Radiomics features of DSC-PWI in time dimension may provide a new chance to identify ischemic stroke

Abstract

Ischemic stroke has become a severe disease endangering human life. However, few studies have analyzed the radiomics features that are of great clinical significance for the diagnosis, treatment, and prognosis of patients with ischemic stroke. Due to sufficient cerebral blood flow information in dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) images, this study aims to find the critical features hidden in DSC-PWI images to characterize hypoperfusion areas (HA) and normal areas (NA). This study retrospectively analyzed 80 DSC-PWI data of 56 patients with ischemic stroke from 2013 to 2016. For exploring features in HA and NA,13 feature sets (F _method ) were obtained from different feature selection algorithms. Furthermore, these 13 F _method were validated in identifying HA and NA and distinguishing the proportion of ischemic lesions in brain tissue. In identifying HA and NA, the composite score (CS) of the 13 F _method ranged from 0.624 to 0.925. F _Lasso in the 13 F _method achieved the best performance with mAcc of 0.958, mPre of 0.96, mAuc of 0.982, mF1 of 0.959, and mRecall of 0.96. As to classifying the proportion of the ischemic region, the best CS was 0.786, with Acc of 0.888 and Pre of 0.863. The classification ability was relatively stable when the reference threshold (RT) was <0.25. Otherwise, when RT was >0.25, the performance will gradually decrease as its increases. These results showed that radiomics features extracted from the Lasso algorithms could accurately reflect cerebral blood flow changes and classify HA and NA. Besides, In the event of ischemic stroke, the ability of radiomics features to distinguish the proportion of ischemic areas needs to be improved. Further research should be conducted on feature engineering, model optimization, and the universality of the algorithms in the future.

Keywords: DSC-PWI; feature selection; hypoperfusion area; ischemic stroke; radiomics.

Figure 1

The flowchart of the proposed method in this study. (A) Shows the process of preprocessing images and making ROIs of HA and NA, wherein the red area is HA and the green is NA. (B–D) Show the process of computing radiomics features, outstanding feature selection, and evaluating the performance of feature sets.

Figure 2

The information on significant features and 128 outstanding features. (A,B) Show the counts and p-values of significant features in each radiomics feature group; (C,D) show the time values of the 128 selected features and their counts in each radiomics feature group. The orange box in (B) indicates the distribution range of 25–75% p-values; The long horizontal line '—' above the box indicates 1.5 times the interquartile range value (1.5 IQR), and the discrete points above the short horizontal line are abnormal points.

Figure 3

The performance of each F_typeand F_allon the ten models. (A–E) Show the five indexes (Acc, Pre, Auc, F1, Recall) of F_typeand F_all, and (F) show the coefficients H_typeof them.

Figure 4

The performance of 13 feature sets on the ten models. (A–E) Show the five index (Acc, Pre, Auc, F1, Recall) results, and (F) shows the corresponding CS.

Figure 5

The information of samples and F${}_{RT\text{\_}S}^{{}^{\prime }}$. (A) Shows the distribution of positive samples with ranging S and RT and the features in F${}_{RT\text{\_}S}^{{}^{\prime }}$, and (B–D) show the selected features under different RT values when S = 3, 4, and 5 respectively, wherein blue indicates that the corresponding features are selected.

Figure 6

The five indexes of F${}_{RT\text{\_}S}^{{}^{\prime }}$ with S = 3 on the ten models, wherein the dark purple lines represent the mean indexes (mAcc, mPre, mAuc, mF1, mRecall), and the other colors represent the performance of the ten models.

Figure 7

The five indexes of F${}_{RT\text{\_}S}^{{}^{\prime }}$ with S = 4 on the ten models, wherein the dark purple lines represent the mean indexes (mAcc, mPre, mAuc, mF1, mRecall), and the other colors represent the performance of the ten models.

Figure 8

The five indexes of F${}_{RT\text{\_}S}^{{}^{\prime }}$ with S = 5 on the ten models, wherein the dark purple lines represent the mean indexes (mAcc, mPre, mAuc, mF1, mRecall), and the other colors represent the performance of the ten models.

Figure 9

The box plots of the five index under the three situation (S = 3–5). (A–E) The box plots of mACC, mPre, mAuc, mF1, and mRecall in the three situations, respectively. (F) The relationship between CS and RT at varying S.

Figure 10

The difference of HA and NA in the DSC-PWI image. (A) The ROIs of HA and NA in the DSC-PWI image, the HA is shown in red and the NA is shown in green. (B) The mean time-intensity curve I(t) of HA and NA, the black represents the mean I(t) of HA, and the orange is that of NA.