Hemodynamically unstable pelvic fracture results from blunt external force and is often accompanied by hypotension. Massive blood transfusion is needed in the case and the mortality rate can be 40%-65%. The key to the early treatment of hemodynamically unstable pelvic fracture lies in bleeding control. Currently, the primary methods of hemostasis include pelvic brace fixation, pre-peritoneal pelvic packing, internal iliac artery ligation, internal iliac artery embolization, etc. However, due to the urgent need for emergency hemostasis and the difficulty in identifying the bleeding sites, hemodynamically unstable pelvic fracture remain a serious challenge for trauma surgeons. Pre-peritoneal pelvic packing used in emergency situations to control the bleeding hemodynamically unstable pelvic fracture can effectively control venous and fracture-site bleeding after pelvic fracture and reduce mortality. Moreover, it is easy and convenient to operate and is especially suitable for cases in which angiographic embolization can not be performed immediately or the patients are hemodynamically extremely unstable. However, there is still a controversy in the clinical practice regarding the selection between pre-peritoneal pelvic packing and other hemostatic methods such as angiographic embolization. To this end, the author reviewed the progress of the researches on the application of pre-peritoneal pelvic packing in emergency hemostasis for hemodynamically unstable pelvic fracture, aiming to provide a reference for its clinical treatment.

Purpose To achieve intelligent detection of acute pulmonary embolism(APE)in CT pulmonary angiography based on the Res2Net attention mechanism network.Materials and Methods Retrospectively included patients with suspected of APE who underwent CT pulmonary angiography examination and were diagnosed as APE at the First Affiliated Hospital of Henan University of Chinese Medicine from February 2015 to May 2023.The dataset was randomly divided into training,validation and test set in a ratio of 7∶2∶1.The model was trained based on the Res2Net network,combined with atrous spatial pyramid pooling and attention mechanism modules,and was performed five-fold cross internal validation.Using the area under the receiver operator characteristic curve,sensitivity and specificity to assess the diagnostic performance of the model.Dice similarity coefficient,precision and intersection over union(IOU)were used to assess the segmentation performance of thrombus on the test set and plot the corresponding curves.The performance of the Res2Net attention mechanism network was compared with the classic U-Net and CE-Net model.Results A total of 303 patients with APE were included in this study.There were 212,61 and 30 cases in the training set,validation set and test set,respectively.The model's area under the curve was 0.95,sensitivity was 0.90,specificity was 1.00,Dice similarity coefficient was 0.86,precision was 0.90,Pos-IOU was 0.78 and Neg-IOU was 1.00,respectively.The parameter curves and radar chart showed that the Res2Net attention mechanism network performed better than the U-Net and CE-Net models.The visualization results of the segmentation comparison showed that the Res2Net attention mechanism network achieved higher precision in segmenting pulmonary artery thrombus.Conclusion The Res2Net attention mechanism network has good performance for detection of APE.

Objective:To establish and validate the diagnostic model of acute pulmonary embolism (APE) based on clinical and laboratory variables.Methods:This retrospective analysis was conducted on patients with suspected APE who underwent CT pulmonary angiography at the First Affiliated Hospital of Henan University of Chinese Medicine between February 2015 and December 2023. The patients were randomly divided into a training set and a validation set at a ratio of 7∶3. Clinical and laboratory data of the enrolled patients were collected, and patients were divided into an APE group and a non-APE group according to CT pulmonary angiography results. In the training set, univariate and multivariate logistic regression as well as Lasso regression were used to identify risk factors for APE, and a diagnostic model was developed and validated. Receiver operating characteristic curves were plotted, and calibration and decision curves were used to assess the performance of the diagnostic model. The diagnostic efficacy of the model was compared with that of the Wells score and the revised Geneva score using the DeLong test.Results:A total of 752 patients were enrolled, aged (64±15) years, including 417 (55.5%) males. The training set included 526 patients and the validation set included 226 patients. The incidence of APE in this cohort was 48.7% (366/752), with 366 cases in the APE group and 386 in the non-APE group. Multivariable logistic regression analysis showed that cyanosis ( OR=8.88, 95% CI 2.04-49.11), elevated neutrophil count ( OR=1.82, 95% CI 1.06-3.15), elevated creatine kinase isoenzyme ( OR=3.45, 95% CI 1.76-6.91), decreased partial pressure of carbon dioxide ( OR=12.88, 95% CI 7.64-22.34), elevated age-adjusted D-dimer ( OR=2.53, 95% CI 1.10-6.20), prolonged thrombin time ( OR=4.08, 95% CI 2.06-8.33), and positive lower limb venous ultrasound for thrombus ( OR=4.39, 95% CI 2.59-7.58) were risk factors associated with APE. The area under the curve ( AUC) of the diagnostic model was 0.92 (95% CI 0.90-0.94) in the training set and 0.92 (95% CI 0.89-0.95) in the validation set. The diagnostic efficacy of this model was superior to that of the Wells score ( AUC: 0.92 vs. 0.63, P<0.01) and the revised Geneva score ( AUC: 0.92 vs. 0.59, P<0.01). Conclusion:The diagnostic model for acute pulmonary embolism constructed based on clinical and laboratory parameters demonstrates excellent diagnostic performance and may facilitate rapid and accurate screening in clinical practice.

