Objective. Radiotherapy planning requires significant expertise to balance tumor control and organ-at-risk (OAR) sparing. Automated planning can improve both efficiency and quality. This study introduces GPT-Plan, a novel multi-agent system powered by the GPT-4 family of large language models (LLMs), for automating the iterative radiotherapy plan optimization. Approach. GPT-Plan uses LLM-driven agents, mimicking the collaborative clinical workflow of a dosimetrist and physicist, to iteratively generate and evaluate text-based radiotherapy plans based on predefined criteria. Supporting tools assist the agents by leveraging historical plans, mitigating LLM hallucinations, and balancing exploration and exploitation. Performance was evaluated on 12 lung (IMRT) and 5 cervical (VMAT) cancer cases, benchmarked against the ECHO auto-planning method and manual plans. The impact of historical plan retrieval on efficiency was also assessed. Results. For IMRT lung cancer cases, GPT-Plan generated high-quality plans, demonstrating superior target coverage and homogeneity compared to ECHO while maintaining comparable or better OAR sparing. For VMAT cervical cancer cases, plan quality was comparable to a senior physicist and consistently superior to a junior physicist, particularly for OAR sparing. Retrieving historical plans significantly reduced the number of required optimization iterations for lung cases (p < 0.01) and yielded iteration counts comparable to those of the senior physicist for cervical cases (p = 0.313). Occasional LLM hallucinations have been mitigated by self-reflection mechanisms. One limitation was the inaccuracy of vision-based LLMs in interpreting dose images. Significance. This pioneering study demonstrates the feasibility of automating radiotherapy planning using LLM-powered agents for complex treatment decision-making tasks. While challenges remain in addressing LLM limitations, ongoing advancements hold potential for further refining and expanding GPT-Plan’s capabilities.

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.

Objective. Deep learning has shown promise in generating synthetic CT (sCT) from magnetic resonance imaging (MRI). However, the misalignment between MRIs and CTs has not been adequately addressed, leading to reduced prediction accuracy and potential harm to patients due to the generative adversarial network (GAN)hallucination phenomenon. This work proposes a novel approach to mitigate misalignment and improve sCT generation. Approach. Our approach has two stages: iterative refinement and knowledge distillation. First, we iteratively refine registration and synthesis by leveraging their complementary nature. In each iteration, we register CT to the sCT from the previous iteration, generating a more aligned deformed CT (dCT). We train a new model on the refined 〈dCT, MRI〉 pairs to enhance synthesis. Second, we distill knowledge by creating a target CT (tCT) that combines sCT and dCT images from the previous iterations. This further improves alignment beyond the individual sCT and dCT images. We train a new model with the 〈tCT, MRI〉 pairs to transfer insights from multiple models into this final knowledgeable model. Main results. Our method outperformed conditional GANs on 48 head and neck cancer patients. It reduced hallucinations and improved accuracy in geometry (3% ↑ Dice), intensity (16.7% ↓ MAE), and dosimetry (1% ↑ γ _3%3mm ). It also achieved <1% relative dose difference for specific dose volume histogram points. Significance. This pioneering approach for addressing misalignment shows promising performance in MRI-to-CT synthesis for MRI-only planning. It could be applied to other modalities like cone beam computed tomography and tasks such as organ contouring.

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.

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.