Automated interpretation and reporting of chest X-rays (CXRs) hold significant promise in reducing diagnostic errors and supporting radiologists under heavy clinical workloads. However, existing methods typically rely on global visual features and token-level supervision, limiting their sensitivity to subtle abnormalities and reducing their clinical reliability. To address these challenges, we present Reflective X-ray Network (RefleXNet), which systematically integrates multi-scale visual feature fusion and anatomical relational reasoning with a targeted self-reflective learning strategy. RefleXNet first constructs multi-scale visual representations and captures anatomical context through graph-based relational modeling. Building upon these representations, we introduce a targeted self-reflection strategy that uses clinically guided feedback from generated reports to selectively refine abnormality predictions and their associated region-level visual features. Extensive experiments on MIMIC-CXR demonstrate that RefleXNet consistently outperforms state-of-the-art baselines across clinical factual correctness metrics. Notably, our compact 3B-parameter model surpasses several recent models with over twice the parameter count. Additionally, RefleXNet exhibits strong generalization performance in zero-shot evaluations on IU-Xray compared with leading multimodal language models, highlighting its robustness and clinical effectiveness.

Automated chest X-ray report generation requires not only clinical accuracy but also transparent and interpretable diagnostic reasoning. In this work, we propose FiR-Rad, a two-stage framework that combines explicit structured reasoning with targeted fine-grained optimization. In the first stage, a supervised chain-of-thought approach guides the model to sequentially analyze and describe a comprehensive range of clinically significant thoracic abnormalities, ensuring clinically meaningful coverage. In the second stage, we introduce a segment-level reinforcement learning strategy based on Group Relative Policy Optimization (GRPO), which assigns precise rewards to each disease-specific reasoning step by evaluating the accuracy of corresponding findings in the synthesized report. This design provides direct feedback for intermediate reasoning and encourages consistency between detailed abnormality analysis and final diagnostic conclusions. Experimental results on the MIMIC-CXR and IU-Xray datasets demonstrate that our framework achieves state-of-the-art performance across clinical and linguistic metrics, with strong zero-shot generalization on IU-Xray. The proposed method significantly enhances interpretability and clinical accuracy, effectively addressing key limitations in automated radiology report generation.

Medical AI has achieved strong predictive performance, yet most systems remain limited by shallow reasoning, poor transparency, and weak generalisation in safety-critical settings. Neurosymbolic AI offers a path beyond these constraints by combining neural models' ability to learn from complex clinical data with the explicit structure, logic, and domain knowledge of symbolic methods. This article examines how neurosymbolic approaches can address core challenges in healthcare AI through five key areas: hybrid reasoning that unifies learning and logic; symbol grounding that links internal representations to clinically meaningful concepts; clinical interpretability that exposes reasoning steps; human-integrated decision-making that keeps clinicians in control; and knowledge-driven diagnosis that incorporates guidelines, ontologies, and causal understanding. Together, these elements outline how neurosymbolic AI can support systems that are not only accurate but also transparent, clinically aligned, and robust in complex or data-sparse scenarios. Advancing this paradigm will require collaboration across AI research, clinical practice, and knowledge engineering, as well as governance mechanisms that ensure fairness and accountability. Neurosymbolic AI thus represents a promising direction for building trustworthy, knowledge-rich intelligence in healthcare.

Medical report generation refers to the automatic creation of accurate and coherent diagnostic reports for medical images. This task can alleviate the workload of radiologists, enhance the efficiency of disease diagnosis, and therefore holds significant value and challenges. Considering the feature differences between different modalities, existing methods primarily focus on facilitating medical report generation through cross-modal alignment of images and texts. However, since medical images are very similar to each other, it is difficult to tag obvious objects, making most methods limited to coarse-grained image-text global alignment. In this paper, we propose a medical report generation model based on adaptive topic learning and fine-grained cross-modal alignment, which aligns images and texts from medical topic perspective and token perspective. From the medical topic perspective, a global-local contrastive loss is introduced to adaptively learn efficient medical topic features, and medical topics are utilized to map images and texts to the same semantic space for fine-grained alignment. From the token perspective, a token prediction module is designed to enable the model to focus on important local information by predicting the key tokens contained in the report. Experimental results on the two public datasets (i.e. IU-Xray and MIMIC-CXR) demonstrate that our proposed model outperforms state-of-the-art baselines.

Radiological Report Summarization (RRS) involves automated summarization of key impressions derived from identified findings, intending to alleviate the workload and stress experienced by radiologists. Many existing RRS methods predominantly concentrate on summarizing findings, neglecting crucial clinical context, such as the patient’s previous medical examinations. This context, which is a focal point for radiologists, plays a critical role in producing comprehensive and accurate impressions. This paper endeavors to emulate the workflows of radiologists by incorporating the patient’s clinical context alongside current findings. To achieve this, we reconceptualize RRS as a conversational question-answering task, generating temporal radiological conversations. These conversations are subsequently employed to fine-tune a large chat model. The resulting radiology chatbot, RadChat, demonstrates superior performance in RRS task, showcasing the potential of integrating clinical context for more accurate impressions. Experimental results conducted on the MIMIC-CXR dataset validate the superiority of RadChat in comparison to state-of-the-art baselines.

