Cerebral ischaemic changes in association with the severity of ICA lesions and cerebropetal flow

A Pilot Study of Radiomic Based on Routine CT Reflecting Difference of Cerebral Hemispheric Perfusion

Background

To explore the effectiveness of radiomics features based on routine CT to reflect the difference of cerebral hemispheric perfusion.

Methods

We retrospectively recruited 52 patients with severe stenosis or occlusion in the unilateral middle cerebral artery (MCA), and brain CT perfusion showed an MCA area with deficit perfusion. Radiomics features were extracted from the stenosis side and contralateral of the MCA area based on precontrast CT. Two different region of interest drawing methods were applied. Then the patients were randomly grouped into training and testing sets by the ratio of 8:2. In the training set, ANOVA and the Elastic Net Regression with fivefold cross-validation were conducted to filter and choose the optimized features. Moreover, different machine learning models were built. In the testing set, the area under the receiver operating characteristic (AUC) curve, calibration, and clinical utility were applied to evaluate the predictive performance of the models.

Results

The logistic regression (LR) for the triangle-contour method and artificial neural network (ANN) for the semiautomatic-contour method were chosen as radiomics models for their good prediction efficacy in the training phase (AUC = 0.869, 0.873) and the validation phase (AUC = 0.793, 0.799). The radiomics algorithms of the triangle-contour and semiautomatic-contour method were implemented in the whole training set (AUC = 0.870, 0.867) and were evaluated in the testing set (AUC = 0.760, 0.802). According to the optimal cutoff value, these two methods can classify the vascular stenosis side class and normal side class.

Conclusion

Radiomic predictive feature based on precontrast CT image could reflect the difference of cerebral hemispheric perfusion to some extent.

Perfusion-weighted magnetic resonance imaging in patients with carotid artery disease before and after carotid endarterectomy

OBJECTIVE

The purpose of this study was to investigate the potential of perfusion-weighted magnetic resonance imaging for preoperative and postoperative evaluation of cerebral hemodynamics in patients undergoing carotid endarterectomy for carotid artery stenosis.

METHODS

We examined 26 patients with angiographically proven stenoses (60%-99%) of the internal carotid artery preoperatively. Perfusion imaging studies were performed by bolus-tracking of a dosage of 0.2 mmol/kg body weight of gadolinium diethylenetriaminepentaacetic acid on a 1.5-T scanner using a T2*-weighted fast low-angle shot sequence. The observed signal intensities were converted pixel by pixel into concentration-time curves. In each patient, the hemispheres were compared and the difference between the normalized first moments (NFMs) and the percentage changes of the regional cerebral blood volume (CBV) were calculated. Three months postoperatively, perfusion-weighted magnetic resonance imaging was performed in 13 patients.

RESULTS

In patients with <80% stenosis (n = 10), there was no significant alteration of NFM and regional CBV compared with the contralateral hemisphere (-0.16 +/- 0.7 s, +5.9 +/- 24.6%). In patients with stenoses >or=80% (n = 16), we found an increase in NFM ipsilateral to the stenosis of 1.2 +/- 0.92 s (P < .001) and an increase of CBV of 16.8 +/- 15.2% (P < .005). Three months postoperatively, perfusion parameters were normal in all 13 patients examined.

CONCLUSIONS

Perfusion-weighted magnetic resonance imaging is well suited to evaluate the preoperative and postoperative hemodynamic changes in patients with carotid artery stenosis. This noninvasive, semiquantitative magnetic resonance technique could prove to be a valuable adjunct in identification of patients who might benefit from carotid endarterectomy.