Key points are not available for this paper at this time.
Background The relationship between early perihematomal edema (PHE) and hematoma expansion (HE) is unclear. We investigated this relationship in patients with acute spontaneous intracerebral hemorrhage (ICH), using radiomics. Methods In this multicenter retrospective study, we analyzed 490 patients with spontaneous ICH who underwent non-contrast computed tomography within 6 h of symptom onset, with follow-up imaging at 24 h. We performed HE and PHE image segmentation, and feature extraction and selection to identify HE-associated optimal radiomics features. We calculated radiomics scores of hematoma (RadscoresHEA) and PHE (RadscoresPHE) and constructed a combined model (RadscoreHEAPHE). Relationships of the PHE radiomics features or RadscoresPHE with clinical variables, hematoma imaging signs, RadscoresHEA, and HE were assessed by univariate, correlation, and multivariate analyses. We compared predictive performances in the training (n = 296) and validation (n = 194) cohorts. Results ShapeVoxelVolume and ShapeMinorAxisLength of PHE were identified as optimal radiomics features associated with HE. RadscorePHE (odds ratio = 1. 039, p = 0. 032) was an independent HE risk factor after adjusting for the ICH onset time, Glasgow Coma Scale score, baseline hematoma volume, hematoma shape, hematoma density, midline shift, and RadscoreHEA. The areas under the receiver operating characteristic curve of RadscorePHE in the training and validation cohorts were 0. 808 and 0. 739, respectively. After incorporating RadscorePHE, the integrated discrimination improvements of RadscoreHEAPHE in the training and validation cohorts were 0. 009 (p = 0. 086) and −0. 011 (p 0. 001), respectively. Conclusion RadscorePHE, based on ShapeVoxelVolume and ShapeMinorAxisLength of PHE, independently predicts HE, while RadscorePHE did not add significant incremental value to RadscoreHEA.
Zhou et al. (Tue,) studied this question.