Objective To develop a method for accurate identification of multiscale carotid plaques in ultrasound images.Methods We proposed a two-stage carotid plaque detection method based on deep convolutional neural network(SM-YOLO).A series of algorithms such as median filtering,histogram equalization,and Gamma transformation were used to preprocess the dataset to improve image quality.In the first stage of the model construction,a candidate plaque set was built based on the YOLOX_l target detection network,using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes.In the second stage,the Histogram of Oriented Gradient(HOG)features and Local Binary Pattern(LBP)features were extracted and fused,and a Support Vector Machine(SVM)classifier was used to screen the candidate plaque set to obtain the final detection results.This model was compared quantitatively and visually with several target detection models(YOLOX_l,SSD,EfficientDet,YOLOV5_l,Faster R-CNN).Results SM-YOLO achieved a recall of 89.44%,an accuracy of 90.96%,a F1-Score of 90.19%,and an AP of 92.70%on the test set,outperforming other models in all performance indicators and visual effects.The constructed model had a much shorter detection time than the Faster R-CNN model(only one third of that of the latter),thus meeting the requirements of real-time detection.Conclusion The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

Objective To establish a deep learning model for testing the feasibility of combining magnetic resonance imaging(MRI)deep learning features with clinical features for preoperative prediction of cytokeratin 19(CK19)status of hepatocellular carcinoma(HCC).Methods A retrospective experiment was conducted based on the data of 116 HCC patients with confirmed CK19 status.A single sequence multi-scale feature fusion deep learning model(MSFF-IResnet)and a multi-scale and multi-modality feature fusion model(MMFF-IResnet)were established based on the hepatobiliary phase(HBP),diffusion weighted imaging(DWI)sequences of enhanced MRI images,and the clinical features significantly correlated with CK19 status.The classification performance of the models were evaluated to assess the effectiveness of the deep learning models for predicting CK19 status of HCC before surgery.Results Multivariate analysis showed that an increased neutrophil-to-lymphocyte ratio(P=0.029)and incomplete tumor capsule(P=0.028)were independent predictors of CK19 expression in HCC.The deep learning models improved by multi-scale feature fusion and multi-modality feature fusion methods achieved better classification results than the traditional machine learning models and baseline models,and the final MMFF-IResnet model showed the best classification performance with an AUC of 84.2%,an accuracy of 80.6%,a sensitivity of 80.1%and a specificity of 81.2%.Conclusion The multi-scale and multi-modality feature fusion model based on MRI and clinical parameters is capable of predicting CK19 status of HCC,demonstrating the feasibility of combining deep learning methods with MRI and clinical features for preoperative prediction of CK19 status.

Objective To develop a method for accurate identification of multiscale carotid plaques in ultrasound images.Methods We proposed a two-stage carotid plaque detection method based on deep convolutional neural network(SM-YOLO).A series of algorithms such as median filtering,histogram equalization,and Gamma transformation were used to preprocess the dataset to improve image quality.In the first stage of the model construction,a candidate plaque set was built based on the YOLOX_l target detection network,using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes.In the second stage,the Histogram of Oriented Gradient(HOG)features and Local Binary Pattern(LBP)features were extracted and fused,and a Support Vector Machine(SVM)classifier was used to screen the candidate plaque set to obtain the final detection results.This model was compared quantitatively and visually with several target detection models(YOLOX_l,SSD,EfficientDet,YOLOV5_l,Faster R-CNN).Results SM-YOLO achieved a recall of 89.44%,an accuracy of 90.96%,a F1-Score of 90.19%,and an AP of 92.70%on the test set,outperforming other models in all performance indicators and visual effects.The constructed model had a much shorter detection time than the Faster R-CNN model(only one third of that of the latter),thus meeting the requirements of real-time detection.Conclusion The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

Objective To establish a deep learning model for testing the feasibility of combining magnetic resonance imaging(MRI)deep learning features with clinical features for preoperative prediction of cytokeratin 19(CK19)status of hepatocellular carcinoma(HCC).Methods A retrospective experiment was conducted based on the data of 116 HCC patients with confirmed CK19 status.A single sequence multi-scale feature fusion deep learning model(MSFF-IResnet)and a multi-scale and multi-modality feature fusion model(MMFF-IResnet)were established based on the hepatobiliary phase(HBP),diffusion weighted imaging(DWI)sequences of enhanced MRI images,and the clinical features significantly correlated with CK19 status.The classification performance of the models were evaluated to assess the effectiveness of the deep learning models for predicting CK19 status of HCC before surgery.Results Multivariate analysis showed that an increased neutrophil-to-lymphocyte ratio(P=0.029)and incomplete tumor capsule(P=0.028)were independent predictors of CK19 expression in HCC.The deep learning models improved by multi-scale feature fusion and multi-modality feature fusion methods achieved better classification results than the traditional machine learning models and baseline models,and the final MMFF-IResnet model showed the best classification performance with an AUC of 84.2%,an accuracy of 80.6%,a sensitivity of 80.1%and a specificity of 81.2%.Conclusion The multi-scale and multi-modality feature fusion model based on MRI and clinical parameters is capable of predicting CK19 status of HCC,demonstrating the feasibility of combining deep learning methods with MRI and clinical features for preoperative prediction of CK19 status.