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 observe the efficacy of self-guided attention network for detecting responsible lesions related to cerebral palsy(CP)in children with periventricular white matter injury(PVWMI).Methods Totally 383 children with PVWMI were retrospectively enrolled and divided into CP group(n=243)and non-CP group(n=140),while 214 children without obvious brain abnormality on brain MRI were taken as control group.ROI of 4 key anatomical structures related to CP,i.e.centrum semiovale,posterior limb of internal capsule,cerebral peduncle and thalamus were delineated on T1WI,while responsible lesions related to CP within the key anatomical structures were labeled on T2WI,and the images were then registrated and used as input of the networks.ResNet34 network was adopted combined with attention and self-guided networks to train the network for detecting responsible lesions related to CP in children with PVWMI,and their efficacies were evaluated.The optimal network was screened,and its efficacy for segmenting the key anatomical structures was evaluated.Results Self-guided attention network was the optimal network,its area under the curve(AUC)for detecting lesions was 0.794-0.914,and the Dice similarity coefficient for segmenting the key anatomical structures was 0.702-0.764.Conclusion Self-guided attention network could be used for preliminarily detecting responsible lesions related to CP in children with PVWMI.

Objective To observe the efficacy of self-guided attention network for detecting responsible lesions related to cerebral palsy(CP)in children with periventricular white matter injury(PVWMI).Methods Totally 383 children with PVWMI were retrospectively enrolled and divided into CP group(n=243)and non-CP group(n=140),while 214 children without obvious brain abnormality on brain MRI were taken as control group.ROI of 4 key anatomical structures related to CP,i.e.centrum semiovale,posterior limb of internal capsule,cerebral peduncle and thalamus were delineated on T1WI,while responsible lesions related to CP within the key anatomical structures were labeled on T2WI,and the images were then registrated and used as input of the networks.ResNet34 network was adopted combined with attention and self-guided networks to train the network for detecting responsible lesions related to CP in children with PVWMI,and their efficacies were evaluated.The optimal network was screened,and its efficacy for segmenting the key anatomical structures was evaluated.Results Self-guided attention network was the optimal network,its area under the curve(AUC)for detecting lesions was 0.794-0.914,and the Dice similarity coefficient for segmenting the key anatomical structures was 0.702-0.764.Conclusion Self-guided attention network could be used for preliminarily detecting responsible lesions related to CP in children with PVWMI.

Purpose To achieve intelligent detection of acute pulmonary embolism(APE)in CT pulmonary angiography based on the Res2Net attention mechanism network.Materials and Methods Retrospectively included patients with suspected of APE who underwent CT pulmonary angiography examination and were diagnosed as APE at the First Affiliated Hospital of Henan University of Chinese Medicine from February 2015 to May 2023.The dataset was randomly divided into training,validation and test set in a ratio of 7∶2∶1.The model was trained based on the Res2Net network,combined with atrous spatial pyramid pooling and attention mechanism modules,and was performed five-fold cross internal validation.Using the area under the receiver operator characteristic curve,sensitivity and specificity to assess the diagnostic performance of the model.Dice similarity coefficient,precision and intersection over union(IOU)were used to assess the segmentation performance of thrombus on the test set and plot the corresponding curves.The performance of the Res2Net attention mechanism network was compared with the classic U-Net and CE-Net model.Results A total of 303 patients with APE were included in this study.There were 212,61 and 30 cases in the training set,validation set and test set,respectively.The model's area under the curve was 0.95,sensitivity was 0.90,specificity was 1.00,Dice similarity coefficient was 0.86,precision was 0.90,Pos-IOU was 0.78 and Neg-IOU was 1.00,respectively.The parameter curves and radar chart showed that the Res2Net attention mechanism network performed better than the U-Net and CE-Net models.The visualization results of the segmentation comparison showed that the Res2Net attention mechanism network achieved higher precision in segmenting pulmonary artery thrombus.Conclusion The Res2Net attention mechanism network has good performance for detection of APE.

