ABSTRACT
Objective:To construct radiomics models of micro-calcification in carotid plaques, and compare their diagnostic values.Methods:Fifty-two patients with large atherosclerotic cerebral infarction admitted to Department of Neurology, Third Affiliated Hospital of Soochow University from May 2017 to November 2019 were enrolled. All patients underwent conventional carotid artery Doppler ultrasound to detect carotid plaques and Micropure? ultrasound to detect micro-calcifications in the plaques. A cross-section image with maximum numbers of micro-calcifications was chosen when there were micro-calcifications in carotid plaques; otherwise, a cross-section image with the largest area of the plaque was chosen. After all images were normalized by Photoshop software, the plaques were delineated as regions of interest using MaZda 4.6 software and 283 texture features of the plaques were automatically extracted. The texture features with the strongest predictive value were selected through consistency analysis (intrclass correlation coefficient [ICC]>0.75), two-sample t-test, Least absolute shrinkage and selection operator (Lasso) regression. The predictive models were constructed by RandomForest (RF) and Support vector machine (SVM) classifiers. The training set and test set were divided by 7: 3 to analyze the classification accuracy. Receiver operating characteristic (ROC) curves were used to calculate the area under the curve (AUC) to evaluate the diagnostic values of the models. Delong test was used to compare the difference between the diagnostic values of the 2 classifiers in test set. Results:A total of 148 plaque images from 52 patients were enrolled, including 104 plaques with micro-calcification and 44 plaques without micro-calcification. Nine texture features were finally selected after ICC analysis, T test and Lasso regression: 5 image gray histogram features were mean, variance, skewness, kurtosis and 99 th percentile (Perc. 99%); 1 autoregressive model feature was Teta3, and 3 wavelet transform features were WavEnLH_s-3, WavEnLH_s-4, and WavEnLH_s-6. With RF classifier, accuracy of the diagnostic model was 0.93, enjoying AUC of 0.92; with SVM classifier, that was 0.91, enjoying AUC of 0.90; Delong test showed that the diagnostic values of the 2 classifiers in test set were significantly different ( Z=1.000, P=0.320). Conclusion:Radiomic models constructed by RF and SVM classifiers can identify micro-calcification in carotid plaques, and the 2 classifiers share equivalent diagnostic values.
ABSTRACT
Objective:To investigate the correlation between the Type D personality and the severity of white matter hyperintensities (WMHs) in patients with cerebral small vessel disease (CSVD).Methods:Consecutive patients with CSVD admitted to the Changzhou First People's Hospital between November 2020 and June 2021 were enrolled prospectively. The patients were scored on the Type D Personality Scale at admission; the scores of negative affectivity (NA) and social inhibition (SI) dimension were calculated respectively. The general data, laboratory examination data and imaging data of the patients were collected. Periventricular and deep WMHs were scored using the Fazekas visual scoring method. The total score 0-2 was defined as low-WMHs (L-WMHs), and 3-6 was defined as high-WMHs (H-WMHs). Multivariate logistic regression analysis was used to determine the independent influencing factor of WMHs. Results:A total of 100 patients with CSVD were enrolled, including 51 males (51%), aged 67.21±9.38 years, 29 (29%) had Type D personality; 56 (56%) were in the L-WMHs group and 44 (44%) were in the H-WMHs group. Univariate analysis showed that the proportion of Type D personality, NA dimension score, the proportion of hypertension, diastolic blood pressure, triglyceride and homocysteine in the H-WMHs group were significantly higher than those in the L-WMHs group (all P<0.05). Multivariate logistic regression analysis showed that NA dimension score (odds ratio [ OR] 18.351, 95% confidence interval [ CI] 2.780-121.135; P=0.003), age ( OR 1.134, 95% CI 1.039-1.238; P=0.005) and hypertension ( OR 7.771, 95% CI 1.525-39.607; P=0.014) were significantly positively correlated with the severity of WMHs, while triglycerides were significantly negatively correlated with the severity of WMHs ( OR 0.306, 95% CI 0.130-0.722; P=0.007). Conclusion:Type D personality is closely associated with the severity of WMHs in patients with CSVD.