Automated cerebral infarct volume measurement in follow-up noncontrast CT scans of patients with acute ischemic stroke

Abstract

Background and purpose: Cerebral infarct volume as observed in follow-up CT is an important radiologic outcome measure of the effectiveness of treatment of patients with acute ischemic stroke. However, manual measurement of CIV is time-consuming and operator-dependent. The purpose of this study was to develop and evaluate a robust automated measurement of the CIV.

Materials and methods: The CIV in early follow-up CT images of 34 consecutive patients with acute ischemic stroke was segmented with an automated intensity-based region-growing algorithm, which includes partial volume effect correction near the skull, midline determination, and ventricle and hemorrhage exclusion. Two observers manually delineated the CIV. Interobserver variability of the manual assessments and the accuracy of the automated method were evaluated by using the Pearson correlation, Bland-Altman analysis, and Dice coefficients. The accuracy was defined as the correlation with the manual assessment as a reference standard.

Results: The Pearson correlation for the automated method compared with the reference standard was similar to the manual correlation (R = 0.98). The accuracy of the automated method was excellent with a mean difference of 0.5 mL with limits of agreement of -38.0-39.1 mL, which were more consistent than the interobserver variability of the 2 observers (-40.9-44.1 mL). However, the Dice coefficients were higher for the manual delineation.

Conclusions: The automated method showed a strong correlation and accuracy with the manual reference measurement. This approach has the potential to become the standard in assessing the infarct volume as a secondary outcome measure for evaluating the effectiveness of treatment.

Fig 1.

Illustration of the automated CIV segmentation pipeline. This figure shows an infarct in the right hemisphere in a 6-day follow-up CT. A, The unprocessed NCCT. B, A seed point is positioned within the infarcted area by an observer. C, Determination of the midline. D, Segmentation of the ventricles, E, The final segmentation representing the CIV.

Fig 2.

Example of incorrect automated segmentation due to hemorrhage and erroneous midline determination. A, NCCT scan of a patient with a midline shift. The blue line indicates the midline determined by the algorithm. The hemorrhage is indicated by the white arrow. B, The infarcted area delineated by observer 1. C, Incorrect outcome of automated segmentation. The hemorrhage is unrecognized as infarct, and the infarcted tissue is shifted over the original midline. This shift results in underestimation of the CIV.

Fig 3.

Example of incorrect automated segmentation due to multiple infarcts. A, NCCT scan of a patient with multiple infarcts, 2 new infarcts (black arrows) and 1 old infarct (white arrow). B, The infarcted area delineated by observer 1. C, Incorrect outcome of automated segmentation. The old infarct and one of the new infarcts are unrecognized as infarcts. As a result, the automated segmentation underestimates the CIV.