Medical image analysis tasks are characterized by high-noise, volumetric, and multi-modality, posing challenges for the model that attempts to learn robust features from the input images. Over the last decade, deep neural networks (DNNs) have achieved enormous success in medical image analysis tasks, which can be attributed to their powerful feature representation capability. Despite the promising results reported in numerous literature, DNNs are also criticized for several pivotal limits, with one of the limitations is lack of safety. Safety plays an important role in the applications of DNNs during clinical practice, helping the model defend against potential attacks and preventing the model from silent failure prediction. The recently proposed neural ordinary differential equation (NODE), a continuous model bridging the gap between DNNs and ODE, provides a significant advantage in ensuring the model’s safety. Among the variants of NODE, the neural memory ordinary differential equation (nmODE) owns the global attractor theoretically, exhibiting superiority in prompting the model’s performance and robustness during applications. While NODE and its variants have been widely used in medical image analysis tasks, there is a lack of a comprehensive review of their applications, hindering the in-depth understanding of NODE’s working principle and its potential applications. To mitigate this limitation, this paper thoroughly reviews the literature on the applications of NODE in medical image analysis from the following five aspects: segmentation, reconstruction, registration, disease prediction, and data generation. We also summarize both the strengths and downsides of the applications of NODE, followed by the possible research directions. To the best of our knowledge, this is the first review regards the applications of NODE in the field of medical image analysis. We hope this review can draw the researchers’ attention to the great potential of NODE and its variants in medical image analysis.

As the development of the Internet of Things (IoT) continues, Federated Learning (FL) is gaining popularity as a distributed machine learning framework that does not compromise the data privacy of each participant. However, the data held by enterprises and factories in the IoT often have different distribution properties (Non-IID), leading to poor results in their federated learning. This problem causes clients to forget about global knowledge during their local training phase and then tends to slow convergence and degrades accuracy. In this work, we propose a method named FedRAD, which is based on relational knowledge distillation that further enhances the mining of high-quality global knowledge by local models from a higher-dimensional perspective during their local training phase to better retain global knowledge and avoid forgetting. At the same time, we devise an entropy-wise adaptive weights module (EWAW) to better regulate the proportion of loss in single-sample knowledge distillation versus relational knowledge distillation so that students can weigh losses based on predicted entropy and learn global knowledge more effectively. A series of experiments on CIFAR10 and CIFAR100 show that FedRAD has better performance in terms of convergence speed and classification accuracy compared to other advanced FL methods.

Data have become an important asset. Mining the value contained in personal data, making personal data an exchangeable commodity, has become a hot spot of industry research. Then, how to price personal data reasonably becomes a problem we have to face. Based on previous research on data provenance, this paper proposes a novel minimum provenance pricing method, which is to price the minimum source tuple set that contributes to the query. Our pricing model first sets prices for source tuples according to their importance and then makes query pricing based on data provenance, which considers both the importance of the data itself and the relationships between the data. We design an exact algorithm that can calculate the exact price of a query in exponential complexity. Furthermore, we design an easy approximate algorithm, which can calculate the approximate price of the query in polynomial time. We instantiated our model with a select-joint query and a complex query and extensively evaluated its performances on two practical datasets. The experimental results show that our pricing model is feasible.

The widespread acceptance of data sharing has promoted the relevant research in both academia and industry. “Data sharing” is the process of interchanging data among multiple data sources in a controllable access manner. Any such system provides common functionality of storage and access; however, there are prominent differences in non-functionalities, such as self-control, transparency, cost-effectiveness, incentive, and auditing, which make data sharing in a dilemma. In this paper, we propose a distributed data sharing model based on blockchain technology: data owner publishes data with an additional control policy; data consumer inquires data with an access request; and consensus nodes evaluate the request and make decisions. After formalizing the system model, we discuss the procedure of data sharing, reputation management, and proposed solution. With the access control policy, price compensation, and reputation management mechanism, we achieve self-control and price balance in sharing data. Our model is equally a closed-loop control system that acts as a regulator of supervising its participants. The analyses and experimental results show, comparing with the existing sharing systems, that our model is practical and can spur agents to participate actively in sharing data.

Massive open online courses (MOOCs) represent an innovative online learning paradigm that has garnered considerable popularity in recent years, attracting a multitude of learners to MOOC platforms due to their accessible and adaptable instructional structure. However, the elevated dropout rate in current MOOCs limits their advancement. Current dropout prediction models predominantly employ fixed-size convolutional kernels for feature extraction, which insufficiently address temporal dependencies and consequently demonstrate specific limitations. We propose a Lie Group-based feature context-local fusion attention model for predicting dropout in MOOCs. This model initially extracts shallow features using Lie Group machine learning techniques and subsequently integrates multiple parallel dilated convolutional modules to acquire high-level semantic representations. We design an attention mechanism that integrates contextual and local features, effectively capturing the temporal dependencies in the study behaviors of learners. We performed multiple experiments on the XuetangX dataset to evaluate the model’s efficacy. The results show that our method attains a precision score of 0.910, exceeding the previous state-of-the-art approach by 3.3%.