DE-UFormer: U-shaped dual encoder architectures for brain tumor segmentation.

Objective. In brain tumor segmentation tasks, the convolutional neural network (CNN) or transformer is usually acted as the encoder since the encoder is necessary to be used. On one hand, the convolution operation of CNN has advantages of extracting local information although its performance of obtaining global expressions is bad. On the other hand, the attention mechanism of the transformer is good at establishing remote dependencies while it is lacking in the ability to extract high-precision local information. Either high precision local information or global contextual information is crucial in brain tumor segmentation tasks. The aim of this paper is to propose a brain tumor segmentation model that can simultaneously extract and fuse high-precision local and global contextual information.Approach. We propose a network model DE-Uformer with dual encoders to obtain local features and global representations using both CNN encoder and Transformer encoder. On the basis of this, we further propose the nested encoder-aware feature fusion (NEaFF) module for effective deep fusion of the information under each dimension. It may establishe remote dependencies of features under a single encoder via the spatial attention Transformer. Meanwhile ,it also investigates how features extracted from two encoders are related with the cross-encoder attention transformer.Main results. The proposed algorithm segmentation have been performed on BraTS2020 dataset and private meningioma dataset. Results show that it is significantly better than current state-of-the-art brain tumor segmentation methods.Significance. The method proposed in this paper greatly improves the accuracy of brain tumor segmentation. This advancement helps healthcare professionals perform a more comprehensive analysis and assessment of brain tumors, thereby improving diagnostic accuracy and reliability. This fully automated brain model segmentation model with high accuracy is of great significance for critical decisions made by physicians in selecting treatment strategies and preoperative planning.

A Thermochromic Superhydrophobic Surface.

Highly enhanced solid-state thermochromism is observed in regioregular poly(3-hexylthiophene), P3HT, when deposited on a superhydrophobic polymer-SiO2 nanocomposite coating. The conformal P3HT coating on the nanocomposite surface does not alter or reduce superhydrophicity while maintaining its reversible enhanced thermochromism. The polymeric matrix of the superhydrophobic surface is comprised of a blend of poly(vinylidene fluoride-co-hexafluoropropylene) copolymer and an acrylic adhesive. Based on detailed X-ray diffraction measurements, this long-lasting, repeatable and hysteresis-free thermochromic effect is attributed to the enhancement of the Bragg peak associated with the d-spacing of interchain directional packing (100) which remains unaltered during several heating-cooling cycles. We propose that the superhydrophobic surface confines π-π interchain stacking in P3HT with uniform d-spacing into its nanostructured texture resulting in better packing and reduction in face-on orientation. The rapid response of the system to sudden temperature changes is also demonstrated by water droplet impact and bounce back on heated surfaces. This effect can be exploited for embedded thin film temperature sensors for metal coatings.

Depth discrimination of constant angular size stimuli in action space: role of accommodation and convergence cues.

In our daily life experience, the angular size of an object correlates with its distance from the observer, provided that the physical size of the object remains constant. In this work, we investigated depth perception in action space (i.e., beyond the arm reach), while keeping the angular size of the target object constant. This was achieved by increasing the physical size of the target object as its distance to the observer increased. To the best of our knowledge, this is the first time that a similar protocol has been tested in action space, for distances to the observer ranging from 1.4-2.4 m. We replicated the task in virtual and real environments and we found that the performance was significantly different between the two environments. In the real environment, all participants perceived the depth of the target object precisely. Whereas, in virtual reality (VR) the responses were significantly less precise, although, still above chance level in 16 of the 20 observers. The difference in the discriminability of the stimuli was likely due to different contributions of the convergence and the accommodation cues in the two environments. The values of Weber fractions estimated in our study were compared to those reported in previous studies in peripersonal and action space.