Constantly optimized mean teacher for semi-supervised 3D MRI image segmentation.

The mean teacher model and its variants, as important methods in semi-supervised learning, have demonstrated promising performance in magnetic resonance imaging (MRI) data segmentation. However, the superior performance of teacher model through exponential moving average (EMA) is limited by the unreliability of unlabeled image, resulting in potentially unreliable predictions. In this paper, we propose a framework to optimized the teacher model with reliable expert-annotated data while preserving the advantages of EMA. To avoid the tight coupling that results from EMA, we leverage data augmentations to provide two distinct perspectives for the teacher and student models. The teacher model adopts weak data augmentation to provide supervision for the student model and optimizes itself with real annotations, while the student uses strong data augmentation to avoid overfitting on noise information. In addition, double softmax helps the model resist noise and continue learning meaningful information from the images, which is a key component in the proposed model. Extensive experiments show that the proposed method exhibits competitive performance on the Left Atrium segmentation MRI dataset (LA) and the Brain Tumor Segmentation MRI dataset (BraTS2019). For the LA dataset, we achieved a dice of 91.02% using only 20% labeled data, which is close to the dice of 91.14% obtained by the supervised approach using 100% labeled data. For the BraTs2019 dataset, the proposed method achieved 1.02% and 1.92% improvement on 5% and 10% labeled data, respectively, compared to the best baseline method on this dataset. This study demonstrates that the proposed model can be a potential candidate for medical image segmentation in semi-supervised learning scenario.

A transformer-based deep neural network model for SSVEP classification.

Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signals in the brain-computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data becomes urgent. In recent years, developing the methods that can work in inter-subject scenario has become a promising new direction. As a popular deep learning model nowadays, Transformer has been used in EEG signal classification tasks owing to its excellent performance. Therefore, in this study, we proposed a deep learning model for SSVEP classification based on Transformer architecture in inter-subject scenario, termed as SSVEPformer, which was the first application of Transformer on the SSVEP classification. Inspired by previous studies, we adopted the complex spectrum features of SSVEP data as the model input, which could enable the model to simultaneously explore the spectral and spatial information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) was proposed to improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12 targets; Dataset 2: 35 subjects, 40 targets). The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate than other baseline methods. The proposed models validate the feasibility of deep learning models based on Transformer architecture for SSVEP data classification, and could serve as potential models to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.

An efficient CNN-LSTM network with spectral normalization and label smoothing technologies for SSVEP frequency recognition.

Objective. Steady-state visual evoked potentials (SSVEPs) based brain-computer interface (BCI) has received great interests owing to the high information transfer rate and available large number of targets. However, the performance of frequency recognition methods heavily depends on the amount of the calibration data for intra-subject classification. Some research adopted the deep learning (DL) algorithm to conduct the inter-subject classification, which could reduce the calculation procedure, but the performance still has large room to improve compared with the intra-subject classification.Approach. To address these issues, we proposed an efficient SSVEP DL NETwork (termed SSVEPNET) based on one-dimensional convolution and long short-term memory (LSTM) module. To enhance the performance of SSVEPNET, we adopted the spectral normalization and label smoothing technologies during implementing the network architecture. We evaluated the SSVEPNET and compared it with other methods for the intra- and inter-subject classification under different conditions, i.e. two datasets, two time-window lengths (1 s and 0.5 s), three sizes of training data.Main results. Under all the experimental settings, the proposed SSVEPNET achieved the highest average accuracy for the intra- and inter-subject classification on the two SSVEP datasets, when compared with other traditional and DL baseline methods.Significance. The extensive experimental results demonstrate that the proposed DL model holds promise to enhance frequency recognition performance in SSVEP-based BCIs. Besides, the mixed network structures with convolutional neural network and LSTM, and the spectral normalization and label smoothing could be useful optimization strategies to design efficient models for electroencephalography data.

A double-network strategy for the tough tissue adhesion of hydrogels with long-term stability under physiological environment.

Achieving tough and stable tissue adhesion under a physiological environment is of great significance for the clinical applications of hydrogel adhesives. The current tough hydrogel adhesives face challenges in the preservation of the maximal adhesion for a long time due to swelling. Here, we propose a double-network strategy for tough tissue adhesion by a hydrogel with long-term stability under a physiological environment. A double-network hydrogel consisting of a covalently crosslinked primary network with tunable hydrophilicity and a non-covalently crosslinked secondary network with functional groups is designed. The primary network exhibited hydrophobicity in the physiological environment, which could constrict the secondary network and limit the swelling of the entire hydrogel. The secondary network could form strong interlinks with tissue and provide large energy dissipation through the unzipping of its noncovalent crosslinks when separated by a force. The combination of the two networks resulted in a tough and stable tissue adhesion. A poly(N-isopropylacrylamide)/calcium alginate hydrogel synthesized based on this strategy realized an adhesion energy of 300-500 J m-2 with porcine tissues, and the maximal adhesion could be maintained for over 1000 min after submerging in a PBS solution at 37 °C. The swelling behavior of the hydrogel and changes in mechanical properties under the physiological environment are studied, and its application in repairing the aorta wound is demonstrated.

Hydrogel-mesh composite for wound closure.

During operations, surgical mesh is commonly fixed on tissues through fasteners such as sutures and staples. Attributes of surgical mesh include biocompatibility, flexibility, strength, and permeability, but sutures and staples may cause stress concentration and tissue damage. Here, we show that the functions of surgical mesh can be significantly broadened by developing a family of materials called hydrogel-mesh composites (HMCs). The HMCs retain all the attributes of surgical mesh and add one more: adhesion to tissues. We fabricate an HMC by soaking a surgical mesh with a precursor, and upon cure, the precursor forms a polymer network of a hydrogel, in macrotopological entanglement with the fibers of the surgical mesh. In a surgery, the HMC is pressed onto a tissue, and the polymers in the hydrogel form covalent bonds with the tissue. To demonstrate the concept, we use a poly(N-isopropylacrylamide) (PNIPAAm)/chitosan hydrogel and a polyethylene terephthalate (PET) surgical mesh. In the presence a bioconjugation agent, the chitosan and the tissue form covalent bonds, and the adhesion energy reaches above 100 J⋅m-2 At body temperature, PNIPAAm becomes hydrophobic, so that the hydrogel does not swell and the adhesion is stable. Compared with sutured surgical mesh, the HMC distributes force over a large area. In vitro experiments are conducted to study the application of HMCs to wound closure, especially on tissues under high mechanical stress. The performance of HMCs on dynamic living tissues is further investigated in the surgery of a sheep.