Junjie Hu

Objective. To develop and validate UNetrDose, a Transformer-based deep learning model designed for fast and accurate photon beamlet dose prediction. The study aims to achieve Monte Carlo (MC)-level dosimetric accuracy using only CT-derived electron density images and beamlet coordinates as input, enabling the efficient reconstruction of complete 3D dose distributions for intensity-modulated radiation therapy (IMRT) plans. Approach. For each beamlet, a fixed-size 3D image patch was extracted along its propagation path, centered on the beamlet trajectory. The geometric information, defined as the beamlet’s relative position within the beam field, was used alongside the image patch as model input. The ground-truth dose distributions were generated using MC simulations. The proposed UNetrDose model combined convolutional layers for local feature extraction with Transformer modules to capture long-range dependencies. A total of 90 fixed-beam IMRT plans (51 esophageal and 39 rectal cases) were used for model training, validation, and testing. Model performance was comprehensively assessed, evaluating spatial accuracy with 3D gamma pass rates and clinical acceptability through dose-volume histogram comparisons and other dosimetric parameters. Main results. UNetrDose demonstrated high fundamental accuracy at the individual beamlet level, where pass rates for the stringent γ (1 mm, 1%) criterion exceeded 96% for both esophageal and rectal cases. This translated to excellent clinical performance on full IMRT plans, where the model achieved mean γ (2 mm, 2%) pass rates ranging from 97.06 ± 2.05 % for esophageal cases to 98.75 ± 0.78 % for rectal cases. The model was also highly efficient, with an average inference time of approximately 28 ms per beamlet. Significance. UNetrDose offers a promising alternative to traditional dose calculation engines by providing a balance between high dosimetric accuracy and fast computation. Its ability to predict dose distributions using only electron density images and beamlet positions simplifies the workflow, making it highly applicable for time-sensitive clinical scenarios.

Mangrove ecosystems are recognized for their exceptional carbon sequestration potential and crucial contribution to coastal ecological balance. However, the sharp decline in mangrove area necessitates efficient monitoring via remote sensing. While Deep Neural Networks (DNNs) have excelled in segmentation tasks, their robustness remains inadequate. This limitation stems from the lack of theoretical guarantees regarding the continuity of layer-by-layer discrete transformations, rendering models susceptible not only to man-made adversarial attacks but also to natural degradations. To address these vulnerabilities, this paper leverages Neural Ordinary Differential Equations (NODEs) to enhance the robustness of mangrove segmentation. We designed and integrated various NODE architectures, including a novel NODE-SE-Block inspired by adaptive feature recalibration, to achieve more stable feature representations. Crucially, our findings reveal that by employing an adversarial training framework based on known attacks, the NODE-integrated network demonstrates superior cross-domain robustness. It not only defends against malicious exploits but also exhibits significantly enhanced resilience toward natural degradations, such as Gaussian noise and sensor-induced artifacts. Experimental results on mangrove datasets verify that the proposed methodology provides a reliable and interference-resistant foundation for ecological management in mission-critical scenarios.

Micro-expression recognition (MER) reveals genuine emotions and is widely applied in fields such as depression detection and clinical psychological assessment. However, due to the short duration, low intensity of muscle movements, and small affected facial regions of micro-expressions (MEs), MER presents significant challenges. Despite recent advancements in neural network that have improved the performance of MER, existing network models still exhibit limitations owing to issues such as the small-scale of MEs datasets, insufficient training data, and class imbalance. In MER, the optical flow features reflect subtle changes in muscle movements between consecutive frames in video segments, the AUs are closely related to subtle changes in facial expressions, and the combinations of different AUs can reflect different facial expressions.We propose a novel framework called the AU-guided three-stream fusion network (AUTONet). The proposed framework constructs three subnetworks, one pre-trained on a large-scale image dataset and one shallow CNN, are used for extracting optical flow features, and another CNN based on the AUs intensity matrix is used for extracting AUs during MEs occurrences. The fusion module within the framework effectively utilizes the complementarity of multimodal features by creating a composite feature vector, thereby achieving better performance in MER. In addition, an AU-guided gaussian enhancement module guided by AUs is designed in the framework, which selectively enhances key regions in the optical flow using the position information of AUs. The experimental results indicate that AUTONet exhibits excellent performance on CASME II and SAMM datasets. Meanwhile, its low computational complexity and robustness to four types of perturbations show the practical viability in real-world conditions. Our work provides a promising direction for the combination of optical flow and AUs in MER.

Inverse treatment planning is pivotal in tumor treatment planning. It enables the multi-objective optimization of radiation dose delivery, ensuring precise tumor targeting while sparing surrounding healthy tissues. This process often requires frequent parameter adjustments to achieve the desired balance between objectives, making it both labor-intensive and time-consuming. Deep reinforcement learning (DRL) provides an automated, model-based planning solution, aimed at reducing reliance on human expertise and enhancing the efficiency of objective parameter optimization. However, most current approaches apply DRL to inverse planning without fully leveraging the knowledge embedded in the continuous state–action space, defined by the coupling between nonstationary planning states and continuous decision variables. This may result in insufficient exploration and exploitation, leading to inefficient optimization. This work introduces an innovative action-guided DRL (AgDRL) approach for automatic inverse planning. Our goal is to enhance exploration and exploitation by leveraging insightful guidance from reward-guided actions. The implementation of AgDRL incorporates both exploitation and exploration in the action–state space. For exploitation, high-reward actions are employed as guidance to achieve the optimal action adjustment. For exploration, low-reward actions are recommended as training resets to explore a broader range of the latent state space. Quantitative and qualitative experiments are conducted in various settings to evaluate the proposed method. The results are assessed using DRL-related metrics (e.g. reward gains) and clinical-related measurements (e.g. dose–volume histograms, DVHs). Experimental results on a real-world rectal cancer dataset empirically demonstrate that the proposed AgDRL-based approach significantly improves optimization efficiency through a high-reward strategy while enhancing exploration diversity via a low-reward strategy, consistently outperforming the MatRad treatment planning optimization platform.