ABSTRACT
Objective:To explore the classification performance of combined model constructed from CT signs combined with radiomics for discriminating COVID-19 pneumonia and other viral pneumonia.Methods:The clinical and CT imaging data of 181 patients with viral pneumonia confirmed by reverse transcription-polymerase chain reaction in 15 hospitals of Yunnan Province from March 2015 to March 2020 were analyzed retrospectively. The 181 patients were divided into COVID-19 group (89 cases) and non-COVID-19 group (92 cases), which were further divided into training cohort (126 cases) and test cohort (55 cases) at a ratio of 7∶3 using random stratified sampling. The CT signs of pneumonia were determined and the radiomics features were extracted from the initial unenhanced chest CT images to build independent and combined models for predicting COVID-19 pneumonia. The diagnostic performance of the models were evaluated using receiver operating characteristic (ROC) analysis, continuous net reclassification index (NRI) calibration curve and decision curve analysis.Results:The combined models consisted of 3 significant CT signs and 14 selected radiomics features. For the radiomics model alone, the area under the ROC curve (AUC) were 0.904 (sensitivity was 85.5%, specificity was 84.4%, accuracy was 84.9%) in the training cohort and 0.866 (sensitivity was 77.8%, specificity was 78.6%, accuracy 78.2%) in the test cohort. After combining CT signs and radiomics features, AUC of the combined model for the training cohort was 0.956 (sensitivity was 91.9%, specificity was 85.9%, accuracy was 88.9%), while that for the test cohort was 0.943 (sensitivity was 88.9%, specificity was 85.7%, accuracy was 87.3%). The AUC values of the combined model and the radiomics model in the differentiation of COVID-19 group and the non-COVID-19 group were significantly different in the training cohort ( Z=-2.43, P=0.015), but difference had no statistical significance in the test cohort ( Z=-1.73, P=0.083), and further analysis using the NRI showed that the combined model in both the training cohort and the test cohort had a positive improvement ability compared with radiomics model alone (training cohort: continuous NRI 1.077, 95 %CI 0.783-1.370; test cohort: continuous NRI 1.421, 95 %CI 1.051-1.790). The calibration curve showed that the prediction probability of COVID-19 predicted by the combined model was in good agreement with the observed value in the training and test cohorts; the decision curve showed that a net benefit greater than 0.6 could be obtained when the threshold probability of the combined model was 0-0.75. Conclusion:The combination of CT signs and radiomics might be a potential method for distinguishing COVID-19 and other viral pneumonia with good performance.
ABSTRACT
Objective To explore the value of T2-mapping imaging in assessment of lumbar dorsal extensors group (multifidus,longissimus and iliocostalis) function before and after exercises in healthy volunteers.Methods Totally 50 healthy young volunteers underwent T2-mapping imaging before and after exercises.T2 value and cross-section area (CSA) of multifidus,longissimus and iliocostalis were measured at the level of L3 and 14 superior border.Differences of CSA and T2 value were compared between left and right side muscles before and after exercises.The correlation between CSA difference and T2 difference before and after exercises was analyzed.Results At the level of L3 and L4 superior border,CSA and T2 value of bilateral multifidus,longissimus and iliocostalis increased after exercises (all P＜0.05).At the level of L3 superior border,CSA after exercises and CSA difference of left multifidus were higher than those of right side (all P＜0.05).Before exercises,there were statistical differences of T2 values on left and right side of longissimus and iliocostalis at the level of L3 superior border and the longissimus at the level of L4 superior border (all P＜0.05).Positive correlations were found between CSA difference and T2 difference on bilateral iliocostalis at the level of L3 and L4 superior border,as well as on bilateral multifidus at the level of L4 superior border (all P ＜0.05).Conclusion T2-mapping imaging can be used to assess the activity state of lumbar dorsal extensors group before and after exercises.
ABSTRACT
Objective To investigate the value of blood oxygenation level dependent(BOLD)fMRI in assessing the functional changes of the lumbar dorsal extensor muscles before and after exercise in healthy young people.Methods The changes of the R2*value of lumbar dorsal extensor group in 30 healthy young volunteers(15 males and 15 females)before and after exercise was prospectively studied.BOLD-fMRI scans were performed on healthy young volunteers before and after exercise, the exercise mode was to perform the upper body flexion and extension movement with a simple Rome stool.The scanned images were processed and analyzed, the cross-sectional area and R2* value of the lumbar dorsal extensor muscles (including the multifidus,the longissimus and the iliocostalis)were measured at the upper margin of the L3 and L4 vertebral body before and after exercise.The paired t test was used to compare CSA and R2*values of muscles before and after loading. The CSA and R2* value of different muscles in different sides were compared by independent sample t test. Pearson correlation analysis was used to analyze the relevance between CSA and R2* in muscle before and after exercise. Results After exercise, the R2* values of multifidus,longissimus and iliocostalis at the upper margin of the L4 vertebral body were[(39.2±8.6),(38.9± 7.7),(41.6±7.8)]Hz,significantly lower than before exercise[(46.1±6.9),(45.3±6.2),(46.0±6.7)]Hz(P<0.01);the changes of R2*values of the muscles between the left and right sides before and after the movements were not statistically significant(P>0.05).The R2*values of longissimus and iliocostalis at the upper margin of the L3 vertebral body were[(44.2±9.1),(46.6±9.3)]Hz,significantly lower than before exercise[(48.6±7.2),(49.7± 6.8)]Hz (P<0.01), but the R2* values of multifidus after loading was (43.9 ± 9.0)Hz, there was no statistical difference compared with before exercise (46.8 ± 6.6)Hz (P>0.05);there was a significant difference in the changes of R2*value before and after the movement between the left and right side of iliocostalis(P<0.05).A significant negative correlation between CSA and R2*value was found in the iliocostalis on the right side at the upper margin of L3 vertebral body and in the multifidus on the left side at the upper margin of L4 vertebral body,and the correlation coefficients were (-0.697,-0.616).Conclusion BOLD-fMRI can be a new way to assess the functional changes of the lumbar dorsal extensor group before and after exercise.