Radiomic markers of intracerebral hemorrhage expansion on non-contrast CT: independent validation and comparison with visual markers

Stefan P Haider; Adnan I Qureshi; Abhi Jain; Hishan Tharmaseelan; Elisa R Berson; Tal Zeevi; David J Werring; Moritz Gross; Adrian Mak; Ajay Malhotra; Lauren H Sansing; Guido J Falcone; Kevin N Sheth; Seyedmehdi Payabvash

doi:10.3389/fnins.2023.1225342

Radiomic markers of intracerebral hemorrhage expansion on non-contrast CT: independent validation and comparison with visual markers

Front Neurosci. 2023 Aug 16:17:1225342. doi: 10.3389/fnins.2023.1225342. eCollection 2023.

Authors

Affiliations

¹ Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, United States.
² Department of Otorhinolaryngology, University Hospital of Ludwig-Maximilians-Universität München, Munich, Germany.
³ Zeenat Qureshi Stroke Institute and Department of Neurology, University of Missouri, Columbia, MO, United States.
⁴ Stroke Research Centre, University College London, Queen Square Institute of Neurology, London, United Kingdom.
⁵ Department of Neurology, Yale School of Medicine, New Haven, CT, United States.

^# Contributed equally.

Abstract

Objective: To devise and validate radiomic signatures of impending hematoma expansion (HE) based on admission non-contrast head computed tomography (CT) of patients with intracerebral hemorrhage (ICH).

Methods: Utilizing a large multicentric clinical trial dataset of hypertensive patients with spontaneous supratentorial ICH, we developed signatures predictive of HE in a discovery cohort (n = 449) and confirmed their performance in an independent validation cohort (n = 448). In addition to n = 1,130 radiomic features, n = 6 clinical variables associated with HE, n = 8 previously defined visual markers of HE, the BAT score, and combinations thereof served as candidate variable sets for signatures. The area under the receiver operating characteristic curve (AUC) quantified signatures' performance.

Results: A signature combining select radiomic features and clinical variables attained the highest AUC (95% confidence interval) of 0.67 (0.61-0.72) and 0.64 (0.59-0.70) in the discovery and independent validation cohort, respectively, significantly outperforming the clinical (p_discovery = 0.02, p_validation = 0.01) and visual signature (p_discovery = 0.03, p_validation = 0.01) as well as the BAT score (p_discovery < 0.001, p_validation < 0.001). Adding visual markers to radiomic features failed to improve prediction performance. All signatures were significantly (p < 0.001) correlated with functional outcome at 3-months, underlining their prognostic relevance.

Conclusion: Radiomic features of ICH on admission non-contrast head CT can predict impending HE with stable generalizability; and combining radiomic with clinical predictors yielded the highest predictive value. By enabling selective anti-expansion treatment of patients at elevated risk of HE in future clinical trials, the proposed markers may increase therapeutic efficacy, and ultimately improve outcomes.

Keywords: cerebral hemorrhage; computed tomography; hematoma; machine learning; radiomics.

Abstract

Grants and funding