OBJECTIVE To evaluate the effectiveness， safety， economy， innovation， suitability and accessibility of recombinant Mycobacterium tuberculosis fusion protein （EC）， and to provide evidence for selecting skin detection methods for tuberculosis infection diagnosis and auxiliary diagnosis of tuberculosis. METHODS The effectiveness and safety of EC compared with purified protein derivative of tuberculin （TB-PPD） were analyzed by the method of systematic review. Cost minimization analysis， cost-effectiveness analysis and cost-utility analysis were used to evaluate the short-term economy of EC compared with TB-PPD， and cost-utility analysis was used to evaluate the long-term economy. The evaluation dimensions of innovation， suitability and accessibility were determined by systematic review and improved Delphi expert consultation， and the comprehensive score of EC and TB-PPD in each dimension were calculated by the weight of each indicator. RESULTS The scores of effectiveness， safety， economy， innovation and suitability of EC were all higher than those of TB-PPD. The affordability scores of the two drugs were consistent， while the availability score of EC was lower than those of TB-PPD. After considering dimensions and index weight， the scores of effectiveness， safety， economy， innovation， suitability， accessibility and the comprehensive score of EC were all higher than those of TB-PPD. CONCLUSIONS Compared with TB-PPD， EC performs better in all dimensions of effectiveness， safety， economy， innovation， suitability and accessibility. However， it is worth noting that EC should further improve its availability in the dimension of accessibility.

OBJECTIVE: To investigate the consistency and diagnostic performance of magnetic resonance imaging (MRI) for detecting microvascular invasion (MVI) of hepatocellular carcinoma (HCC) and the validity of deep learning attention mechanisms and clinical features for MVI grade prediction. METHODS: This retrospective study was conducted among 158 patients with HCC treated in Shunde Hospital Affiliated to Southern Medical University between January, 2017 and February, 2020. The imaging data and clinical data of the patients were collected to establish single sequence deep learning models and fusion models based on the EfficientNetB0 and attention modules. The imaging data included conventional MRI sequences (T₁WI, T₂WI, and DWI), enhanced MRI sequences (AP, PP, EP, and HBP) and synthesized MRI sequences (T1mapping-pre and T1mapping-20 min), and the high-risk areas of MVI were visualized using deep learning visualization techniques. RESULTS: The fusion model based on T1mapping-20min sequence and clinical features outperformed other fusion models with an accuracy of 0.8376, a sensitivity of 0.8378, a specificity of 0.8702, and an AUC of 0.8501 for detecting MVI. The deep fusion models were also capable of displaying the high-risk areas of MVI. CONCLUSION The fusion models based on multiple MRI sequences can effectively detect MVI in patients with HCC, demonstrating the validity of deep learning algorithm that combines attention mechanism and clinical features for MVI grade prediction.
Humans ; Carcinoma, Hepatocellular ; Retrospective Studies ; Liver Neoplasms ; Magnetic Resonance Imaging ; Algorithms

Antipyretic-analgesics are currently one of the most prescribed drugs in children.The clinical application of antipyretic-analgesics for children in our country still have irrational phenomenon, which affects the therapeutic effect and even poses hidden dangers to the safety of children.In this paper, suggestions were put forward from the indications, dosage form/route, dosage suitability, pathophysiological characteristics of children with individual differences and drug interactions in the symptomatic treatment of febrile children, so as to provide reference for the general pharmacists when conducting prescription review.

Objective:To explore the effect of setting up an internal-cross disciplinary team (ICDT) in the intensive care unit (ICU) on a new model of overall treatment for patients with chronic critical illness (CCI).Methods:A 60-year-old male patient with acute exacerbation of chronic obstructive pulmonary disease (AECOPD) admitted to ICU in the Second Affiliated Hospital of Fujian Medical University was introduced. The role of ICDT composed of physicians, nurses, respiratory therapists, physiotherapists, clinical dietitians and patients' family members in ventilator withdrawal and super-early rehabilitation was analyzed in this case.Results:The patient was diagnosed as AECOPD, type Ⅱ aspiration penumonia respiratory failure, septic shock. The ICDT in ICU carried out early rehabilitation treatment for the patient on the basis of traditional infection control and supportive treatment. Under the care of the ICDT, peripheral blood white blood cell count (WBC), neutrophil count (NEU), procalcitonin (PCT), arterial partial pressure of carbon dioxide (PaCO 2), maximum inspiratory pressure (MIP), maximum expiratory pressure (MEP), right excursion of diaphragm, sputum viscosity, tidal volume (VT) and respiratory rate (RR) were improved. Subsequently, the ventilator mode was gradually changed and the ventilator parameters were down-regulated. The ventilator was successfully weaned on the 10th day of treatment. After weaning, the patient's bedside pulmonary function indicators improved, and he was transferred out of ICU on the 15th day of treatment and discharged on the 20th day. The mental state of the patients was good and the quality of life was greatly improved in CCI outpatient follow-up. Conclusions:ICDT cooperation is very important for monitoring and treatment of CCI patients, which is beneficial to the super-early rehabilitation and prognosis improvement of critically ill patients.

