Motor imagery brain-computer interfaces (BCIs) have demonstrated great potential and attract world-spread attentions. Due to the nonstationary character of the motor imagery signals, costly and boring calibration sessions must be proceeded before use. This prevents them from going into our realistic life. In this paper, the source subject's data are explored to perform calibration for target subjects. Model trained on source subjects is transferred to work for target subjects, in which the critical problem to handle is the distribution shift. It is found that the performance of classification would be bad when only the marginal distributions of source and target are made closer, since the discriminative directions of the source and target domains may still be much different. In order to solve the problem, our idea comes that joint distribution adaptation is indispensable. It makes the classifier trained in the source domain perform well in the target domain. Specifically, a measure for joint distribution discrepancy (JDD) between the source and target is proposed. Experiments demonstrate that it can align source and target data according to the class they belong to. It has a direct relationship with classification accuracy and works well for transferring. Secondly, a deep neural network with joint distribution matching for zero-training motor imagery BCI is proposed. It explores both marginal and joint distribution adaptation to alleviate distribution discrepancy across subjects and obtain effective and generalized features in an aligned common space. Visualizations of intermediate layers illustrate how and why the network works well. Experiments on the two datasets prove the effectiveness and strength compared to outstanding counterparts.

As the value of blockchain has been widely recognized, more and more industries are proposing their blockchain solutions, including the rehabilitation medical industry. Blockchain can play a powerful role in the field of rehabilitation medicine, bringing a new research idea to the management of rehabilitation medical data. The electronic rehabilitation medical record (ERMR) contains rich data dimensions, which can provide comprehensive and accurate information for assessing the health of patients, thereby enhancing the effect of rehabilitation treatment. This paper analyzed the data characteristics of ERMR and the application requirements of blockchain in rehabilitation medicine. Based on the basic principles of blockchain, the technical advantages of blockchain used in ERMR sharing have been studied. In addition, this paper designed a blockchain-based ERMR sharing scheme in detail, using the specific technologies of blockchain such as hybrid P2P network, block-chain data structure, asymmetric encryption algorithm, digital signature, and Raft consensus algorithm to achieve distributed storage, data security, privacy protection, data consistency, data traceability, and data ownership in the process of ERMR sharing. The research results of this paper have important practical significance for realizing the safe and efficient sharing of ERMR, and can provide important technical references for the management of rehabilitation medical data with broad application prospects

Radiotherapy has become a common treatment option for head and neck (H&N) cancer, and organs at risk (OARs) need to be delineated to implement a high conformal dose distribution. Manual drawing of OARs is time consuming and inaccurate, so automatic drawing based on deep learning models has been proposed to accurately delineate the OARs. However, state-of-the-art performance usually requires a decent amount of delineation, but collecting pixel-level manual delineations is labor intensive and may not be necessary for representation learning. Encouraged by the recent progress in self-supervised learning, this study proposes and evaluates a novel multiview contrastive representation learning to boost the models from unlabelled data. The proposed learning architecture leverages three views of CTs (coronal, sagittal, and transverse plane) to collect positive and negative training samples. Specifically, a CT in 3D is first projected into three 2D views (coronal, sagittal, and transverse planes), then a convolutional neural network takes 3 views as inputs and outputs three individual representations in latent space, and finally, a contrastive loss is used to pull representation of different views of the same image closer (“positive pairs”) and push representations of views from different images (“negative pairs”) apart. To evaluate performance, we collected 220 CT images in H&N cancer patients. The experiment demonstrates that our method significantly improves quantitative performance over the state-of-the-art (from 83% to 86% in absolute Dice scores). Thus, our method provides a powerful and principled means to deal with the label-scarce problem.

Medical imaging technologies such as computed tomography (CT) and magnetic resonance imaging (MRI) imaging are indispensable for contemporary neurorehabilitation diagnostics, intervention, and monitoring. It would be desirable to reconstruct images from sparse measurements to reduce the ionizing radiation and motion artifacts. Although recent coordinate-based representation methods have shown promise advances for sparse-view reconstruction, they overfit a single MLP on a single patient. In this work, we generalize it across many patients by incorporating an interpatient prior into the ill-posed inverse/reconstruction problem, which is the missing ingredient in the previous works. The experiment demonstrates that our method significantly improves image quality over the state-of-the-art both qualitatively and quantitatively. Thus, our method provides a powerful and principled means to deal with the measurement-scarce problem.

In parallel with the rapid adoption of deep learning to multimedia data analysis, there has been growing awareness and concerns about data security and privacy. The recent advancement of federated learning enables many network clients to collaboratively train a model under the orchestration of a central server while preserving clients’ privacy. However, the standard assumption of independent and identical distribution (IID) may be broken under the federated learning because data label preferences may vary across clients. Recent efforts address this issue either by adapting a strong global model for each local model, respectively, or by training individual local models for similar clients together. However, both strategies degrade in highly non-IID scenarios. This work introduces a novel method, deep cooperative learning (DCL), to address this problem. It leverages the reciprocal structure between deep learning tasks in different clients to obtain effective feedback signals to enhance the learning process of personalized local models. To the best of our knowledge, this is the first time the non-IID is addressed under the principle of task interactions. We demonstrated the effectiveness of DCL on the two tasks of medical multimedia data analysis. The results show that our method presents a significant performance improvement compared with the standard federated learning method. In conclusion, this work developed a method for addressing non-IID problems in deep-learning-based privacy preservation learning. It allows the highly non-IID data to be used to improve the local model performance.

Thecurrent practice in intensity-modulated radiation therapy (IMRT) planning almost always includes different dose calculation strategies for plan optimization and final dose verification. The accurate Monte Carlo (MC) dose algorithm is considered to be time-consuming for the optimization. Thus a fast, simplified dose algorithm is used in the optimization. The significant differences between the optimized dose and the delivered dose lead to tediously planning loops and potentially suboptimal solutions. This work aims to develop an IMRT optimization algorithm to minimize the dose discrepancy so that the delivered dose can be optimized in a holistic, end-to-end manner. Methods: The proposed algorithm, namely NeuralDAO, integrates a neural dose network into the column generation (CG) direct aperture optimization (DAO) formulation for step-and-shoot IMRT planning. The neural dose network is designed and trained to produce doses of MC-level accuracy within few milliseconds. Its differentiability is fully exploited to compute gradients for identifying potential aperture shapes. A prototype of NeuralDAO was developed in PyTorch and available to the public. Five lung patient cases have been studied. Dosimetric accuracy was compared with the MC dose. Plan quality and time were compared with a state-of -the-art (SoA) dose-correct algorithm. Statistical analysis was performed by Wilcoxon signed-rank test. Results:The average gamma passing rate at 2 mm/2% is 99.7% between the optimized and delivered doses. The convergence process produced by Neural-DAO is virtually identical to that produced by an MC-based DAO. The average dose calculation time is 12.1 ms for an aperture on GPU. One session of optimization took 10-36 min. Compared with the SoA, better conformity index and homogeneity index were observed for the target. The esophagus was significantly spared. Significant reductions were observed for the replanning number and the planning time. Conclusions: A new DAO algorithm based on the neural dose network has been developed. The results suggest that this algorithm minimizes the discrepancy between the optimized and delivered doses, which offers a promising approach to reduce the time and effort required in IMRT planning. This work demonstrates the possibility of applying the neural network in IMRT optimization. It is of great potential to extend this algorithm to other treatment modalities.