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

Cancer-associated fibroblasts (CAFs) is considered as a key factor for the severely limited efficacy in tumor radiotherapy. CAFs, as the primary stromal cells in the tumor microenvironment, can lead to tumor radiotherapy resistance by secreting a series of pro-tumor cytokines and nutrients, inhibiting anti-tumor immune response and remodeling extracellular matrix. Some progress has been made in the study of targeted CAFs sensitization radiotherapy, but the relevant study system is still imperfect. Therefore, a systematic exploration of the role of CAFs in tumor radiotherapy resistance and CAFs targeted therapy strategies can provide a basis for improving the current status of tumor radiotherapy resistance.

Objective To analyze the effect of the changes of hospital diagnosis and treatment mode on the treatment time in patients with acute ischemic stroke before and after the establishment of Cerebrovascular Disease Center. Methods A total of 103 consecutive patients with acute ischemic stroke admitted to the Department of Neurology,Changhai Hospital,the Second Military Medical University between June 2008 and December 2012 were enrolled retrospectively. Thirty-one of them were excluded because of incomplete medical records. Finally,72 patients were enrolled as a control group and received series diagnosis and treatment mode. A total of 210 consecutive patients with acute ischemic stroke admitted to the Cerebrovascular Disease Center,Changhai Hospital,the Second Military Medical University from September 2013 to February 2015 were enrolled retrospectively. Thirteen patients were excluded (4 patients with recurrent transient ischemic attack were treated with recombinant tissue-type plasminogen activator,9 without complete data were treated with intravenous thrombolysis),197 were enrolled as an observation group finally,and they were received series diagnosis and treatment mode. The patients of both groups were visited within 4. 5 h after onset and received rt-PA treatment. The time-consuming changes of each time period from onset-to-door,door-to-imaging,imaging-to-needle,door-to-needle,and onset-to-needle time between the control group and the observation group were compared and analyzed. Results Compared with the control group,the door-to-imaging,imaging-to-needle,door-to-needle and onset-to-needle time were significantly shorter in the observation group. There were significant difference between the 2 groups (24 ± 12 min vs. 60 ± 20 min,27 ± 12 min vs. 62 ± 31 min,51 ± 17 min vs. 122 ± 52 min,and 153 ± 69 min vs. 230 ± 81 min,all P < 0. 01). There was no significant difference for onset-to-door time between the observation group and the control group (P > 0. 05). Conclusion The establishment of cerebral vascular disease center and the improvement of the processes have shortened the treatment time in patients with acute ischemic stroke within time window. The time from onset-to-door is still longer,and the propaganda and education of stroke should be strengthened.