OBJECTIVES: We propose a Contrastive Regional Attention and Prior Knowledge-Infused U-Transformer model (CRAKUT) to address the challenges of imbalanced text distribution, lack of contextual clinical knowledge, and cross-modal information transformation to enhance the quality of generated radiology reports. METHODS: The CRAKUT model comprises 3 key components, including an image encoder that utilizes common normal images from the dataset for extracting enhanced visual features, an external knowledge infuser that incorporates clinical prior knowledge, and a U-Transformer that facilitates cross-modal information conversion from vision to language. The contrastive regional attention in the image encoder was introduced to enhance the features of abnormal regions by emphasizing the difference between normal and abnormal semantic features. Additionally, the clinical prior knowledge infuser within the text encoder integrates clinical history and knowledge graphs generated by ChatGPT. Finally, the U-Transformer was utilized to connect the multi-modal encoder and the report decoder in a U-connection schema, and multiple types of information were used to fuse and obtain the final report. RESULTS: We evaluated the proposed CRAKUT model on two publicly available CXR datasets (IU-Xray and MIMIC-CXR). The experimental results showed that the CRAKUT model achieved a state-of-the-art performance on report generation with a BLEU-4 score of 0.159, a ROUGE-L score of 0.353, and a CIDEr score of 0.500 in MIMIC-CXR dataset; the model also had a METEOR score of 0.258 in IU-Xray dataset, outperforming all the comparison models. CONCLUSIONS The proposed method has great potential for application in clinical disease diagnoses and report generation.
Humans ; Radiology Information Systems ; Radiology

Objective To establish a portable gas chromatography-mass spectrometry (GC-MS) method for determining carbon disulfide in workplace air. Methods Samples were collected using the built-in Tenax GR adsorption tube in the portable GC-MS, followed by thermal desorption. The analytes were separated on a DB-1 chromatographic column and detected by a 3D ion trap mass spectrometer, with 1,3,5-tris(trifluoromethyl)benzene used as the internal standard. Qualitative analysis was based on retention time and characteristic ions, and quantitative analysis was performed using the internal standard method. Results The method showed a linear range of 0.034-0.340 mg/m³ with a correlation coefficient of 0.999 4 using the adsorption tube enrichment mode. The detection limit was 0.007 mg/m³, and the lower limit of quantification was 0.022 mg/m³. The average recovery ranged from 97.5% to 104.0%. The within-run and between-run relative standard deviation was 2.7%-10.4% and 8.8%-14.8%, respectively. Conclusion A rapid, green, highly sensitive, and interference-resistant on-site detection method was established. As a supplement to existing national standard methods, this method is suitable for real-time monitoring of carbon disulfide in workplace air and for occupational exposure risk assessment.

In view of the challenges and opportunities presented in the new century and after rational deliberations on five occasions, the completely new model of "hi tech+humanistic solicitude=the green hospital" was put forward and the overall framework of "one line of thought", "two cornerstones", and "three goals" was carefully formulated. In the meantime, all staff members of the hospital were called on to be involved in the "six major activities". As a result, great changes have taken place in the appearance and development of the hospital. It has been proved through practice that "the green hospital" is a successful model conforming to the trends of the times.