NIR irradiation. Moreover, vascular endothelial growth factor and basic fibroblast growth factor could promote the angiogenesis. A series of experiments proved that the MN patch exhibited broad-spectrum antibacterial and anti-inflammatory capacities. In vivo, it obviously increased the temperature of fingertips in diabetic rats as well as promoted collagen deposition and angiogenesis during wound healing. In conclusion, this therapeutic platform provides a promising method for the prevention and treatment of DFU.

Self-Deliverable Peptide-Mediated and Reactive-Oxygen-Species-Amplified Therapeutic Nanoplatform for Highly Effective Bacterial Inhibition.

An "antibiotic-free strategy" provides a viable option to address bacterial infections, especially for the "superbug" challenge. However, the undesirable antibacterial activity of antibiotic-free agents hinders their practical applications. In this study, we developed a combination antibacterial strategy of coupling peptide-drug therapy with chemodynamic therapy (CDT) to achieve the effective bacterial inhibition. An amphiphilic oligopeptide (LAOOH-OPA) containing a therapeutic unit of D(KLAK)2 peptide and a hydrophobic linoleic acid hydroperoxide (LAHP) was designed. The positively charged D(KLAK)2 peptide with an α-helical conformation enabled rapid binding with microbial cells via electrostatic interaction and subsequent membrane insertion to deactivate the bacterial membrane. When triggered by Fe2+, moreover, LAHP could generate singlet oxygen (1O2) to elicit lipid bilayer leakage for enhanced bacteria inhibition. In vitro assays demonstrated that the combination strategy possessed excellent antimicrobial activity not only merely toward susceptible strains (Gram-positive Staphylococcus aureus and Gram-negative Escherichia coli) but also toward methicillin-resistant Staphylococcus aureus (MRSA). On the mouse skin abscess model induced by S. aureus, self-assembled LAOOH-OPA exhibited a more significant bacteria reduction (1.4 log10 reduction) in the bioburden compared to that of the standard vancomycin (0.9 log10 reduction) without apparent systemic side effects. This combination antibacterial strategy shows great potential for effective bacterial inhibition.

Experimental and Numerical Analysis on the Impact Wear Behavior of TP316H Steel.

In this work, the contact force model and experiment methods were used to study the dynamic response and impact wear behavior of TP316H steel. The Flore model and the classic Hertz model were selected for comparison with the experimental results, and the model was revised according to the section parameters of the TP316H tube. The results show that there is a large difference between the models without considering the effect of structural stiffness on the impact system and the test results, whereas the revised model has a good agreement. With the rise in impact mass, the coefficient of restitution increases from 0.65 to 0.78, whereas the energy dissipation and wear volume decrease. Spalling, delamination, plastic deformation, and oxidative wear are the main impact wear mechanism of TP316H steel.

Infection-activated lipopeptide nanotherapeutics with adaptable geometrical morphology for in vivo bacterial ablation.

The nonselective membrane disruption of antimicrobial peptides (AMPs) helps in combating the antibacterial resistance. But their overall positive charges lead to undesirable hemolysis and toxicity toward normal living cells, as well as the rapid clearance from blood circulation. In consequence, developing smart AMPs to optimize the antimicrobial outcomes is highly urgent. Relying on the local acidity of microbial infection sites, in this work, we designed an acidity-triggered charge reversal nanotherapeutics with adaptable geometrical morphology for bacterial targeting and optimized therapy. C16-A3K4-CONH2 was proposed and the ε-amino groups in lysine residues were acylated by dimethylmaleic amide (DMA), enabling the generated C16-A3K4(DMA)-CONH2 to self-assemble into negatively charged spherical nanostructure, which relieved the protein adsorption and prolonged blood circulation in vivo. After the access of C16-A3K4(DMA)-CONH2 into the microbial infection sites, acid-sensitive ß-carboxylic amide would hydrolyze to regenerate the positive C16-A3K4-CONH2 to destabilize the negatively charged bacterial membrane. In the meanwhile, attractively, the self-assembled spherical nanoparticle transformed to rod-like nanostructure, which was in favor of the efficient binding with bacterial membranes due to the larger contact area. Our results showed that the acid-activated AMP nanotherapeutics exhibited strong and broad-spectrum antimicrobial activities against Yeast, Gram-positive Staphylococcus aureus, Gram-negative Escherichia coli, and methicillin-resistant Staphylococcus aureus (MRSA). Moreover, the biocompatible lipopeptide nanotherapeutics dramatically improved the dermapostasis caused by bacterial infection. The strategy of merging pathology-activated therapeutic function and morphological adaptation to augment therapeutic outcomes shows the great potential for bacterial inhibition. STATEMENT OF SIGNIFICANCE: The overall positive charges of antimicrobial peptides (AMPs) lead to undesirable hemolysis and nonselective toxicity, as well as the rapid clearance from blood circulation. Infection-activated lipopeptide nanotherapeutics with adaptable geometrical morphology were developed to address these issues. The self-assembled lipopeptide was pre-decorated to reverse the positive charge to reduce the hemolysis and nonselective cytotoxicity. After accessing the acidic infection sites, the nanotherapeutics recovered the positive charge to destabilize negatively charged bacterial membranes. Meanwhile, the morphology of self-assembled nanotherapeutics transformed from spherical nanoparticles to rod-like nanostructures in the lesion site, facilitating the improved association with bacterial membranes to boost the therapeutic efficiency. These results provide new design rationale for AMPs developed for bacterial inhibition.

