Automatic medical image segmentation has made great progress owing to powerful deep representation learning. Inspired by the success of self-attention mechanism in transformer, considerable efforts ...are devoted to designing the robust variants of the encoder-decoder architecture with transformer. However, the patch division used in the existing transformer-based models usually ignores the pixel-level intrinsic structural features inside each patch. In this article, we propose a novel deep medical image segmentation framework called dual swin transformer U-Net (DS-TransUNet), which aims to incorporate the hierarchical swin transformer into both the encoder and the decoder of the standard U-shaped architecture. Our DS-TransUNet benefits from the self-attention computation in swin transformer and the designed dual-scale encoding, which can effectively model the non-local dependencies and multiscale contexts for enhancing the semantic segmentation quality of varying medical images. Unlike many prior transformer-based solutions, the proposed DS-TransUNet adopts a well-established dual-scale encoding mechanism that uses dual-scale encoders based on swin transformer to extract the coarse and fine-grained feature representations of different semantic scales. Meanwhile, a well-designed transformer interactive fusion (TIF) module is proposed to effectively perform multiscale information fusion through the self-attention mechanism. Furthermore, we introduce the swin transformer block into the decoder to further explore the long-range contextual information during the up-sampling process. Extensive experiments across four typical tasks for medical image segmentation demonstrate the effectiveness of DS-TransUNet, and our approach significantly outperforms the state-of-the-art methods.
Hollow periodic mesoporous organosilicas (PMOs) with molecularly homogeneous organic functional groups in the inorganic pore walls are attracting more and more attention due to the high surface ...areas, tunable pore sizes, low densities, large cavities in the center, permeable thin shells, and versatile organic–inorganic hybrid frameworks, which make them promising in a variety of applications including adsorption, catalysis, drug delivery, and nanotheranostics. Herein, recent advances in the synthesis of hollow PMO nanoparticles with various organic moieties are summarized, and the mechanism and new insights of synthesis approaches, including hard‐core templating methods, liquid‐interface assembly methods, and the interfacial reassembly and transformation strategy are discussed in‐depth. Meanwhile, the design principles, properties, and synthetic strategies for some smart hollow architectures such as multishelled hollow PMOs, yolk–shell structured PMOs, and nonspherical hollow PMOs are discussed. Moreover, the typical applications of hollow PMO nanomaterials as nanoreactors for chemical transformations and nanoplatforms for biomedicine are summarized. Finally, the challenges and prospects for the future development of hollow PMOs are described.
Hollow periodic mesoporous organosilica nanoparticles (PMOs) with unique organic–inorganic hybrid frameworks and well‐defined nanostructures attract significant attention. A comprehensive overview of the synthetic strategies and recent developments of hollow PMOs and their applications as nanoreactors for chemical transformations and nanoplatforms for biomedicine, along with future directions for the material design and synthesis, is presented.
Though most of the faces are axis-symmetrical objects, few real-world face images are axis-symmetrical images. In the past years, there are many studies on face recognition, but only little attention ...is paid to this issue and few studies to explore and exploit the axis-symmetrical property of faces for face recognition are conducted. In this paper, we take the axis-symmetrical nature of faces into consideration and design a framework to produce approximately axis-symmetrical virtual dictionary for enhancing the accuracy of face recognition. It is noteworthy that the novel algorithm to produce axis-symmetrically virtual face images is mathematically very tractable and quite easy to implement. Extensive experimental results demonstrate the superiority in face recognition of the virtual face images obtained using our method to the original face images. Moreover, experimental results on different databases also show that the proposed method can achieve satisfactory classification accuracy in comparison with state-of-the-art image preprocessing algorithms. The MATLAB code of the proposed method can be available at http://www.yongxu.org/lunwen.html.
•Developed a novel method to automatically produce approximately axis-symmetrical virtual face images.•Treated as an effective image preprocessing method.•Used as a virtual image dictionary learning method for image classification.•Extensive experiments on different face databases show its effectiveness as an image preprocessing algorithm.•The strong identification capability of our method is verified in comparison with state-of-the-art dictionary learning algorithms.
Display omitted
•Convenient in-situ preparation strategy of MgAl-LDH coatings on Mg was proposed.•The prepared superhydrophobic coating has long-lasting anti-corrosion performance.•The anti-corrosion ...mechanism of MgAl-LDH coatings modified by different long-chain molecules has been clarified.