Objective: To investigate the clinical outcomes and radiological results of arthroscopic autologous scapular spine bone graft transplant to treat shoulder recurrent instability. Methods: Data of 27 patients diagnosed as shoulder recurrent instability with the bone defect of 10%-15% from July 2016 to August 2018 who were treated by arthroscopic autologous scapular spine bone graft transplant were retrospectively analyzed. There were 20 males and 7 females with an average age of 30.8 years old (range, 19-50). The bone loss of the glenoid was 10%-15%. The time between the first dislocation and the surgery was 24.1±15.8 months. The patients were treated with arthroscopic autologous scapular spine bone graft transplant. Postoperatively the affected shoulder was immobilized by the abduction brace for 6 weeks, after that the passive motion was applied. Strengthening exercise began at 10-12 weeks and sports was allowed after 6 months. Constant-Murley score and the Disabilities of Arm, Shoulder and Hand (DASH) score were used to evaluate the shoulder function, and visual analogue score (VAS) score was used to evaluate the degree of pain. Computed tomography scans were obtained one week post-operation and at the latest follow-up, from which the length, width, height and volume of the bone graft were measured and the absorption rate of the bone graft was calculated. The subjective satisfaction degree of patients at the latest follow-up was also recorded. Results: All 27 patients were followed up for 19.8 months (range, 13-39 months). No infection or neurovascular injury was identified. At the latest follow-up, the Constant-Murley score was 85.15±5.62 (range, 76-94), the DASH score 13.39±5.51 (range, 3.19-21.95) and the VAS score 1.29±0.45 (range, 1-2), thus all of those were improved significantly compared to those of pre-operation. At the latest follow-up, the anterior flexion was 153°±24°, lateral rotation by side 38°±21°, internal rotation 70°±21°, and abduction was 139°±18°. At the latest follow-up, the absorption rate of the bone graft was 46.1%±20.6% (range, 24.0%-71.7%). Among all the 27 patients, 19 patients considered the outcome as very good, and 6 patients considered as good, 2 patients fair. Conclusion Arthroscopic autologous scapular spine bone graft transplant could successfully treat shoulder recurrent instability with glenoid bone loss at 10%-15%. This technique could achieve satisfactory clinical results, improve glenohumeral stability, decrease the re-dislocation rate.

Objective:To compare the accuracy and generalized robustness of three predictive models of knowledge-based treatment strategies for radiotherapy for optimized model selection.Methods:The clinical radiotherapy plans of 45 prostate cancer (PC) cases and 25 nasopharyngeal cancer (NPC) cases were collected, and analyzed using three models (Z, L and S model), proposed by Zhu et al, Appenzoller et al and Shiraishi et al, respectively, to predict the dose-volume histogram (DVH) of bladder and rectum on PC cases and that of left and right parotid on NPC cases. The prediction error was measured by the difference of area under the predicted DVH and the clinical DVH curves (|V (pre_DVH)-V (clin_DVH)|), where a smaller prediction error implies a greater prediction accuracy. The accuracies of these three models were compared on the single organ at risk (OAR), and the generalized robustness of models was evaluated and compared by calculating the standard deviation of the prediction accuracy on different OAR. Results:For bladder and rectum, the prediction error of L model (0.114 and 0.163, respectively) was significantly higher than those values of Z and S models (≤0.071, P<0.05); for left parotid gland, the predicted error of S model (0.033) did not present significant difference from those values of Z and L models (≤0.025, P>0.05); for right parotid gland, S model (0.033) demonstrated significantly higher prediction error than those of Z and L models (≤0.028, P<0.05). Regarding different OAR, S model showed a lower standard deviation of prediction accuracy when comparing to Z and L models (0.016, 0.018 and 0.060, respectively). Conclusions:In the prediction of DVH in bladder and rectum of PC, Z and S models were more accurate than L model. In contrast, Z and L models demonstrated higher accuracy than S model in the prediction of left and right parotid glands of NPC. In respect to different OAR, the generalized robustness of S model was superior than the other two models.