Hemodynamically unstable pelvic fracture results from blunt external force and is often accompanied by hypotension. Massive blood transfusion is needed in the case and the mortality rate can be 40%-65%. The key to the early treatment of hemodynamically unstable pelvic fracture lies in bleeding control. Currently, the primary methods of hemostasis include pelvic brace fixation, pre-peritoneal pelvic packing, internal iliac artery ligation, internal iliac artery embolization, etc. However, due to the urgent need for emergency hemostasis and the difficulty in identifying the bleeding sites, hemodynamically unstable pelvic fracture remain a serious challenge for trauma surgeons. Pre-peritoneal pelvic packing used in emergency situations to control the bleeding hemodynamically unstable pelvic fracture can effectively control venous and fracture-site bleeding after pelvic fracture and reduce mortality. Moreover, it is easy and convenient to operate and is especially suitable for cases in which angiographic embolization can not be performed immediately or the patients are hemodynamically extremely unstable. However, there is still a controversy in the clinical practice regarding the selection between pre-peritoneal pelvic packing and other hemostatic methods such as angiographic embolization. To this end, the author reviewed the progress of the researches on the application of pre-peritoneal pelvic packing in emergency hemostasis for hemodynamically unstable pelvic fracture, aiming to provide a reference for its clinical treatment.

Objective:To establish and validate the diagnostic model of acute pulmonary embolism (APE) based on clinical and laboratory variables.Methods:This retrospective analysis was conducted on patients with suspected APE who underwent CT pulmonary angiography at the First Affiliated Hospital of Henan University of Chinese Medicine between February 2015 and December 2023. The patients were randomly divided into a training set and a validation set at a ratio of 7∶3. Clinical and laboratory data of the enrolled patients were collected, and patients were divided into an APE group and a non-APE group according to CT pulmonary angiography results. In the training set, univariate and multivariate logistic regression as well as Lasso regression were used to identify risk factors for APE, and a diagnostic model was developed and validated. Receiver operating characteristic curves were plotted, and calibration and decision curves were used to assess the performance of the diagnostic model. The diagnostic efficacy of the model was compared with that of the Wells score and the revised Geneva score using the DeLong test.Results:A total of 752 patients were enrolled, aged (64±15) years, including 417 (55.5%) males. The training set included 526 patients and the validation set included 226 patients. The incidence of APE in this cohort was 48.7% (366/752), with 366 cases in the APE group and 386 in the non-APE group. Multivariable logistic regression analysis showed that cyanosis ( OR=8.88, 95% CI 2.04-49.11), elevated neutrophil count ( OR=1.82, 95% CI 1.06-3.15), elevated creatine kinase isoenzyme ( OR=3.45, 95% CI 1.76-6.91), decreased partial pressure of carbon dioxide ( OR=12.88, 95% CI 7.64-22.34), elevated age-adjusted D-dimer ( OR=2.53, 95% CI 1.10-6.20), prolonged thrombin time ( OR=4.08, 95% CI 2.06-8.33), and positive lower limb venous ultrasound for thrombus ( OR=4.39, 95% CI 2.59-7.58) were risk factors associated with APE. The area under the curve ( AUC) of the diagnostic model was 0.92 (95% CI 0.90-0.94) in the training set and 0.92 (95% CI 0.89-0.95) in the validation set. The diagnostic efficacy of this model was superior to that of the Wells score ( AUC: 0.92 vs. 0.63, P<0.01) and the revised Geneva score ( AUC: 0.92 vs. 0.59, P<0.01). Conclusion:The diagnostic model for acute pulmonary embolism constructed based on clinical and laboratory parameters demonstrates excellent diagnostic performance and may facilitate rapid and accurate screening in clinical practice.

Diabetic peripheral neuropathy（DPN） is a neurodegenerative disease of diabetes mellitus involving peripheral nervous system damage， which is characterized by axonal degenerative necrosis， Schwann cell apoptosis and demyelination of nerve myelin sheath as the main pathological features， this disease is highly prevalent and is a major cause of disability in diabetic patients. Currently， the pathogenesis of DPN may be related to oxidative stress， inflammatory response， metabolic abnormality， and microcirculation disorder. The treatment of DPN in modern medicine mainly starts from controlling blood glucose， nourishing nerves and improving microcirculation， which can only alleviate the clinical symptoms of patients， and it is difficult to fundamentally improve the pathological damage of peripheral nerves. Mitochondrial quality control refers to the physiological mechanisms that can maintain the morphology and functional homeostasis of mitochondria， including mitochondrial biogenesis， mitochondrial dynamics， mitochondrial oxidative stress and mitochondrial autophagy， and abnormal changes of which may cause damage to peripheral nerves. After reviewing the literature， it was found that traditional Chinese medicine（TCM） can improve the low level of mitochondrial biogenesis in DPN， maintain the balance of mitochondrial dynamics， inhibit mitochondrial oxidative stress and mitochondrial autophagy， and delay apoptosis of Schwann cells and neural axon damage， which has obvious effects on the treatment of DPN. With the deepening of research， mitochondrial quality control may become one of the potential targets for the research of new anti-DPN drugs， therefore， this paper summarized the research progress of TCM in treating DPN based on four aspects of mitochondrial quality control， with the aim of providing a theoretical research basis for the discovery of new drugs.