Layered double hydroxides (LDHs) have been widely used as “smart” containers in the field of metal corrosion protection, and have broad industrial prospects. It is environmentally friendly and feasible to use aliphatic carboxylates and corresponding acids as substitutes for harmful corrosion inhibitors. However, previous studies rarely involved comparing the anti-corrosion mechanisms of different aliphatic acids modified on the LDH surface, and the durability of the prepared coatings also needs to be improved. In this work, MgAl-LDH laminates were grown in situ on AZ31 substrates by a hydrothermal method, and then modified by sodium laurate (SL) and sodium dodecylbenzene sulfonate (SDBS). Due to the physical barrier effect of the LDH layers, the spatial repulsion effect of the air film and the ion exchange reactions in the interlayer galleries, the functional coatings prepared exhibit smart and superior anti-corrosion performance on the magnesium substrates in 3.5 wt.% NaCl solution. Compared with LDH-SDBS-8 coating, the obtained superhydrophobic LDH-SL-8 coating shows more excellent long-term corrosion protection owing to the stronger intercalation capacity.
Contactless palmprint recognition has recently made significant progress in palm-scanning payment and social security. However, most existing methods are based on handcrafted kernels and are ...sensitive to illumination and scale variations. To address this problem, a competitive convolutional neural network (CompNet) with constrained learnable Gabor filters is proposed for contactless palmprint recognition. The proposed CompNet is built on multisize competitive blocks, which are applied to effectively exploit the rich direction ordering information of the palmprint patterns by means of the ad-hoc softmax and channel-wise convolution operations. Compared to the current deep neural networks, the backbone of the proposed network contains only very few parameters, making it quite easy to train, especially on small-scale datasets. Experimental results obtained on four popular contactless palmprint datasets demonstrate that the proposed CompNet achieves the lowest equal error rate compared to the most commonly used methods.
Background
MRI is the most commonly used imaging method for diagnosing anterior cruciate ligament (ACL) injuries. However, the interpretation of knee MRI is time‐intensive and depends on the clinical ...experience of the reader. An automated detection system based on a deep‐learning algorithm may improve interpretation time and reliability.
Purpose
To determine the feasibility of using a deep learning approach to detect ACL injuries within the knee joint on MRI.
Study Type
Retrospective.
Population
In all, 163 subjects with an ACL tear and 245 subjects with an intact ACL. There were 285, 81, and 42 volumes for training, validation, and test sets, respectively.
Field Strength/Sequence
2D sagittal proton density‐weighted spectral attenuated inversion recovery sequences at 1.5T and 3.0T.
Assessment
Based on the architecture of 3D DenseNet, we constructed a classification convolutional neural network. We tested this deep learning approach with different inputs and two other algorithms, including VGG16 and ResNet. Then we had both inexperienced radiologists and senior radiologists read the MR images.
Statistical Tests
Using arthroscopic results as the reference standard, the performance of three different inputs and three different algorithms, the residents and senior radiologists assessed the classification accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC).
Results
The accuracy, sensitivity, specificity, PPV, and NPV of our customized 3D deep learning architecture was 0.957, 0.976, 0.944, 0.940, and 0.976, respectively. The average AUCs were 0.946, 0.859, 0.960 for ResNet, VGG16, and our proposed network, respectively. The diagnostic accuracy of our model, residents, and senior radiologists was 0.957, 0.814, and 0.899, respectively.
Data Conclusion
Our study demonstrated the feasibility of using an automated deep‐learning‐based detection system to evaluate ACL injury.
Level of Evidence
3
Technical Efficacy Stage
1 J. MAGN. RESON. IMAGING 2020;52:1745–1752.
Palmprint processes a number of unique features for reliable personal recognition. However, different types of palmprint images contain different dominant features. Instead, only some features of the ...palmprint are visible in a palmprint image, whereas the other features may not be notable. For example, the low-resolution palmprint image has visible principal lines and wrinkles. By contrast, the high-resolution palmprint image contains clear ridge patterns and minutiae points. In addition, the three dimensional (3-D) palmprint image possesses curvatures of the palmprint surface. So far, there is no work to summarize the feature extraction of different types of palmprint images. In this paper, we have an aim to completely study the feature extraction and recognition of palmprint. We propose to use a unified framework to classify palmprint images into four categories: 1) the contact-based; 2) contactless; 3) high-resolution; and 4) 3-D palmprint images. Then, we analyze the motivations and theories of the representative extraction and matching methods for different types of palmprint images. Finally, we compare and test the state-of-the-art methods via the widely used palmprint databases, and point out some potential directions for future research.
