ABSTRACT
The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.
Subject(s)
Humans , Adult , Imagination , Neural Networks, Computer , Imagery, Psychotherapy/methods , Electroencephalography/methods , Algorithms , Brain-Computer Interfaces , Signal Processing, Computer-AssistedABSTRACT
The background of abdominal computed tomography (CT) images is complex, and kidney tumors have different shapes, sizes and unclear edges. Consequently, the segmentation methods applying to the whole CT images are often unable to effectively segment the kidney tumors. To solve these problems, this paper proposes a multi-scale network based on cascaded 3D U-Net and DeepLabV3+ for kidney tumor segmentation, which uses atrous convolution feature pyramid to adaptively control receptive field. Through the fusion of high-level and low-level features, the segmented edges of large tumors and the segmentation accuracies of small tumors are effectively improved. A total of 210 CT data published by Kits2019 were used for five-fold cross validation, and 30 CT volume data collected from Suzhou Science and Technology Town Hospital were independently tested by trained segmentation models. The results of five-fold cross validation experiments showed that the Dice coefficient, sensitivity and precision were 0.796 2 ± 0.274 1, 0.824 5 ± 0.276 3, and 0.805 1 ± 0.284 0, respectively. On the external test set, the Dice coefficient, sensitivity and precision were 0.817 2 ± 0.110 0, 0.829 6 ± 0.150 7, and 0.831 8 ± 0.116 8, respectively. The results show a great improvement in the segmentation accuracy compared with other semantic segmentation methods.
Subject(s)
Humans , Kidney Neoplasms/diagnostic imaging , Neural Networks, Computer , Specimen Handling , Tomography, X-Ray ComputedABSTRACT
Objective:To investigate the effect of enhancing the strength of the hamstring on the stability of the knee joint.Methods:Thirty patients with anterior cruciate ligament (ACL) tears were randomly divided into a training group ( n=15) and a control group ( n=15). After the injury′s edema stage, all of the subjects received the standard 6-stage rehabilitation training for ACL injury, including isokinetic exercise, isometric tension and contraction exercise, single or bipedal jumping, proprioception exercises and cardiovascular exercise. On the basis of that standard training, additional hamstring strengthening training was given to the training group. It involved three sessions of weight-bearing flexion of the knee joint six to eight times, at least five times a week for three months. All of the subjects underwent the passive relaxation test (PRT), knee function scoring (Lysholm scores) and weight-bearing MRI before and within 1 month after the training. Anterior shift of the tibia (TAS) was measured using weight-bearing magnetic resonance imaging (MRI). Results:Before the training there were no significant differences between the groups in terms of average PRT or Lysholm scores. After the training, the average PRT score in neither group had improved significantly. The average Lysholm scores of the training and control groups were not significantly different either, though both groups′ averages had improved significantly compared with before the training. The average tibial shifts were also significantly smaller than before the training, with the training group′s average significantly smaller than that of the control group.Conclusion:Increasing hamstring muscle strength can reduce tibial anteversion in the weight-bearing upright position and improve the stability of the knee joint after ACL injury.
ABSTRACT
Objective To investigate the correlation between pathological features of clear cell renal cell carcinoma(ccRCC) and Fuhrman classification with enhanced MDCT image findings.Methods CT findings and clinical data of 108 ccRCC patients confirmed by pathology were collected and the CT values of tumor parenchyma,ipsilateral renal cortex and aorta were measured and absolute and relative CT values of tumor parenchyma were calculated.According to the Fuhrman pathological classification,all cases were divided into low grade (Fuhrman Ⅰ-Ⅱ) and high-grade (Fuhrman Ⅲ-Ⅳ) groups and the CT findings included CT attenuation of four phases and the absolute and relative enhancement values were compared respectively.Results Low-grade tumors differed from high-grade tumors with lower attenuation on unenhanced CT scan,absolute enhancement values in three phases were higher,relative enhancement values were also higher in arterial and venous phases,the difference were statistically significant (P＜0.05).A1 (r =-0.311,P＜0.05) and the absolute enhancement in delay(r =-0.310,P＜0.05) and nephrographic phase(r =-0.304,P＜0.05) were negatively correlated to the Fuhrman grade,A 1 (AUC =0.707),C1 (AUC =0.705) and corticomedullary phase absolute enhancement (AUC =0.675) had the more larger AUCs.Conclusion The MDCT enhancement index of ccRCC is negatively correlated with pathological Fuhrman grading which is helpful to predict the grade of ccRCC before operation and has certain clinical values.
