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.

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.

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.