Facial Expression Recognition (FER) is a long-standing but challenging research problem in computer vision. Existing approaches mainly focus on single-label emotional prediction, which cannot handle ...the complex multi-label FER task because of the coupling behavior of multiple emotions on a single facial image. To this end, in this paper, we propose a novel Self-supervised Exclusive-Inclusive Interactive Learning (SEIIL) method to facilitate discriminative multi-label FER in the wild, which can effectively handle the coupled multiple sentiments with limited unconstrained training data. Specifically, we construct an emotion disentangling module to capture the inclusive and exclusive characteristics of facial expressions, which can decouple the compound numerous emotions on an image. Moreover, an adaptively-weighted ensemble technique is conceived to aggregate category-level latent exclusive embeddings, and then a conditional adversarial interactive learning module is designed to fully leverage the complementary between the inclusive and formulated latent representations. Furthermore, to tackle the insufficient data for training, we introduce a self-supervised learning strategy to augment the amount and diversity of facial images, which can endow the model with advanced generalization ability. Under this strategy, the proposed two modules can be concurrently utilized in our SEIIL to jointly handle the coupled emotions and alleviate the overfitting problem. Extensive experimental results on six databases illustrate the superb performance of our method against state-of-the-art baselines.
SEE MATTAR ET AL DOI101093/AWW151 FOR A SCIENTIFIC COMMENTARY ON THIS ARTICLE: Functional brain networks demonstrate significant temporal variability and dynamic reconfiguration even in the resting ...state. Currently, most studies investigate temporal variability of brain networks at the scale of single (micro) or whole-brain (macro) connectivity. However, the mechanism underlying time-varying properties remains unclear, as the coupling between brain network variability and neural activity is not readily apparent when analysed at either micro or macroscales. We propose an intermediate (meso) scale analysis and characterize temporal variability of the functional architecture associated with a particular region. This yields a topography of variability that reflects the whole-brain and, most importantly, creates an analytical framework to establish the fundamental relationship between variability of regional functional architecture and its neural activity or structural connectivity. We find that temporal variability reflects the dynamical reconfiguration of a brain region into distinct functional modules at different times and may be indicative of brain flexibility and adaptability. Primary and unimodal sensory-motor cortices demonstrate low temporal variability, while transmodal areas, including heteromodal association areas and limbic system, demonstrate the high variability. In particular, regions with highest variability such as hippocampus/parahippocampus, inferior and middle temporal gyrus, olfactory gyrus and caudate are all related to learning, suggesting that the temporal variability may indicate the level of brain adaptability. With simultaneously recorded electroencephalography/functional magnetic resonance imaging and functional magnetic resonance imaging/diffusion tensor imaging data, we also find that variability of regional functional architecture is modulated by local blood oxygen level-dependent activity and α-band oscillation, and is governed by the ratio of intra- to inter-community structural connectivity. Application of the mesoscale variability measure to multicentre datasets of three mental disorders and matched controls involving 1180 subjects reveals that those regions demonstrating extreme, i.e. highest/lowest variability in controls are most liable to change in mental disorders. Specifically, we draw attention to the identification of diametrically opposing patterns of variability changes between schizophrenia and attention deficit hyperactivity disorder/autism. Regions of the default-mode network demonstrate lower variability in patients with schizophrenia, but high variability in patients with autism/attention deficit hyperactivity disorder, compared with respective controls. In contrast, subcortical regions, especially the thalamus, show higher variability in schizophrenia patients, but lower variability in patients with attention deficit hyperactivity disorder. The changes in variability of these regions are also closely related to symptom scores. Our work provides insights into the dynamic organization of the resting brain and how it changes in brain disorders. The nodal variability measure may also be potentially useful as a predictor for learning and neural rehabilitation.
Alleviation of tumor hypoxia has been the premise for improving the effectiveness of radiotherapy, which hinges upon the advanced delivery and rapid release of oxygen within the tumor region. Herein, ...we propose a “bubble-enhanced oxygen diffusion” strategy to achieve whole tumor oxygenation for significant radiation enhancement based on the “bystander effect”. Toward this end, sub-50 nm CuS-modified and 64Cu-labeled hollow mesoporous organosilica nanoparticles were constructed for tumor-specific delivery of O2-saturated perfluoropentane (PFP). Through the aid of PFP gasification arising from NIR laser-triggered mild hyperthermia, simultaneous PET/PA/US multimodality imaging and rapid oxygen diffusion across the tumor can be achieved for remarkable hypoxic radiosensitization. Furthermore, the multifunctional oxygen-carrying nanotheranostics also allow for other oxygen-dependent treatments, thus greatly advancing the development of bubble-enhanced synergistic therapy platforms.
PDF