Recurrent Saliency Transformation Network for Tiny Target Segmentation in Abdominal CT Scans.

We aim at segmenting a wide variety of organs, including tiny targets (e.g., adrenal gland), and neoplasms (e.g., pancreatic cyst), from abdominal CT scans. This is a challenging task in two aspects. First, some organs (e.g., the pancreas), are highly variable in both anatomy and geometry, and thus very difficult to depict. Second, the neoplasms often vary a lot in its size, shape, as well as its location within the organ. Third, the targets (organs and neoplasms) can be considerably small compared to the human body, and so standard deep networks for segmentation are often less sensitive to these targets and thus predict less accurately especially around their boundaries. In this paper, we present an end-to-end framework named recurrent saliency transformation network (RSTN) for segmenting tiny and/or variable targets. The RSTN is a coarse-to-fine approach that uses prediction from the first (coarse) stage to shrink the input region for the second (fine) stage. A saliency transformation module is inserted between these two stages so that 1) the coarse-scaled segmentation mask can be transferred as spatial weights and applied to the fine stage and 2) the gradients can be back-propagated from the loss layer to the entire network so that the two stages are optimized in a joint manner. In the testing stage, we perform segmentation iteratively to improve accuracy. In this extended journal paper, we allow a gradual optimization to improve the stability of the RSTN, and introduce a hierarchical version named H-RSTN to segment tiny and variable neoplasms such as pancreatic cysts. Experiments are performed on several CT datasets including a public pancreas segmentation dataset, our own multi-organ dataset, and a cystic pancreas dataset. In all these cases, the RSTN outperforms the baseline (a stage-wise coarse-to-fine approach) significantly. Confirmed by the radiologists in our team, these promising segmentation results can help early diagnosis of pancreatic cancer. The code and pre-trained models of our project were made available at https://github.com/198808xc/OrganSegRSTN.

Mussel-Inspired Adhesive Polydopamine-Functionalized Hyaluronic Acid Hydrogel with Potential Bacterial Inhibition.

Hyaluronic acid (HA)-based hydrogels have been receiving increasing attention for wound management. However, pure HA hydrogels usually exhibit weak mechanical strength and poor anti-infection. Herein, a hybrid HA-based hydrogel (PDA-HA) comprised of polydopamine (PDA) and thiolated hyaluronic acid (HA-SH) is developed based on the Michael addition reaction. The introduction of PDA into HA hydrogel can decrease the critical gel concentration, improve the cell affinity and tissue adhesion, as well as endow the hydrogel with efficient free-radical scavenging ability. Combining the merits of good biocompatibility and moist environment from HA hydrogel with excellent tissue adhesiveness and free radical scavenging capability from PDA, this cross-linked PDA-HA hybrid hydrogel exhibits great potential for creating antimicrobial wound medical dressings.

In Situ Electrochemical Synthesis of Novel Lithium-Rich Organic Cathodes for All-Organic Li-Ion Full Batteries.

The lithium-rich organic cathodes are undoubtedly important for fabricating lithium-ion (Li-ion) full batteries. Currently, very few lithium-rich organic cathodes have been reported for their O2-sensitive characteristics. In this article, we initially propose a new electrochemical method to in situ synthesize a novel lithium-rich organic cathode, namely lithium anthracene-9,10-bis[2-benzene-1,4-bis(olate)] (ABB4OLi, CT = 256 mA h g-1), from its phenol precursor of anthracene-9,10-bis(2-benzene-1,4-diol). The addition of anthracene moiety as the linking bridge is to increase the molecular weight and simultaneously enhance the electronic conductivity for the designed organic molecule (ABB4OLi). In Li-ion half cells, ABB4OLi could deliver average specific capacities of 194 mA h g-1 during 250 cycles (50 mA g-1) and 100 mA h g-1 during 400 cycles (2 A g-1). In the all-organic Li-ion full cells with the working voltage above 1 V, the ABB4OLi electrode could realize the average capacities of 70 mA h g-1cathode during 200 cycles (50 mA g-1). This work has forwarded a significant step for the development of organic Li-ion full batteries.

Highly Stable and High Rate-Performance Na-Ion Batteries Using Polyanionic Anthraquinone as the Organic Cathode.

Sodium 9,10-anthraquinone-2,6-disulfonate (Na2 AQ26DS), with polyanionic character and two O-Na ionic bonds, is found to be a highly stable organic cathode in Na-ion batteries, delivering capacities of approximately 120 mAh g-1 for 300 cycles (50 mA g-1 ) and around 99 mAh g-1 for 1000 cycles (1 A g-1 ). These results are the best performance reported to date for small-molecule, anthraquinone-based organic cathodes in Li-, Na-, or K-ion batteries.