Clinical reinforcement learning (RL) holds promise for treatment recommendation but remains hindered by black-box decision processes, limited safety guarantees, and lack of individualized reasoning. We introduce Delphi Engine, the first fully trainable neuro-symbolic causal RL framework for dynamic treatment planning, designed to answer three core clinical questions in real time: Why this action? Why is it safe? Why for this patient? Specifically, Delphi integrates: (1) causality-aware state modeling using discretized physiological variables and subtype-specific causal graphs; (2) adaptive symbolic rule constraints, combining clinical guidelines and behavior-derived rules into soft differentiable logic; and (3) interpretable decision fusion, where actions are selected based on joint neural-symbolic Q-values and explained via structured LLM-based justifications. We evaluate Delphi on the MIMIC-III sepsis cohort using both standard off-policy evaluations (WIS↑1.47, DR↑1.29, RMSE↓0.207) and the first blinded physician evaluation of an explainable RL system in healthcare. Delphi consistently outperforms historical physicians' treatments in safety (+10.4%), understandability (+8.9%), and adoption rate (+5.75%) across six clinical axes. These results highlight Delphi’s potential as a safe, interpretable, and patient-specific AI assistant for critical care medicine.

Atopic dermatitis (AD) is a chronic inflammatory skin disorder characterized by recurrent itching, erythema, dryness, and eczematous lesions. Automated AD severity assessment is crucial for cost-effective and precision clinical decision-making but remains challenging. This is due to the subtle contrast variations between key dermatological signs and significant variations in lesion sizes across patients and disease stages. To address these issues, we propose ADSA-Net, which is designed to handle both intra- and inter-class variabilities. ADSA-Net first extracts multi-scale texture-aware features to effectively model variations in lesion size and texture. It then leverages contrastive learning to enhance intra- and inter-class differentiation, strengthening model's discriminatory ability for samples that are difficult to distinguish. Finally, ADSA-Net refines the learning process by leveraging a dynamic feature pool of correctly classified samples to guide the calibration of misclassified instances, enhancing overall accuracy. We further establish a dataset for AD severity assessment. Comprehensive experiments on this dataset show that ADSA-Net significantly outperforms existing state-of-the-art methods.

As the first satellite specifically designed to serve Sustainable Development Goals (SDGs), the Sustainable Development Science Satellite 1 (SDGSAT-1) has attracted numerous attention by providing panchromatic glimmer imagery with a unprecedented clarity of 10 meters. However, unsatisfactory positional accuracy of glimmer imagery hinder further fine-grained studies. This study identifies the cause of these positional errors as misalignments generated during the data production process, and thus proposes a correction method based on deep learning object detection and cross-correlation. The method achieves accurate measurements of the position, direction, and distance of the misalignment, which are used to correct the glimmer imagery and to effectively improve the positional accuracy. In this study, we (1) propose a simulated misalignment dataset which demonstrated with excellent performance during the training of multiple deep learning object detection models, reaching up to 99.44% average precision (AP); (2) propose pixel brightness correlation coefficient based on cross-correlation and validate its effectiveness to characterize misalignments; (3) improve detection efficiency by the threshold design of window average brightness and object detection confidence; (4) explore the reasons for the misalignment suggests that it is the difference between the satellite’s designed operating time and the actual operating time that leads to the Charge-coupled Device(CCD) stitching flaw. Our proposed method can contribute to evaluating and improving the positional accuracy of SDGSAT-1 panchromatic glimmer imagery, providing a way to obtain datasets with good spatial consistency and to conduct related research.

Online state-time trajectory planning in highly dynamic environments remains an unsolved problem due to the curse of dimensionality of the state-time space. Existing state-time planners are typically implemented based on randomized sampling approaches or path searching on discrete graphs. The smoothness, path clearance, or planning efficiency is sometimes not satisfying. In this work, we propose a gradient-based planner on the state-time space for online trajectory generation in highly dynamic environments. To enable the gradient-based optimization, we propose a Timed-ESDT that supports distance and gradient queries with state-time keys. Based on the Timed-ESDT, we also define a smooth prior and an obstacle likelihood function that are compatible with the state-time space. The trajectory planning is then formulated to a MAP problem and solved by an efficient numerical optimizer. Moreover, to improve the optimality of the planner, we also define a state-time graph and conduct path searching on it to find a better initialization for the optimizer. By integrating the graph searching, the planning quality is significantly improved. Experiments on simulated and benchmark datasets demonstrate the superior performance of our proposes method over conventional ones.

Human activities are hugely restricted by COVID-19, recently. Robots that can conduct inter-floor navigation attract much public attention since they can substitute human workers to conduct the service work. However, current robots either depend on human assistance or elevator retrofitting, and fully autonomous inter-floor navigation is still not available. As the very first step of inter-floor navigation, elevator button segmentation and recognition hold an important position. Therefore, we release the first large-scale publicly available elevator panel dataset in this work, containing 3,718 panel images with 35,100 button labels, to facilitate more powerful algorithms on autonomous elevator operation. Together with the dataset, a number of deep learning based implementations for button segmentation and recognition are also released to benchmark future methods in the community. The dataset is available at https://github.com/zhudelong/elevator_button_recognition

Metastatic involvement of lymph nodes is one of the most important prognostic variables for many cancers. Several deep learning based algorithms have been developed to segment metastatic regions in pathological images to help predict prognosis. However, the training of these methods requires a large amount of annotated data, and the labeling task is an extremely time-consuming process for human annotators. In order to reduce the annotation burden, we for the first time propose a semi-automatic annotation method (PiPo-Net) for the labeling of pathological images. The method is comprised of two subnetworks, a pixel-wise segmentation network (Pi-Net) and a polygon-based annotation network (Po-Net). The Pi-Net adopts an improved encoder-decoder architecture and can effectively aggregate multi-scale image features. The Po-Net is built on the Pi-Net and leverages a two-layer recurrent neural network to generate tight-bounded polygons for the metastatic regions. Corresponding to the proposed network architecture, a loss function called PiPo-loss is introduced to help optimize the whole network. The main advantage of our method is that it integrates human annotators into the prediction loop, allowing to iteratively refine the predictions according to the suggestions from human annotators. We evaluate our method on Camelyon16 database and achieve a Dice score of 91% in the initial annotation attempt. We also demonstrate the effectiveness of the human-network collaborative annotation, which achieves promising labeling results, verifying the advantages of our proposed method.

Multiple instance learning (MIL) is a typical weakly-supervised learning method where the label is associated with a bag of instances instead of a single instance. Despite extensive research over past years, effectively deploying MIL remains an open and challenging problem, especially when the commonly assumed standard multiple instance (SMI) assumption is not satisfied. In this paper, we propose a multiple instance learning method based on deep graph convolutional network and feature selection (FS-GCN-MIL) for histopathological image classification. The proposed method consists of three components, including instance-level feature extraction, instance-level feature selection, and bag-level classification. We develop a self-supervised learning mechanism to train the feature extractor based on a combination model of variational autoencoder and generative adversarial network (VAE-GAN). Additionally, we propose a novel instance-level feature selection method to select the discriminative instance features. Furthermore, we employ a graph convolutional network (GCN) for learning the bag-level representation and then performing the classification. We apply the proposed method in the prediction of lymph node metastasis using histopathological images of colorectal cancer. Experimental results demonstrate that the proposed method achieves superior performance compared to the state-of-the-art methods.