Medical image segmentation is an essential prerequisite for developing healthcare systems, especially for disease diagnosis and treatment planning. On various medical image segmentation tasks, the ushaped architecture, also known as U-Net, has become the de-facto standard and achieved tremendous success. However, due to the intrinsic locality of convolution operations, U-Net generally demonstrates limitations in explicitly modeling long-range dependency. Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures with innate global self-attention mechanisms, but can result in limited localization abilities due to insufficient low-level details. In this paper, we propose TransUNet, which merits both Transformers and U-Net, as a strong alternative for medical image segmentation. On one hand, the Transformer encodes tokenized image patches from a convolution neural network (CNN) feature map as the input sequence for extracting global contexts. On the other hand, the decoder upsamples the encoded features which are then combined with the high-resolution CNN feature maps to enable precise localization. We argue that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information. TransUNet achieves superior performances to various competing methods on different medical applications including multi-organ segmentation and cardiac segmentation. Code and models are available at https://github.com/Beckschen/ TransUNet.
In multi-organ segmentation of abdominal CT scans, most existing fully supervised deep learning algorithms require lots of voxel-wise annotations, which are usually difficult, expensive, and slow to obtain. In comparison, massive unlabeled 3D CT volumes are usually easily accessible. Current mainstream works to address semi-supervised biomedical image segmentation problem are mostly graphbased. By contrast, deep network based semi-supervised learning methods have not drawn much attention in this field. In this work, we propose Deep Multi-Planar Co-Training (DMPCT), whose contributions can be divided into two folds: 1) The deep model is learned in a co-training style which can mine consensus information from multiple planes like the sagittal, coronal, and axial planes; 2) Multiplanar fusion is applied to generate more reliable pseudolabels, which alleviates the errors occurring in the pseudolabels and thus can help to train better segmentation networks. Experiments are done on our newly collected large dataset with 100 unlabeled cases as well as 210 labeled cases where 16 anatomical structures are manually annotated by four radiologists and confirmed by a senior expert. The results suggest that DMPCT significantly outperforms the fully supervised method by more than 4% especially when only a small set of annotations is used.
Keratins play critical roles in intermediate filament formation, inflammatory responses and cellular signaling in epithelium. While keratins is a major epidermal fluorophore, the mechanisms underlying the autofluorescence (AF) of keratins and its biomedical implications have remained unknown. Our study used mouse skin as a model to study these topics,showing that UV dose-dependently induced increases in green AF at the spinous layer of the epidermis of mouse within 6 hr of the UV exposures, which may be used for non-invasive prediction of UV-induced skin damage. The UV-induced AF appears to be induced by cysteine protease-mediated keratin 1 proteolysis: 1) UV rapidly induced significant keratin 1 degradation; 2) administration of keratin 1 siRNA largely decreased the UV-induced AF; and 3) administration of E-64, a cysteine protease inhibitor, significantly attenuated the UV-induced AF and keratin 1 degradation. Our study has also suggested that the UV-induced keratin 1 proteolysis may be a novel crucial pathological factor in UV-induced skin damage, which is supported by both the findings that indicate critical biological roles of keratin 1 in epithelium and our observation that prevention of UV-induced keratin 1 proteolysis can lead to decreased UV-induced skin damage. Collectively, our study has suggested that UV-induced keratin 1 proteolysis may be a novel and valuable target for diagnosis, prevention and treatment of UV-induced skin damage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.