Shuxin Yang

Automatic chest radiology report generation is critical in clinics which can relieve experienced radiologists from the heavy workload and remind inexperienced radiologists of misdiagnosis or missed diagnose. Existing approaches mainly formulate chest radiology report generation as an image captioning task and adopt the encoder-decoder framework. However, in the medical domain, such pure data-driven approaches suffer from the following problems: 1) visual and textual bias problem; 2) lack of expert knowledge. In this paper, we propose a knowledge-enhanced radiology report generation approach introduces two types of medical knowledge: 1) General knowledge, which is input independent and provides the broad knowledge for report generation; 2) Specific knowledge, which is input dependent and provides the fine-grained knowledge for chest X-ray report generation. To fully utilize both the general and specific knowledge, we also propose a knowledge-enhanced multi-head attention mechanism. By merging the visual features of the radiology image with general knowledge and specific knowledge, the proposed model can improve the quality of generated reports. The experimental results on the publicly available IU-Xray dataset show that the proposed knowledge-enhanced approach outperforms state-of-the-art methods in almost all metrics. And the results of MIMIC-CXR dataset show that the proposed knowledge-enhanced approach is on par with state-of-the-art methods. Ablation studies also demonstrate that both general and specific knowledge can help to improve the performance of chest radiology report generation.

In clinics, a radiology report is crucial for guiding a patient's treatment. However, writing radiology reports is a heavy burden for radiologists. To this end, we present an automatic, multi-modal approach for report generation from a chest x-ray. Our approach, motivated by the observation that the descriptions in radiology reports are highly correlated with specific information of the x-ray images, features two distinct modules: (i) Learned knowledge base: To absorb the knowledge embedded in the radiology reports, we build a knowledge base that can automatically distill and restore medical knowledge from textual embedding without manual labor; (ii) Multi-modal alignment: to promote the semantic alignment among reports, disease labels, and images, we explicitly utilize textual embedding to guide the learning of the visual feature space. We evaluate the performance of the proposed model using metrics from both natural language generation and clinic efficacy on the public IU-Xray and MIMIC-CXR datasets. Our ablation study shows that each module contributes to improving the quality of generated reports. Furthermore, the assistance of both modules, our approach outperforms state-of-the-art methods over almost all the metrics. Code is available at https://github.com/LX-doctorAI1/M2KT.

Intrusion detection ensures that IoT can protect itself against malicious intrusions in extensive and intricate network traffic data. In recent years, deep learning has been extensively and effectively employed in IoT intrusion detection. However, the limited computing power and storage space of IoT devices restrict the feasibility of deploying resource-intensive intrusion detection systems on them. This article introduces the DL-BiLSTM lightweight IoT intrusion detection model. By combining deep neural networks (DNNs) and bidirectional long short-term memory networks (BiLSTMs), the model enables nonlinear and bidirectional long-distance feature extraction of complex network information. This capability allows the system to capture complex patterns and behaviors related to cyber-attacks, thus enhancing detection performance. To address the resource constraints of IoT devices, the model utilizes the incremental principal component analysis (IPCA) algorithm for feature dimensionality reduction. Additionally, dynamic quantization is employed to trim the specified cell structure of the model, thereby reducing the computational burden on IoT devices while preserving accurate detection capability. The experimental results on the benchmark datasets CIC IDS2017, N-BaIoT, and CICIoT2023 demonstrate that DL-BiLSTM surpasses traditional deep learning models and cutting-edge detection techniques in terms of detection performance, while maintaining a lower model complexity.

Host pathways mediating changes in immune states elicited by intestinal microbial colonization are incompletely characterized. Here we describe alterations of the host immune state induced by colonization of germ-free zebrafish larvae with an intestinal microbial community or single bacterial species. We show that microbiota-induced changes in intestinal leukocyte subsets and whole-body host gene expression are dependent on the innate immune adaptor gene myd88. Similar patterns of gene expression are elicited by colonization with conventional microbiome, as well as mono-colonization with two different zebrafish commensal bacterial strains. By studying loss-of-function myd88 mutants, we find that colonization suppresses Myd88 at the mRNA level. Tlr2 is essential for microbiota-induced effects on myd88 transcription and intestinal immune cell composition.

Type 2 diabetes, obesity, and metabolic syndrome are pathologies where insulin resistance plays a central role, and that affect a large population worldwide. These pathologies are usually associated with a dysregulation of insulin secretion leading to a chronic exposure of the tissues to high insulin levels (i.e. hyperinsulinemia), which diminishes the concentration of key downstream elements, causing insulin resistance. The complexity of the study of insulin resistance arises from the heterogeneity of the metabolic states where it is observed. To contribute to the understanding of the mechanisms triggering insulin resistance, we have developed a zebrafish model to study insulin metabolism and its associated disorders. Zebrafish larvae appeared to be sensitive to human recombinant insulin, becoming insulin-resistant when exposed to a high dose of the hormone. Moreover RNA-seq-based transcriptomic profiling of these larvae revealed a strong downregulation of a number of immune-relevant genes as a consequence of the exposure to hyperinsulinemia. Interestingly, as an exception, the negative immune modulator protein tyrosine phosphatase nonreceptor type 6 (ptpn6) appeared to be upregulated in insulin-resistant larvae. Knockdown of ptpn6 was found to counteract the observed downregulation of the immune system and insulin signaling pathway caused by hyperinsulinemia. These results indicate that ptpn6 is a mediator of the metabolic switch between insulin-sensitive and insulin-resistant states. Our zebrafish model for hyperinsulinemia has therefore demonstrated its suitability for discovery of novel regulators of insulin resistance. In addition, our data will be very useful in further studies of the function of immunological determinants in a non-obese model system.