Medical report generation aims at automating the synthesis of accurate and comprehensive diagnostic reports from radiological images. The task can significantly enhance clinical decision-making and alleviate the workload on radiologists. Existing works normally generate reports from single chest radiographs, although historical examination data also serve as crucial references for radiologists in real-world clinical settings. To address this constraint, we introduce a novel framework that mimics the workflow of radiologists. This framework compares past and present patient images to monitor disease progression and incorporates prior diagnostic reports as references for generating current personalized reports. We tackle the textual diversity challenge in cross-modal tasks by promoting style-agnostic discrete report representation learning and token generation. Furthermore, we propose a novel spatio-temporal fusion method with multi-granularities to fuse textual and visual features by disentangling the differences between current and historical data. We also tackle token generation biases, which arise from long-tail frequency distributions, proposing a novel feature normalization technique. This technique ensures unbiased generation for tokens, whether they are frequent or infrequent, enabling the robustness of report generation for rare diseases. Experimental results on the two public datasets demonstrate that our proposed model outperforms state-of-the-art baselines.

Medical report generation is a valuable and challenging task, which automatically generates accurate and fluent diagnostic reports for medical images, reducing workload of radiologists and improving efficiency of disease diagnosis. Fine-grained alignment of medical images and reports facilitates the exploration of close correlations between images and texts, which is crucial for cross-modal generation. However, visual and linguistic biases caused by radiologists' writing styles make cross-modal image-text alignment difficult. To alleviate visual-linguistic bias, this paper discretizes medical reports and introduces an intermediate modality, i.e. phrasebook, consisting of key noun phrases. As discretized representation of medical reports, phrasebook contains both disease-related medical terms, and synonymous phrases representing different writing styles which can identify synonymous sentences, thereby promoting fine-grained alignment between images and reports. In this paper, an augmented two-stage medical report generation model with phrasebook (PhraseAug) is developed, which combines medical images, clinical histories and writing styles to generate diagnostic reports. In the first stage, phrasebook is used to extract semantically relevant important features and predict key phrases contained in the report. In the second stage, medical reports are generated according to the predicted key phrases which contain synonymous phrases, promoting our model to adapt to different writing styles and generating diverse medical reports. Experimental results on two public datasets, IU-Xray and MIMIC-CXR, demonstrate that our proposed PhraseAug outperforms state-of-the-art baselines.

Temporal knowledge graphs (TKGs) extrapolation reasoning predicts future events based on historical information, which has great research significance and broad application value.Existing methods can be divided into embeddingbased methods and logical rule-based methods.Embedding-based methods rely on learned entity and relation embeddings to make predictions and thus lack interpretability.Logical rule-based methods bring scalability problems due to being limited by the learned logical rules.We combine the two methods to capture deep causal logic by learning rule embeddings, and propose an interpretable model for temporal knowledge graph reasoning called adaptive logical rule embedding model for inductive reasoning (ALRE-IR).ALRE-IR can adaptively extract and assess reasons contained in historical events, and make predictions based on causal logic.Furthermore, we propose a one-class augmented matching loss for optimization.When evaluated on ICEWS14, ICEWS0515 and ICEWS18 datasets, the performance of ALRE-IR outperforms other stateof-the-art baselines.The results also demonstrate that ALRE-IR still shows outstanding performance when transferred to related dataset with common relation vocabulary, indicating our proposed model has good zero-shot reasoning ability. 1

A new classification logic for land cover at regional scale is proposed. The critical features of this classification are that: it is based on spectrum (color) and primary attributes of plant-canopy structure, that are important to globe change modeling and can be measured in the field for validation or/and by remote sensing; according to the phonological difference among broadly defined vegetation, some typical land cover is easily distinguished by using the characteristics of land cover with the change of seasons; mixed land cover is differentiated by its constituent characteristics and influence on land surface processes. A first test of this logic for the middle Qinling mountains in Shanxi province, China is presented based on time-series MODIS 250 m NDVI imageries. Seven basic classes and eleven sub-classes were identified and mapped for the study area. The overall classification accuracy equals to 74.41% and overall kappa statistics 66.65%.

Spatial reference unification is the foundation of "3S" integration project and is also complicated. This paper proposes and designs scheme for coordinate unification according to constitute of multi-source data and system requirements in digital tobacco "3S" monitoring project, then solves the two problem: WGS84 datum transformation with local datum and SAR image calibration with other spatial data in research area. The result proves that the scheme satisfies the precision requirement of this project which makes good preparation for the following monitoring work.

Monitoring of tobacco planted acreage is a very important step for tobacco's management and monitoring. The paper presents a monitoring method by data fusion of multiple remote sensing sources. It extracts tobacco areas according to the NDVI value and classifies the fusion image with texture information, then classifies the SAR data to acquire tobacco plot in cloudy area. After classification post-processing and manual interpretation, the classification precise satisfies the demand. Applied results are in good agreement with the theoretical study, which shows its effectiveness and applicability.