ABSTRACT
Medical imaging is an interdisciplinary subject closely related to clinical and pathological subject. Its clinical reading skills' training has become the focus of postgraduate teaching. In the process of clinical teaching, the interactive reading mode of problem-based learning (PBL) combined with multi-disci-plinary team (MDT) was introduced into clinical reading meeting. The tutors chose the reading cases proved by pathology; designed in-depth issues step by step for execution of PBL teaching; guided postgraduates to delineate imaging signs and propose the diagnostic results, evidences and differential diagnoses according to the step from localizing to qualitative and then to pathological diagnosis;then guided postgraduates to attend in-depth case analysis of MDT and analyze the correlation or inconsistency between the imaging diagnosis and clinical and pathological diagnosis; exercise document retrieval and verbalization, multimedia design, and writing level of the records of the reading cases and papers. The interactive reading mode of PBL com-bined with MDT has achieved significant effects, which is worthy of further exploration and promotion.
ABSTRACT
Through occupying binding site of glycoprotein IIb/IIIa receptor,platelet glycoprotein IIb/IIIa inhibitor (GPI)inhibit the combination of fibrinogen and the receptor,then inhibit platelet aggregation.GPI is the most powerful anti-platelet drug and possesses application value in ACS now.This article made an overview on the newest research progress of safety and effectiveness of GPI in ACS.
ABSTRACT
Objective To assess the relationship between gastric carcinoma perfusion imaging parameters with the multislice spi-ral CT (MSCT)and the tumor angiogenesis(MVD,VEGF).Methods (1)33 patients with gastric cancer were carried on perfusion CT scanning in the suspected lesions,and compared with operation and histological result.MSCT perfusion parameters tumor,such as local blood flow (BF),blood volume (BV),mean transit time of contrast agent (MTT),permeability surface (PS),were recor-ded,and compared with clinical pathological data.(2)27 patients of 33 cases which CT perfusion plane matching with operation pa-thology specimens performed with tumor microvessel density (MVD),vascular endothelial growth factor (VEGF)monoclonal anti-body immunohistochemical examination of MVD,the most intensive areas of high power (×200 HP)field counted,and VEGF stai-ning positive judged.Results Achievement ratio of gastric carcinoma MSCT perfusion imaging was 84.85% (28/33).The average value of BF,BV,MTT and PS were 63.658 ± 18.305,7.5 1 1 ± 2.427,1 1.952 ± 4.325 and 31.81 7 ± 13.533,respectively,and MVD was 37.7 ± 11.1/200 HP (range:13-60).VEGF was positive in 16 cases,negative in 11 cases.Gastric carcinoma undifferentiated group perfusion parameter PS value (35.1 5 ± 12.74 )and MVD (40.53 ± 10.66 )were higher than the differentiation group (23.90 ± 12.71 and 31.13 ± 9.82 )(P < 0.05 ),but BF,BV,MTT not statistically significant;Differences of CT perfusion parameters and MVD were not significant statistically between invasive serosa and noninvasive ;PS value (36.65± 12.80)of lymph node metastasis was greater than without metastasis(22.70 ± 1 1.1 5 )(P <0.01 ),the other was no significant difference;TNM staging Ⅲ,Ⅳ phase group of BF value (69.56 ± 1 6.49),PS value (34.90 ± 12.80)and MVD value (40.74 ± 10.53)were higher than Ⅰ,Ⅱ Group (49.63 ± 1 5.04),(24.50 ± 13.13)and (30.63 ± 9.61)(P <0.01).Spearman correla-tion analysis in confidence (two tails)of 0.01 was statistically significant between MVD in tumor tissues and gastric cancer MSCT perfusion parameters of BF (r=0.404)and MTT (r=0.371),whereas BV and PS were no significance.The regression equation of MVD with BF and MTT:MVD =1 6.602+0.1 50XBF +0.967XMTT,model checking of F values was 6.62,P =0.003.Conclusion The gastric carcinoma multi-slice CT perfusion imaging parameters BF,MTT and MVD,VEGF(+)was positive correlation, MSCT perfusion imaging parameters reflects tumor VEGF positive expression of gastric carcinoma.
ABSTRACT
Objective:To discuss the CT analysis and differential diagnosis of the infrequent diseases from thymus.Methods:26 patients with infrequent diseases from thymus,confirmed by biopsies,surgical-pathologic results and clinical treatments,were analyzed through the results of operation,pathology and the CT image.Results:Various infrequent diseases from thymus have respective CT performance.Conclusion:CT is an important method for diagnosis of the infrequent diseases from thymus.It is of great value for differential diagnosis.
ABSTRACT
Objective To summarize and analysis CT characteristics of traumatic adrenal hematomas.Methods There were 22 cases ofadrenal hematomas.The size, distribution and density of the adrenal hematomas on CT scanning, and the complications of other visceralinjury were analysed.Results 23 adrenal hematomas were found in 22 cases, of them,16 were in right,6 in left and 1 in bilateral. Conclusion CT has high value in diagnosis of the adrenal hematomas.